large language models- TeleChat to Xing4: Advancing Frontier Agentic Models on Domestic Chips and Frameworks · 2026-11-17 · 162 upvotes
- Advances in Agentic Computer Graphics · 2026-11-01 · 148 upvotes
- InclusionMed: Benchmarking AI for Inclusive Healthcare · 2026-11-16 · 104 upvotes · code
- AscendGYM: A Cost-Aware Kernel Optimization Benchmark for Real-World Workloads on Ascend NPUs · 2026-11-13 · 92 upvotes · code
- Weight-Space Programming Doesn't Need Transformers · 2026-11-17 · 55 upvotes · code
- CodeCap-Bench: Can Code Serve as a Good Video Caption? · 2026-10-27 · 50 upvotes
- Factorized MLLM Embeddings for Composed Image Retrieval · 2026-11-03 · 47 upvotes · code
- ToolSpace: Scaling Tool-Centric Environment Synthesis for Long-Horizon Agents · 2026-11-03 · 45 upvotes · code
- Latent Reasoning in Continuous Space for Unified Multimodal Models · 2026-10-30 · 45 upvotes · code
- InteractiveWorld: A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants · 2026-10-25 · 44 upvotes · code
- PhysLoop: Harnessing LLMs' Physics Awareness for Self-Improving Video Generation Models · 2026-11-12 · 42 upvotes · code
- EvoMemState: Evolving Memory State for Personal Agents · 2026-11-02 · 36 upvotes · code
- VideoMemBench: How Well Do MLLMs Remember in Video Conversations? · 2026-10-29 · 36 upvotes · code
- LLMs Don't Know What They Know: Benchmarking Temporal Self-Knowledge for Financial Backtesting · 2026-11-04 · 35 upvotes
- Incentivizing Self-Learning in Large Language Models via Reinforcement Learning · 2026-10-29 · 34 upvotes
- Retrieval Augmented Generation Compositionality · 2026-10-21 · 33 upvotes · code
- A Broader Look into MLLM's Retrieval Heads · 2026-10-23 · 32 upvotes
- On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models · 2026-10-23 · 31 upvotes
- Follow the Gradient: Tracing Safety Degradation Back to Training Data · 2026-10-27 · 29 upvotes
- Towards Foundation Decision Models: Drex · 2026-11-05 · 27 upvotes · code
- Reviso: Not All Visual Evidence Deserves Equal Attention in Video Captioning · 2026-11-02 · 25 upvotes
- Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation · 2026-10-22 · 24 upvotes · code
- CurvDelta: Low-Curvature Delta Modeling For Surgical Learning and Unlearning · 2026-11-18 · 23 upvotes
- MUON-RT Reusing the Teacher's Trajectory for Momentum-Free Muon for LLM Self-Distillation · 2026-10-30 · 23 upvotes
- Every Weight Is a Path of Shared Discrete Decisions · 2026-10-22 · 23 upvotes · code
| 1,823 | – | cs.AI 1092 · cs.CL 647 |
agent- Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agent · 2026-11-13 · 140 upvotes · code
- Work Agents: Systems, Capabilities, and Optimization · 2026-10-26 · 113 upvotes · code
- CoworkOS:Scaling Agent Coworkers for Real-world Automation · 2026-11-02 · 100 upvotes · code
- Video Generation Meets Agent Harness: Agentic Video Generation, Agentic World Modeling and Recursive Self-Improvement · 2026-10-29 · 76 upvotes · code
- StreamVibe: Proactive Video Agents for Evolving User Intent · 2026-10-26 · 75 upvotes
- Harness-S: Learning from Sibling Harnesses for Generalizable Agent Training · 2026-11-03 · 70 upvotes · code
- Don't Just Trust Your Memory: Evidence-Linked Memory Reduces Memory-Induced Degradation in LLM Agents · 2026-11-10 · 69 upvotes · code
- FrontierPhysics: Evaluating Agents for End-to-End Physics Research · 2026-11-04 · 66 upvotes
- Infrathon: Benchmarking Language Agents for Real-World, Long-Horizon AI Infra Optimization · 2026-11-09 · 56 upvotes · code
- MIRIX-2.0: Multi-Agent Memory System · 2026-11-09 · 54 upvotes · code
- SWE-CoWork: Benchmarking Coding Agents as Digital Employees in Organizations · 2026-11-15 · 51 upvotes · code
- The Trinity: Capability-Driven Recursive Self-Improvement for Multimodal Agents · 2026-10-26 · 51 upvotes · code
- Axion 1.0: Open Agent Foundation Models, Simplified · 2026-11-02 · 50 upvotes · code
- Democratizing Robot-Use Agents: A Unified Harness with Open Models · 2026-11-01 · 50 upvotes · code
- CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements · 2026-11-02 · 49 upvotes · code
- ToolSpace: Scaling Tool-Centric Environment Synthesis for Long-Horizon Agents · 2026-11-03 · 45 upvotes · code
- PCBRouteAgent: How Close Are LLM Agents to Becoming PCB Routing Engineers? · 2026-11-05 · 44 upvotes · code
- SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt Injection · 2026-11-04 · 44 upvotes · code
- RSIHub: A Composable Framework for Agent-Evolution Methods · 2026-10-23 · 44 upvotes · code
- WorkFactory: Turning Professional Intents into Executable Work for Scalable Agent Training · 2026-10-27 · 42 upvotes · code
- SWE-Trail: History-Guided Trajectory Collection for Coding Agent Training · 2026-11-01 · 40 upvotes
- What Does Multi-Turn Reinforcement Learning Really Improve in LLM Agents? · 2026-11-04 · 39 upvotes · code
- Actor, Judge, or Teacher? Understanding Decision Models in Long-Horizon Agents · 2026-11-12 · 38 upvotes · code
- SteerDistill: Quantizing LLM Agents via Closed-Loop Teacher Steering · 2026-11-10 · 36 upvotes · code
- EvoMemState: Evolving Memory State for Personal Agents · 2026-11-02 · 36 upvotes · code
| 1,306 | – | cs.AI 1005 · cs.CL 312 |
reinforcement learning- Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agent · 2026-11-13 · 140 upvotes · code
- K2-Horizon: A Frontier Fleet of Open Source Language Models · 2026-11-16 · 88 upvotes
- Behind Video Generation: Observations and Insights on Multimodal Understanding from Kling · 2026-11-03 · 85 upvotes
- AllocFlow: End-to-End Portfolio Trading Action Generation from Raw Market Data · 2026-11-15 · 72 upvotes · code
- Harness-S: Learning from Sibling Harnesses for Generalizable Agent Training · 2026-11-03 · 70 upvotes · code
- ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning · 2026-10-27 · 58 upvotes
- Axion 1.0: Open Agent Foundation Models, Simplified · 2026-11-02 · 50 upvotes · code
- Latent Reasoning in Continuous Space for Unified Multimodal Models · 2026-10-30 · 45 upvotes · code
- SPILLWAY: Separating Target Admission from Sanitization to Defend Tool-Using Agents against Prompt Injection · 2026-11-04 · 44 upvotes · code
- Reframe: Observation-Aligned Multi-Teacher On-Policy Distillation for Agentic Visual Reasoning · 2026-11-09 · 41 upvotes · code
- What Does Multi-Turn Reinforcement Learning Really Improve in LLM Agents? · 2026-11-04 · 39 upvotes · code
- Actor, Judge, or Teacher? Understanding Decision Models in Long-Horizon Agents · 2026-11-12 · 38 upvotes · code
- ALIVE: Making Streaming Video Models Interactive · 2026-11-16 · 36 upvotes · code
- EvoMemState: Evolving Memory State for Personal Agents · 2026-11-02 · 36 upvotes · code
- HiSTEVE 1.0: Harnessing Human-Interface VLA Agents for Open-World Games · 2026-10-22 · 35 upvotes · code
- Incentivizing Self-Learning in Large Language Models via Reinforcement Learning · 2026-10-29 · 34 upvotes
- Eat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RL · 2026-10-24 · 34 upvotes · code
- RynnUnify: Towards Unified Embodied Brain · 2026-10-23 · 34 upvotes · code
- PaperCritic: Training AI Reviewers to Assess the Soundness of Papers · 2026-11-13 · 33 upvotes
- NorthCUA Technical Report: Turbocharging Computer-Use Agents through Experience at Scale · 2026-11-01 · 29 upvotes · code
- Towards Foundation Decision Models: Drex · 2026-11-05 · 27 upvotes · code
- WebHarbor: Docking Real Websites for Evolving GUI Agent Environments · 2026-11-02 · 27 upvotes · code
- FewStepRL: Fine-tuning Few-step Diffusion Models with Reinforcement Learning · 2026-11-05 · 26 upvotes · code
- On the Generalization Limitation of On-Policy Distillation for Post-RL Consolidation · 2026-11-03 · 23 upvotes
- Qwen-Image-PE: Learning Visual Design for Text-to-Image Prompt Enhancement · 2026-10-24 · 23 upvotes
| 945 | – | cs.LG 508 · cs.AI 391 |
ai model fine-tuning platforms- From Pixels to Actions--Towards Native Vision-Language-Action Policies · 2026-11-04 · 59 upvotes
- MIRIX-2.0: Multi-Agent Memory System · 2026-11-09 · 54 upvotes · code
- RoboColosseum: Evaluating Physical Intelligence at Scale In-The-Wild · 2026-11-02 · 53 upvotes · code
- Axion 1.0: Open Agent Foundation Models, Simplified · 2026-11-02 · 50 upvotes · code
- Scaling Mathematical Proof Supervision from Structured Textbooks · 2026-10-29 · 48 upvotes
- Latent Reasoning in Continuous Space for Unified Multimodal Models · 2026-10-30 · 45 upvotes · code
- WorkFactory: Turning Professional Intents into Executable Work for Scalable Agent Training · 2026-10-27 · 42 upvotes · code
- ALIVE: Making Streaming Video Models Interactive · 2026-11-16 · 36 upvotes · code
- Apriel Voice 27B Preview: An Open Model for Speech, Reasoning, and Tool Use · 2026-10-29 · 36 upvotes
- YANAMI: A Large-Scale Multimodal Dataset and Benchmark for Multiturn Stateful Interaction · 2026-11-03 · 33 upvotes
- NorthCUA Technical Report: Turbocharging Computer-Use Agents through Experience at Scale · 2026-11-01 · 29 upvotes · code
- Follow the Gradient: Tracing Safety Degradation Back to Training Data · 2026-10-27 · 29 upvotes
- Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents · 2026-10-24 · 29 upvotes · code
- Towards Foundation Decision Models: Drex · 2026-11-05 · 27 upvotes · code
- FewStepRL: Fine-tuning Few-step Diffusion Models with Reinforcement Learning · 2026-11-05 · 26 upvotes · code
- VidUEU-Agent: A Data-Curation Agent for Multimodal Understanding, Editing, and Unified Tasks · 2026-11-03 · 23 upvotes · code
- MUON-RT Reusing the Teacher's Trajectory for Momentum-Free Muon for LLM Self-Distillation · 2026-10-30 · 23 upvotes
- Multi-Token Prediction Done Right · 2026-10-28 · 23 upvotes · code
- Qwen-Image-PE: Learning Visual Design for Text-to-Image Prompt Enhancement · 2026-10-24 · 23 upvotes
- HiP3R: Hierarchical Pose Graphs for Long-Horizon 3D Reconstruction · 2026-10-22 · 23 upvotes · code
- HINT-WAM: Hindsight-Informed Training for World Action Models · 2026-11-18 · 22 upvotes · code
- Venus-DefakerOne2: A Vision-Forensics Foundation Model with Broader Coverage · 2026-10-27 · 21 upvotes · code
- CaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents · 2026-10-29 · 19 upvotes · code
- WebAnything: From the Wild Web to Scalable Agent Environments · 2026-10-27 · 19 upvotes · code
- ProTEUS: A mutation-resolved world model for closed-loop protein evolution · 2026-11-09 · 15 upvotes · code
| 884 | – | cs.AI 363 · cs.LG 336 |
neural networks · also neural network- MACaQ: Fast, Model Agnostic Calibrated Quantization for Low-Precision Weights and Activations · 2026-11-07 · 31 upvotes · code
- TTB: Test-time Baking for Efficient Rendering of Decoder-only View Synthesis Models · 2026-11-12 · 27 upvotes · code
- Every Weight Is a Path of Shared Discrete Decisions · 2026-10-22 · 23 upvotes · code
- LightTAR: Light and Fast Target-Aware Representations for Multimodal Tabular Learning · 2026-11-12 · 20 upvotes · code
- Exploring Weight-Space Programming: Capabilities, Generalization, and Limitations · 2026-11-06 · 19 upvotes · code
- Nested Sparsity for Scalable Pretraining and Continual Learning · 2026-10-22 · 9 upvotes · code
- Where Does Alignment Emerge and What Does It Mean? A Closer Look at the Platonic Representation Hypothesis · 2026-11-09 · 7 upvotes · code
- How Far Can Untrained Neural Networks Go in Anomaly Detection? From Tables to Pixels · 2026-11-05 · 7 upvotes · code
- A Tutorial on Generative Models for Music Audio · 2026-10-28 · 5 upvotes
- Mixed Signals: Weight-Space Programming for EEG and ECG · 2026-11-10 · 3 upvotes
- Module-Aware Optimization for Graph Neural Networks · 2026-11-05 · 3 upvotes · code
- GaussianRenderFormer: Transformer-based Rendering of 3D Gaussian Splats · 2026-11-03 · 3 upvotes · code
- Learning to evolve by matching velocities · 2026-10-30 · 2 upvotes · code
- On the Token Collapse Phenomenon in Textual Graph Soft Prompting · 2026-10-22 · 2 upvotes · code
- WeightBench: Evaluating Language Models as Weight-Space Programmers · 2026-11-13 · 1 upvotes · code
- WeightCode: Installing New Capabilities into Neural Networks via Weight-Space Programming · 2026-11-19
- When and why can integral constraints improve the accuracy of physics-informed neural networks? · 2026-11-19
- Towards Autoregressive Neural Network Parameter Generation · 2026-11-19
- QFT-Based Hybrid PointNet-Quantum Neural Networks for LiDAR Point-Cloud Classification · 2026-11-19
- On the Informativeness of Structural Stability Bounds for GNNs: GINs versus GATs · 2026-11-19
- Splice-Core: Low-Order-Bit-Splicing GEMM for Highly Energy-Efficient AI Inference Accelerators · 2026-11-19
- Deviations from the NTK Regime in CNNs under Joint Depth-Width Scaling · 2026-11-19
- AdsNet: A Graph Neural Network for Direct Adsorption Energy Prediction · 2026-11-19
- How Reliable Are Explanations of Language Models That Detect Insider Threats? · 2026-11-19
- Fusing Multimodal CNN Features with Structurally-Masked Transformers for Hierarchical Sub-Pixel Tree Species Mapping · 2026-11-19
| 739 | – | cs.LG 541 · cs.AI 203 |
machine learning- Sage S2.1 Flash Technical Report · 2026-11-16 · 96 upvotes · code
- Breath-Dx: A Time Series Classification Benchmark for Disease Screening with eNose · 2026-11-11 · 33 upvotes · code
- ReproBridge: Building Reproducibility into ML Research Artifacts · 2026-11-05 · 33 upvotes
- ParetoRSI-Gym: Can AI Agents Improve Language Models Across Multiple Domains? · 2026-10-25 · 11 upvotes · code
- TabBioMed: A Large-Scale Benchmark for Biomedical Tabular Learning · 2026-11-18 · 9 upvotes · code
- MLE-World: Predicting Machine Learning Experiment Outcomes with a Learned World Model · 2026-10-27 · 6 upvotes
- Do LLM Agents Still Need to Be Told How to Self-Improve? · 2026-11-17 · 5 upvotes · code
- TurtLES: A Large-Scale Benchmark for Turbulent 3D Neural PDE Surrogates · 2026-11-06 · 4 upvotes · code
- FrontierCS 2: A Benchmark for Computer Science R&D · 2026-10-21 · 4 upvotes · code
- AdaPRA: Process Reward Agents with Adaptive Rubrics for Data Science · 2026-10-23 · 3 upvotes
- Now You See Me Now You Don't: A Framework To Detect and Reduce Proxy Capacity · 2026-11-19
- Differentially Private Score Estimation with Applications to Score-Based Generative Models · 2026-11-19
- Towards Autoregressive Neural Network Parameter Generation · 2026-11-19
- AdsNet: A Graph Neural Network for Direct Adsorption Energy Prediction · 2026-11-19
- Safeguarded Learning-Assisted Nonlinear Conjugate Gradient Methods · 2026-11-19
- Beyond Error Mitigation: Using Boosting for Noisy Quantum Machine Learning · 2026-11-19
- Trustworthy Geospatial AI Workflows: Reproducible Maritime Analytics and Forecasting on Open-Source AIS Data · 2026-11-19
- Explainable AI for Solar PV Power Forecasting: From Model Selection to Trustworthy, Reproducible Deployment · 2026-11-19
- A Lightweight Hybrid Approach for Milling Force Reconstruction from Internal Machine Signals · 2026-11-19
- The Delayed Societal Cost of Unfairness · 2026-11-19
- Pareto-Optimal and Strategyproof Data-Sharing Between Competitors · 2026-11-19
- Thermodynamically Consistent Neural Networks for a Universal Fluid Gibbs Free Energy Equation of State · 2026-11-19
- Physics-Informed Feature Representations and Pretrained Tabular Foundation Models for Generalizable Melt Pool Geometry Prediction · 2026-11-19
- A Complete Geometric Message-Passing Architecture for Point Clouds · 2026-11-19
- How to Effectively Manage the Energy in Residential Systems: Development and Comparison of Methods · 2026-11-19
| 522 | – | cs.LG 417 · cs.AI 139 |
data- AllocFlow: End-to-End Portfolio Trading Action Generation from Raw Market Data · 2026-11-15 · 72 upvotes · code
- A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement · 2026-10-28 · 64 upvotes
- On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models · 2026-10-23 · 31 upvotes
- Follow the Gradient: Tracing Safety Degradation Back to Training Data · 2026-10-27 · 29 upvotes
- PyRUA-DataFarm: LLM Agent as a Cost-Efficient Teleoperator for Real-Ready Robot Data · 2026-11-03 · 27 upvotes
- VidUEU-Agent: A Data-Curation Agent for Multimodal Understanding, Editing, and Unified Tasks · 2026-11-03 · 23 upvotes · code
- Channel Selection for Mixture-of-Experts Decoding Needs No Calibration Data · 2026-10-27 · 18 upvotes · code
- Piccolo: Co-Evolving Decision Models and Data through Recursive Self-Improvement · 2026-11-18 · 12 upvotes · code
- HALO: Human-Aligned Data Collection for WhoLe-body MObile Manipulation · 2026-11-12 · 10 upvotes · code
- LongZero: Enhancing Long-Context Reasoning in LLMs from Zero Data · 2026-10-21 · 9 upvotes · code
- Agent-R$^2$: Scaling Agents for Realistic Productivity Work via Real-Source Data Synthesis · 2026-11-05 · 8 upvotes · code
- Glyph: An Interpretability Engine for AI-Driven Scientific Discovery from Clinical Data · 2026-11-06 · 7 upvotes · code
- Latent Feedback Is a Compute and Data Amplifier · 2026-11-16 · 6 upvotes · code
- Kezek: Splitting Mono Two-Person Conversations into Per-Speaker Tracks for Full-Duplex Dialogue Data · 2026-11-12 · 4 upvotes · code
- General progress substitutes for specific training data in language models · 2026-11-18 · 3 upvotes · code
- AdaPRA: Process Reward Agents with Adaptive Rubrics for Data Science · 2026-10-23 · 3 upvotes
- GigaSpeech 3: Scaling Multi-Dialect Arabic Speech Recognition with Weakly Labeled Data · 2026-11-02 · 2 upvotes · code
- FLORA: An Open Model Suite for Scaling Robotics Data Engines · 2026-10-22 · 1 upvotes · code
- RefreshGrad: An Online Adaptive Data-sampling Method for Diffusion-based Visuomotor Learning · 2026-11-19
- From Data Alignment to Parameter Generation: Few-Shot Cross-City Traffic Prediction with Conditional Diffusion · 2026-11-19
- PAD: Policy-Aware Data Valuation for Autonomous Driving · 2026-11-19
- DARSY: A Tool for Data-Driven Abstraction and Policy Synthesis for Stochastic Systems with Unknown Dynamics · 2026-11-19
- Calibrate in Context: Efficient Data-Free Quantization from Small Synthetic Pools · 2026-11-19
- Trustworthy Geospatial AI Workflows: Reproducible Maritime Analytics and Forecasting on Open-Source AIS Data · 2026-11-19
- Fixing the Twin, Not the Detector: Sim-to-Real Roadside LiDAR Detection from Digital-Twin Data · 2026-11-19
| 515 | – | cs.LG 279 · cs.AI 195 |
image models- OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images · 2026-10-26 · 52 upvotes · code
- WeLM-Image: A Unified Image Generation Model towards Visual Intelligence · 2026-11-05 · 47 upvotes
- Factorized MLLM Embeddings for Composed Image Retrieval · 2026-11-03 · 47 upvotes · code
- TailSteer: Trajectory-Tail Steering for Drift-Resistant Multi-turn Image Editing · 2026-11-04 · 43 upvotes · code
- HairDeck: Animation-Ready Stylized Hair Cards from a Single Image · 2026-10-29 · 34 upvotes · code
- FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation · 2026-10-27 · 34 upvotes · code
- LongBanana: An Expert-Verified Benchmark for Long-Context Multi-Reference Image Synthesis · 2026-11-04 · 32 upvotes · code
- Qwen-Image-PE: Learning Visual Design for Text-to-Image Prompt Enhancement · 2026-10-24 · 23 upvotes
- FlowTranslator: Training-Free In-Image Machine Translation with Flow-Based Editing · 2026-11-03 · 13 upvotes
- EditAgent: Rethinking Agentic Image Editing · 2026-10-29 · 13 upvotes
- GLOW-FM: Efficient Generative Low-Light Image Enhancement with One-Step Latent Flow Matching · 2026-10-22 · 13 upvotes · code
- MedJev: A System One Vision-Language Decision Model for Fast and Effective Medical Image Understanding · 2026-11-16 · 12 upvotes · code
- LogT: Logically Think with Images for Visual Search · 2026-11-14 · 12 upvotes
- FMT: Lossless Image Compression in a Fixed Number of Parallel Steps · 2026-11-17 · 10 upvotes
- Cross-modal Steering Vectors Exist Across Both Image and Text Generation · 2026-10-26 · 10 upvotes · code
- DominoBench: Evaluating Multi-Step Physical Reasoning from Still Images · 2026-11-16 · 6 upvotes
- Restoring Diversity in Distilled Image and Video Generators by Probing Activations · 2026-11-13 · 6 upvotes · code
- Easy-3Dfy: Object-Level Geometric Composition for Single-Image 3D Scene Construction · 2026-10-23 · 5 upvotes
- Dual Flow: Joint Image-Measurement Interpolation for Inverse Problems · 2026-11-04 · 4 upvotes · code
- Unlocking Any-Order Generation in Pretrained Autoregressive Image Models · 2026-10-29 · 3 upvotes · code
- Lipschitz-Controlled Flow Matching for Robust Image Restoration · 2026-11-10 · 2 upvotes
- UniRestorer++: Scalable Universal Image Restoration with Multi-Granularity Degradation Modeling · 2026-11-04 · 2 upvotes · code
- Do Underwater Image Quality Metrics Agree with Human Perception? A Benchmark with Human Choices, Simple Edits and Generative Drift · 2026-11-13 · 1 upvotes · code
- Class-Conditional Conformal Triage for ICAO Face-Image Compliance under Class Imbalance · 2026-11-19
- A Unified Framework for Image Manipulation Localization Under Multi-Type Weak Supervision · 2026-11-19
| 515 | – | cs.CV 461 · cs.AI 111 |
video models- Wave Forcing: Towards Speed-of-Light Streaming Video Generation · 2026-10-31 · 127 upvotes · code
- Behind Video Generation: Observations and Insights on Multimodal Understanding from Kling · 2026-11-03 · 85 upvotes
- MoviEdit: Long-form Multi-Shot Video Editing Made Easy · 2026-11-02 · 76 upvotes · code
- Video Generation Meets Agent Harness: Agentic Video Generation, Agentic World Modeling and Recursive Self-Improvement · 2026-10-29 · 76 upvotes · code
- StreamVibe: Proactive Video Agents for Evolving User Intent · 2026-10-26 · 75 upvotes
- DreamX: Video Diffusion Model is a Universal Latent Action Learner · 2026-11-03 · 57 upvotes
- BirdDreams: Joint Perspective and BEV Video Generation for a Plausible, Reactive Driving World Model · 2026-11-10 · 56 upvotes
- OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images · 2026-10-26 · 52 upvotes · code
- CodeCap-Bench: Can Code Serve as a Good Video Caption? · 2026-10-27 · 50 upvotes
- Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation · 2026-10-21 · 47 upvotes · code
- PhysLoop: Harnessing LLMs' Physics Awareness for Self-Improving Video Generation Models · 2026-11-12 · 42 upvotes · code
- WorldCast: World-Consistent Character Video Generation with Large-Angle Camera Control · 2026-10-23 · 41 upvotes · code
- Self-Distilling Future Video Representations for World Action Models · 2026-10-21 · 38 upvotes · code
- Few-Step Streaming Video Generation via Condition Shifting · 2026-11-10 · 37 upvotes
- ALIVE: Making Streaming Video Models Interactive · 2026-11-16 · 36 upvotes · code
- VideoMemBench: How Well Do MLLMs Remember in Video Conversations? · 2026-10-29 · 36 upvotes · code
- LociArt: A Unified Paradigm for Free-Style Local Video Stylization · 2026-10-27 · 35 upvotes
- FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation · 2026-10-27 · 34 upvotes · code
- Reading, Writing, Sharing, and Interacting with the World through Video · 2026-10-22 · 31 upvotes · code
- FastFrames: Video Generation at Interactive Latency · 2026-11-17 · 30 upvotes · code
- Turns Matter: Advancing Streaming Video RL via Turn-Level Credit · 2026-11-04 · 28 upvotes · code
- V-JEPA-LM: Video-Language Models That Read Dynamics Beyond Static, Text-Aligned Representations · 2026-11-13 · 26 upvotes · code
- EvoWorld: Towards Out-of-Sight World Evolution in Generative Video Models · 2026-11-04 · 26 upvotes · code
- EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL · 2026-11-04 · 25 upvotes · code
- Reviso: Not All Visual Evidence Deserves Equal Attention in Video Captioning · 2026-11-02 · 25 upvotes
| 508 | – | cs.CV 460 · cs.AI 112 |
world models- Hy-Nomas: Towards Free-form Interactive World Generation · 2026-10-27 · 108 upvotes · code
- CoworkOS:Scaling Agent Coworkers for Real-world Automation · 2026-11-02 · 100 upvotes · code
- AscendGYM: A Cost-Aware Kernel Optimization Benchmark for Real-World Workloads on Ascend NPUs · 2026-11-13 · 92 upvotes · code
- Video Generation Meets Agent Harness: Agentic Video Generation, Agentic World Modeling and Recursive Self-Improvement · 2026-10-29 · 76 upvotes · code
- ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning · 2026-10-27 · 58 upvotes
- BirdDreams: Joint Perspective and BEV Video Generation for a Plausible, Reactive Driving World Model · 2026-11-10 · 56 upvotes
- Infrathon: Benchmarking Language Agents for Real-World, Long-Horizon AI Infra Optimization · 2026-11-09 · 56 upvotes · code
- World In-Context Learning for Agentic Robot Manipulation · 2026-11-09 · 55 upvotes · code
- WorldFoundry: Towards Unified Infrastructure for World Intelligence · 2026-11-07 · 55 upvotes · code
- Rollback: Experience Backtracking in World Models for Policy Improvement · 2026-10-26 · 53 upvotes
- CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements · 2026-11-02 · 49 upvotes · code
- Duo: A Reciprocal World Model for Full-Duplex Interaction · 2026-11-11 · 47 upvotes · code
- L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory · 2026-10-29 · 47 upvotes · code
- WorldCast: World-Consistent Character Video Generation with Large-Angle Camera Control · 2026-10-23 · 41 upvotes · code
- Self-Distilling Future Video Representations for World Action Models · 2026-10-21 · 38 upvotes · code
- GameVerse: A Minute-Scale Gameplay Dataset for Long-Horizon Interactive World Modeling · 2026-10-27 · 37 upvotes · code
- HiSTEVE 1.0: Harnessing Human-Interface VLA Agents for Open-World Games · 2026-10-22 · 35 upvotes · code
- Reading, Writing, Sharing, and Interacting with the World through Video · 2026-10-22 · 31 upvotes · code
- Frontier3DBench: Benchmarking Coding Agents for 3D Creation across Objects, Scenes, and Interactive Open Worlds · 2026-11-06 · 29 upvotes
- EvoWorld: Towards Out-of-Sight World Evolution in Generative Video Models · 2026-11-04 · 26 upvotes · code
- FINCOSMOS: An Open-World Evaluation Paradigm for Agents in Finance · 2026-11-05 · 25 upvotes
- When Does Latent Prediction Error Support Physical Surprise Claims in Video World Models? · 2026-11-01 · 25 upvotes · code
- Wizard: Manipulate Any World in Real Time via Agentic Control · 2026-10-29 · 25 upvotes
- Dual Exam: Controlled Evaluation of Multimodal Agents and World Models · 2026-10-22 · 24 upvotes
- LynnReal-Hand: Unlocking World Interaction with Hand Control · 2026-11-16 · 23 upvotes · code
| 471 | – | cs.CV 209 · cs.RO 180 |
reasoning models- ThinkWorld: World Imagination Reinforces Chain-of-Dynamics Reasoning · 2026-10-27 · 58 upvotes
- Think Less, Locally: Local Preference Learning for Reasoning Compression · 2026-11-03 · 50 upvotes · code
- Latent Reasoning in Continuous Space for Unified Multimodal Models · 2026-10-30 · 45 upvotes · code
- Reframe: Observation-Aligned Multi-Teacher On-Policy Distillation for Agentic Visual Reasoning · 2026-11-09 · 41 upvotes · code
- Apriel Voice 27B Preview: An Open Model for Speech, Reasoning, and Tool Use · 2026-10-29 · 36 upvotes
- VideoNexus: Video Perception Beyond the Reasoning Context · 2026-11-16 · 20 upvotes
- Diagnosing the Reference Gap: What Visual Scaffolds Can and Cannot Fix in Multimodal Reasoning · 2026-10-29 · 18 upvotes · code
- Why Pay for Long Reasoning When Rewrite Do Trick? Causal Effects of Reasoning History Compaction on Future Generation and Agent Cost · 2026-11-02 · 17 upvotes
- S3AC: Stabilized, Selective, and Scalable Actor-Critic for LLM Reasoning · 2026-10-26 · 17 upvotes · code
- What Effort Level Should I Choose? On the Economics of Reasoning Effort in LLM Agents · 2026-10-25 · 16 upvotes · code
- CPU-ARC: Agentic Reasoning Caching for on-CPU Reasoning Reuse · 2026-11-06 · 12 upvotes
- Adversarial Speculative Reasoning Improves Long Horizon Agents · 2026-11-03 · 12 upvotes
- Inherited, Not Invented: Tracing the Provenance of Wait in Reasoning Models · 2026-10-22 · 9 upvotes · code
- LongZero: Enhancing Long-Context Reasoning in LLMs from Zero Data · 2026-10-21 · 9 upvotes · code
- Knowing When to Teach: Learning from Teachable Prefixes in Multilingual Reasoning Distillation · 2026-11-05 · 7 upvotes
- DominoBench: Evaluating Multi-Step Physical Reasoning from Still Images · 2026-11-16 · 6 upvotes
- Where Do Vision Language Models Fail at 3D Reasoning? · 2026-10-29 · 6 upvotes · code
- Learning and Reasoning with Geometry: How Generation Helps Spatial Understanding · 2026-10-26 · 6 upvotes · code
- PhysEvolve: Verifier-grounded Self-evolution for Physical Reasoning with Executable Worlds · 2026-10-26 · 5 upvotes · code
- How Much Does the Hint Matter? Scope Conditions for Hindsight Self-Distillation in Financial Reasoning · 2026-10-26 · 5 upvotes · code
- Thinking Harder Doesn't Lead to Better Choices: Reasoning Effort Increases the Confidence but Not the Correctness of LLM Shopping Agents · 2026-11-17 · 4 upvotes
- Weaken to Strengthen: Weakening-Induced On-Policy Self-Distillation for Large Reasoning Models · 2026-10-28 · 4 upvotes · code
- AVTR: Adaptive Multimodal Reasoning with Visual Imagination · 2026-11-18 · 3 upvotes · code
- NPCBench: A Clinical Apprenticeship Benchmark for Multimodal Care-Pathway Reasoning in Nasopharyngeal Carcinoma · 2026-11-05 · 3 upvotes · code
- M3OPD-Reasoner: An Open Recipe for Post-Training Multimodal Reasoning with Multi-Teacher On-Policy Distillation · 2026-11-17 · 2 upvotes · code
| 465 | – | cs.AI 248 · cs.CV 154 |
diffusion model platforms- Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs · 2026-10-27 · 117 upvotes · code
- DreamX: Video Diffusion Model is a Universal Latent Action Learner · 2026-11-03 · 57 upvotes
- FewStepRL: Fine-tuning Few-step Diffusion Models with Reinforcement Learning · 2026-11-05 · 26 upvotes · code
- D3D: Decoupled Diffusion Drafting for Asynchronous Speculative Decoding · 2026-11-04 · 19 upvotes · code
- EDGAR: Efficient Diffusion-Driven Gaussian Avatar Refinement via Synthetic Failure · 2026-11-05 · 17 upvotes · code
- Different Tasks, Different Timesteps: Temporal Task-Aware Quantization for Diffusion Language Models · 2026-10-22 · 17 upvotes · code
- Sparsity Should Be ALLOTted by Output: Training-Free Allocation of Block-Sparse Attention for Video Diffusion Transformers · 2026-10-21 · 15 upvotes
- JVT: Just Video Transformer makes pixel-space video diffusion simple · 2026-11-13 · 14 upvotes · code
- eDMD: Endpoint Distribution Matching for Few-Step Diffusion Distillation · 2026-11-12 · 12 upvotes
- Nemotron-Labs-Diffusion-Uni: Elastic Self-Refining Unified Diffusion LLM with Cross-Paradigm On-Policy Distillation · 2026-10-27 · 12 upvotes · code
- Decoding Without a Decoder: Direct Pixel Prediction from Diffusion Transformers · 2026-11-17 · 11 upvotes
- Test-Time Scaling for Diffusion Language Models with Frequency-Aware Remasking · 2026-11-07 · 10 upvotes
- VA-TDM: A Unified View for Improving Few-Step Diffusion Models by Velocity Adversarial Distillation · 2026-11-04 · 10 upvotes · code
- BYOD: Build Your Own DLM - Efficient Autoregressive-to-Diffusion Language Model Conversion · 2026-10-30 · 10 upvotes · code
- Speculative Diffusion is a Tale of Two Tradeoffs · 2026-10-22 · 10 upvotes
- NitroFusion2: Bringing Adversarial Loss to the Text Stream of Multimodal Diffusion Transformers · 2026-11-03 · 9 upvotes · code
- AB-Attention: Accurate Block Attention for Accelerating Video Diffusion Transformers · 2026-10-29 · 8 upvotes · code
- Back to Pixels: Lifting Latent Video Diffusion into Pixel Space · 2026-11-12 · 7 upvotes
- MPEG-Diffusion: Mixed-Resolution Video Generation · 2026-11-09 · 7 upvotes
- No Channels Left Behind: Understanding Diffusion Acceleration through Residual Gates · 2026-10-29 · 7 upvotes
- Disen-Forcing: Disentangling Semantic Anchoring from Motion for Autoregressive Video Diffusion · 2026-11-02 · 6 upvotes · code
- What Makes a Good Unmasking Policy? A Controlled Study of Learned Unmasking in Diffusion Language Models · 2026-10-22 · 6 upvotes
- StepX-OPD: Rethinking Multi-Teacher On-Policy Distillation in Diffusion Models · 2026-11-03 · 5 upvotes · code
- Looped Uniform Diffusion Language Models · 2026-10-21 · 5 upvotes
- OneSteer: Unlocking Steerable General Humanoid Motion Tracking via One-Step Diffusion Whole-Body Control · 2026-10-30 · 3 upvotes
| 401 | – | cs.CV 185 · cs.LG 173 |
memory- Don't Just Trust Your Memory: Evidence-Linked Memory Reduces Memory-Induced Degradation in LLM Agents · 2026-11-10 · 69 upvotes · code
- MIRIX-2.0: Multi-Agent Memory System · 2026-11-09 · 54 upvotes · code
- L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory · 2026-10-29 · 47 upvotes · code
- EvoMemState: Evolving Memory State for Personal Agents · 2026-11-02 · 36 upvotes · code
- Self-Improvement Memory Enables Continual Recursive Self-Improvement · 2026-11-13 · 33 upvotes
- Memory Tax: Dissecting the Net Value of Agent Memory · 2026-10-25 · 26 upvotes · code
- Is Complex Agentic Memory Always Needed? Naive RAG Is Stronger Than We Thought · 2026-10-22 · 22 upvotes · code
- Memory-Centric Continual Learning for AI Agents · 2026-10-21 · 22 upvotes
- MatAnyone-E: Sparse Memory Propagation for Efficient High-Resolution Video Matting · 2026-10-26 · 18 upvotes · code
- More Memory, Better Videos? A Controlled Study of Visual Memory in Long-Video Generation · 2026-10-26 · 16 upvotes · code
- DraMaze: A Multi-Agent Pipeline with Future-Aware Memory for Diverse Microdrama Script Generation · 2026-10-22 · 15 upvotes
- Can Test-Time Memory Evolution Outperform Test-Time Training for Scientific Discovery? · 2026-10-23 · 12 upvotes · code
- Who Remembers What? Multi-Granularity Memory Extraction for Multi-User, Multi-Agent Interaction · 2026-11-07 · 11 upvotes
- MemSteer: Turning User Histories into Supervision for Agent Memory Optimization · 2026-10-29 · 10 upvotes
- PReMind: When Personal Memory Meets Visual Hazards · 2026-11-18 · 9 upvotes
- HeLM: Hierarchical Explicit Language Memory for Non-Markovian Manipulation · 2026-11-02 · 9 upvotes · code
- Rare, Relevant, and Still Wrong: How Memory Fails LLM Group Decisions · 2026-10-27 · 9 upvotes
- Is Your Robot's Memory Just a Clock? Temporal Shortcuts in Memory-Augmented VLA Policies · 2026-11-10 · 8 upvotes · code
- RoboArchitect: Automating the Design of Robotic Agents with Persistent Memory · 2026-10-30 · 8 upvotes · code
- MemInStream: Memorizing or Merely Recognizing? Rethinking Streaming Video Memory Evaluation · 2026-11-11 · 4 upvotes · code
- HiVe-Mem: Interleaving Horizontal Memory Expansion and Vertical Evidence Composition for Multimodal Agents · 2026-11-09 · 4 upvotes · code
- FlyHash for LLM Agent Memory: An Empirical Validation and a New Application · 2026-11-04 · 4 upvotes · code
- DAMI: Dual-Axis Memory Initialization for Enhanced Long-Context Retrieval in Gated Linear Attention · 2026-10-30 · 4 upvotes · code
- RE-CAM: Readout-Enhanced Content-Addressable Memory for Quantitative Similarity Search · 2026-11-19
- Fold the Loop: Decoding-Time KV Memory for Looped Vision-Language Models · 2026-11-19
| 330 | – | cs.AI 174 · cs.CL 98 |
open-weight models- Democratizing Robot-Use Agents: A Unified Harness with Open Models · 2026-11-01 · 50 upvotes · code
- Open Vision Banana: A Fully Open Recipe for Generative Visual Perception · 2026-11-11 · 41 upvotes · code
- You don't need long context · 2026-11-03 · 24 upvotes
- AgentBaton: Efficient Model Collaboration in Agentic Tasks · 2026-10-25 · 24 upvotes
- Why Pay for Long Reasoning When Rewrite Do Trick? Causal Effects of Reasoning History Compaction on Future Generation and Agent Cost · 2026-11-02 · 17 upvotes
- Youtu-Parsing-Omni: One Encoder, One Schema, All Modalities · 2026-10-29 · 17 upvotes
- Measuring AI Agents as Teammates with Collaborative Intelligence · 2026-11-02 · 16 upvotes · code
- What Effort Level Should I Choose? On the Economics of Reasoning Effort in LLM Agents · 2026-10-25 · 16 upvotes · code
- EditAgent: Rethinking Agentic Image Editing · 2026-10-29 · 13 upvotes
- Adversarial Speculative Reasoning Improves Long Horizon Agents · 2026-11-03 · 12 upvotes
- Can Test-Time Memory Evolution Outperform Test-Time Training for Scientific Discovery? · 2026-10-23 · 12 upvotes · code
- Near-Zero Token Embeddings Silently Stall Training in Gated Sequence Models · 2026-11-03 · 7 upvotes
- Evaluating DeepSeek V4.1 Flash-1017 for loss of control and harmful manipulation risks · 2026-10-26 · 7 upvotes
- RoboJev: An Open Vision-Language Judge for Robot Success Detection · 2026-10-24 · 7 upvotes
- DominoBench: Evaluating Multi-Step Physical Reasoning from Still Images · 2026-11-16 · 6 upvotes
- All Quiet on the Neural Front: Language Models Do Not Report Injected Pain States · 2026-11-06 · 6 upvotes
- Where Do Vision Language Models Fail at 3D Reasoning? · 2026-10-29 · 6 upvotes · code
- Correct Labels Are Not Enough: Reliable Metadata Can Silently Control Model Behavior · 2026-11-03 · 5 upvotes
- How Much Does the Hint Matter? Scope Conditions for Hindsight Self-Distillation in Financial Reasoning · 2026-10-26 · 5 upvotes · code
- IDEA: Intent-Dominance Evidence Audit for Inference-Time Backdoor Detection in GUI Agents · 2026-11-18 · 4 upvotes
- RICoT: Recurrent Interleaved Chain-of-Thought for Page Stream Segmentation · 2026-11-17 · 4 upvotes
- IWIBench: Evaluating Gradient-Free Model Driven Intra-weight Injection · 2026-11-05 · 4 upvotes · code
- TinyAstral: Transferring Self-Evolving Harnesses to Tiny Generalist Manipulation Agents · 2026-10-30 · 4 upvotes · code
- The novelty exposed: ablation, reproducibility and transparency in 40 technical reports of open-weight large language models (LLMs) · 2026-11-15 · 3 upvotes · code
- JFinBench: A Continuously Refreshable Japanese Financial Benchmark from the Latest Certification Exams · 2026-11-13 · 3 upvotes · code
| 311 | – | cs.AI 177 · cs.CL 142 |
decision models- Actor, Judge, or Teacher? Understanding Decision Models in Long-Horizon Agents · 2026-11-12 · 38 upvotes · code
- Flide: Accelerating Decision Inference with Exact State Forking · 2026-10-30 · 35 upvotes · code
- Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents · 2026-10-24 · 29 upvotes · code
- MMDM: Measuring Massive Multitask Decision Making · 2026-11-10 · 28 upvotes · code
- Towards Foundation Decision Models: Drex · 2026-11-05 · 27 upvotes · code
- Every Weight Is a Path of Shared Discrete Decisions · 2026-10-22 · 23 upvotes · code
- DecisionRank: On-Policy Distillation for Decision-Model Rerankers · 2026-10-30 · 15 upvotes
- Thinking Fast, Anywhere: One System-1 for the Decision Points of Any Agent Workflow · 2026-11-18 · 13 upvotes · code
- Piccolo: Co-Evolving Decision Models and Data through Recursive Self-Improvement · 2026-11-18 · 12 upvotes · code
- MedJev: A System One Vision-Language Decision Model for Fast and Effective Medical Image Understanding · 2026-11-16 · 12 upvotes · code
- From Tool State to Scientific Action: Auditing Decision Provenance in Biomedical Research Agents · 2026-11-01 · 10 upvotes
- Rare, Relevant, and Still Wrong: How Memory Fails LLM Group Decisions · 2026-10-27 · 9 upvotes
- The Value of Thinking: Learning When to Reason in Hybrid Decision Models · 2026-11-12 · 8 upvotes · code
- Your Policy Is Secretly a Harness: The Decision Geometry of Agent Interfaces · 2026-10-27 · 8 upvotes · code
- Joint or Per-Option? Compact Encoders for Closed-Set Decisions from 17 Million to 1 Billion Parameters · 2026-10-22 · 7 upvotes · code
- Decoupled Predictive Decision Making: A Shared Conditional Predictor for Agents · 2026-11-01 · 6 upvotes
- Do We Need an LLM to Know Why Sources Conflict? Decision Models for Knowledge-Conflict Typing in RAG · 2026-10-27 · 5 upvotes · code
- The Noise Floor of a Quantization Comparison: Engine, restart, batch and kernel drift, measured against 8-bit and 4-bit effects in two decision models · 2026-11-11 · 4 upvotes · code
- Monitor Accuracy Isn't the Answer: A Decision-Value Framework for Evaluating AI Agent Restart Monitors · 2026-10-27 · 4 upvotes
- When Expert Disagreement Hurts: Prestige and Selectivity in LLM Decision Revision · 2026-11-12 · 3 upvotes · code
- PolyRoute: A Twelve-Language and Code-Mixed Benchmark for Typed-Decision Routing, with Baselines and a Leaderboard · 2026-11-10 · 2 upvotes
- Zuse: A Decision Model for European Languages · 2026-11-04 · 1 upvotes
- Incorporating argumentation frameworks for LLM decision-making: Task-specific design and evaluation · 2026-11-19
- Stop Going in Circles:Loop-Triggered Routing for System 1 Decision Agents · 2026-11-19
- Decision Boundaries Matter: Graph-Regularized Residual Adaptation for Cross-Domain Fake Image Detection · 2026-11-19
| 279 | – | cs.AI 149 · cs.LG 112 |
foundation models- Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agent · 2026-11-13 · 140 upvotes · code
- IQuest-Q1: Advancing Foundation Capabilities for Agentic CLI Systems · 2026-10-22 · 99 upvotes
- Axion 1.0: Open Agent Foundation Models, Simplified · 2026-11-02 · 50 upvotes · code
- Open-HumanWAM: An Open Recipe for Scaling Human and Robot Experience for Embodied Foundation Models · 2026-11-04 · 36 upvotes
- FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation · 2026-10-27 · 34 upvotes · code
- Towards Foundation Decision Models: Drex · 2026-11-05 · 27 upvotes · code
- Trustworthy Recursive Self-Improvement in the Era of Large Models: Foundation, Risks, Evaluation and Open Challenges · 2026-10-26 · 23 upvotes
- Venus-DefakerOne2: A Vision-Forensics Foundation Model with Broader Coverage · 2026-10-27 · 21 upvotes · code
- Probing Spatial State Representations in Visual Foundation Models · 2026-10-29 · 20 upvotes
- Recursa: Toward Recursively Self-Improving Foundation Model Systems · 2026-11-02 · 18 upvotes
- $π^4$: A Foundation Model for 4D Scene Geometry and Motion · 2026-11-17 · 17 upvotes · code
- SALA: Semantically Aligned Latent Actions Enable Dual-Axis Scaling of Embodied Foundation Models · 2026-11-12 · 15 upvotes
- Training Foundation Models with a Single Algorithm · 2026-10-29 · 15 upvotes · code
- Emergent Biological Capabilities in a Foundation Model for Molecular Interactions · 2026-11-10 · 10 upvotes
- RynnVLA-Latent: Scaling Robotic Manipulation Foundation Models with 3D-Grounded Latent Actions · 2026-10-25 · 10 upvotes · code
- F2G-Pose: Geometry-Aware Foundation Feature Lifting for Direct RGB-D Category-Level Object Pose Estimation · 2026-10-22 · 8 upvotes · code
- PhysioWave-T: Token-Efficient Wavelet Foundation Models for Biosignals · 2026-11-06 · 2 upvotes · code
- VoxForge: A Unified Foundation Model for Dense 3D Features Across MRI, CT and PET · 2026-11-19
- Antom 3-in-1 Transformer: A Payment Foundation Model · 2026-11-19
- TuringPAI: A Foundation for On-Device Physical AI · 2026-11-19
- Erasing the Wrong Thing: Conditional Attribute Leakage and Concept Erasure in Shared Foundation-Model Embeddings · 2026-11-19
- MatVerse: A Foundation Model for Materials Science · 2026-11-19
- AdaptReg: Skip-level FiLM Adapter for Task-Specific Adaptation of a Frozen Registration Foundation Model · 2026-11-19
- ECHO: In-Context Behavior foundation model for Humanoid Whole-Body Control · 2026-11-19
- When Foundation Models Disagree: Representational Heterogeneity for Calibrated Uncertainty in Whole-Slide Image Classification · 2026-11-19
| 260 | – | cs.LG 123 · cs.AI 101 |
generative ai- Open Vision Banana: A Fully Open Recipe for Generative Visual Perception · 2026-11-11 · 41 upvotes · code
- EvoWorld: Towards Out-of-Sight World Evolution in Generative Video Models · 2026-11-04 · 26 upvotes · code
- Read, Allocate, Route: Role-Coupled Tokenization for Pixel-Space Generative Transformers · 2026-10-29 · 20 upvotes · code
- GLOW-FM: Efficient Generative Low-Light Image Enhancement with One-Step Latent Flow Matching · 2026-10-22 · 13 upvotes · code
- AnyGameRenderer: Entity-Consistent Generative Rendering Across Games and an Entity-Level Benchmark · 2026-10-22 · 13 upvotes · code
- Koopman Generative Operators for Efficient Probabilistic Time-Series Forecasting · 2026-11-03 · 5 upvotes · code
- A Tutorial on Generative Models for Music Audio · 2026-10-28 · 5 upvotes
- UMM-JEPA: Generative Pretraining via Masked Next-Scale Representation Prediction for Unified Multimodal Models · 2026-10-26 · 4 upvotes
- Iris-Z: Scaling One Generative Model Past Specialist Geometry Models · 2026-11-11 · 3 upvotes
- Do Underwater Image Quality Metrics Agree with Human Perception? A Benchmark with Human Choices, Simple Edits and Generative Drift · 2026-11-13 · 1 upvotes · code
- VideoRNG: Relightable Neural Gaussians from Generative Video Models · 2026-11-19
- Learning Generative Ranking Policies for Whole-Page Optimization · 2026-11-19
- Differentially Private Score Estimation with Applications to Score-Based Generative Models · 2026-11-19
- Generative News Recommendation Reproduces Popularity: A Memorization-Based Analysis · 2026-11-19
- AesDistill: Distilling Generative Aesthetics for Image Color Enhancement · 2026-11-19
- Iterative Scarcity-Guided Exploration: Bootstrapping Generative Auto-bidding from Narrow Support · 2026-11-19
- GenSPARQL: A Generative Extension of SPARQL for Incomplete Knowledge Graphs · 2026-11-19
- Fast Self-Supervised Generative CT Denoising via Few-Step Sampling · 2026-11-19
- Plan4D: Generative Plannable 4D Worlds · 2026-11-19
- GEOHunter: Mapping a Generative Engine Optimization Network in the Wild · 2026-11-19
- ProtoDiffusion: Token-per-Layer Generative Modeling of Multi-Layer Images · 2026-11-19
- Variable Length Diffuse Everything: Arbitrary Length Generative Modeling on Arbitrary State Spaces · 2026-11-18
- GTA: Generative Tower of Agents for Scalable Holonic Scene Generation · 2026-11-18
- RecallFlow: Episodic Memory as the Source Distribution of Generative Robot Policies · 2026-11-18
- GenRF: Generative Registration-free Image Fusion · 2026-11-18
| 238 | – | cs.LG 112 · cs.AI 93 |
ai model distillation services- P$^2$-MOPD: Accelerating Multi-Teacher On-Policy Distillation via Parameter Priors · 2026-11-02 · 71 upvotes · code
- Reframe: Observation-Aligned Multi-Teacher On-Policy Distillation for Agentic Visual Reasoning · 2026-11-09 · 41 upvotes · code
- Order-Only On-Policy Distillation · 2026-11-01 · 35 upvotes
- On the Generalization Limitation of On-Policy Distillation for Post-RL Consolidation · 2026-11-03 · 23 upvotes
- MUON-RT Reusing the Teacher's Trajectory for Momentum-Free Muon for LLM Self-Distillation · 2026-10-30 · 23 upvotes
- How Much Training-Inference Mismatch Can On-Policy Distillation Tolerate? · 2026-11-08 · 15 upvotes · code
- DecisionRank: On-Policy Distillation for Decision-Model Rerankers · 2026-10-30 · 15 upvotes
- SpecOPD: Branch-Parallel On-Policy Distillation for Speculative Decoding · 2026-11-02 · 14 upvotes · code
- Every Token Needs Its Own Teacher: Multi-teacher Adaptive On-policy Self-distillation · 2026-10-29 · 14 upvotes · code
- Future Representation Distillation for Imagination-free World Action Models · 2026-11-03 · 13 upvotes
- eDMD: Endpoint Distribution Matching for Few-Step Diffusion Distillation · 2026-11-12 · 12 upvotes
- Nemotron-Labs-Diffusion-Uni: Elastic Self-Refining Unified Diffusion LLM with Cross-Paradigm On-Policy Distillation · 2026-10-27 · 12 upvotes · code
- VA-TDM: A Unified View for Improving Few-Step Diffusion Models by Velocity Adversarial Distillation · 2026-11-04 · 10 upvotes · code
- Agentic On-Policy Distillation Implicitly Reshapes LLMs' ReAct Patterns · 2026-11-14 · 7 upvotes
- Knowing When to Teach: Learning from Teachable Prefixes in Multilingual Reasoning Distillation · 2026-11-05 · 7 upvotes
- On-Policy Self-Distillation with Teacher Evolution · 2026-10-28 · 7 upvotes
- StepX-OPD: Rethinking Multi-Teacher On-Policy Distillation in Diffusion Models · 2026-11-03 · 5 upvotes · code
- How Much Does the Hint Matter? Scope Conditions for Hindsight Self-Distillation in Financial Reasoning · 2026-10-26 · 5 upvotes · code
- Dataset Distillation via Drifting · 2026-11-12 · 4 upvotes
- Weaken to Strengthen: Weakening-Induced On-Policy Self-Distillation for Large Reasoning Models · 2026-10-28 · 4 upvotes · code
- M3OPD-Reasoner: An Open Recipe for Post-Training Multimodal Reasoning with Multi-Teacher On-Policy Distillation · 2026-11-17 · 2 upvotes · code
- HOPD: Historical On-Policy Distillation for SAR MLLM Continual Learning · 2026-11-19
- Efficient Latent Reasoning for Vision-Language Model via Dynamics-Aware Quantization and Distillation · 2026-11-19
- Lightweight Low-Frequency Non-Intrusive Load Monitoring via Karhunen-Loève Feature Distillation and Temporal Convolutional Networks · 2026-11-19
- Hindsight Self-Distillation: Teaching Robots to Act from the Present · 2026-11-19
| 214 | – | cs.AI 89 · cs.LG 85 |
design- On the Design of Hyper-Connections: Simplification, Stability, and Scalability · 2026-11-04 · 30 upvotes · code
- Co-Design Bench: Multimodal Collaborative Coding Evaluation for Agentic Models · 2026-10-26 · 23 upvotes · code
- Qwen-Image-PE: Learning Visual Design for Text-to-Image Prompt Enhancement · 2026-10-24 · 23 upvotes
- QDA: Closed-Loop LLM Quantization Design with Agents · 2026-11-17 · 10 upvotes
- RoboArchitect: Automating the Design of Robotic Agents with Persistent Memory · 2026-10-30 · 8 upvotes · code
- BitDecoding-FP4: Native FP4 KV Cache Decoding via Algorithm-System Co-Design · 2026-11-06 · 4 upvotes · code
- BEND 2.0: Benchmarking the Capabilities Needed to Design DNA · 2026-11-02 · 3 upvotes · code
- TernScope: Model-Hardware Co-Design for Efficient Ternary Endoscopic Segmentation · 2026-10-21 · 3 upvotes · code
- ReLay: Bidirectional Layout-Code Translation and Library Evolution for Reusable and Process-Portable Analog Design · 2026-11-19
- Incorporating argumentation frameworks for LLM decision-making: Task-specific design and evaluation · 2026-11-19
- DRVEXO-4B-Unified: Design and Evaluation of a Modular Speech-Vision System · 2026-11-19
- Design and Evaluation of Epira: An Automated Interview System for Case Investigation and Contact Tracing · 2026-11-19
- QUBO-based feature selection for MRI undersampling pattern design · 2026-11-19
- Design and Validation of a Telescopic Chassis-Assisted Stair-Climbing Mechanism for Powered Wheelchairs · 2026-11-19
- The FrontierOR Challenge: Agentic Algorithm Design for Operations Research · 2026-11-19
- Prism: Hierarchical Text Detection with Minimalist Design · 2026-11-19
- Asuka-FM: A System-Architectural Co-Design Framework for Efficient Text-to-Image Pretraining on Consumer Hardware · 2026-11-19
- SHUSH: Emission-Aware Reward Design for Proactive Video Assistants · 2026-11-19
- JARVIS: An Agent That Designs, Builds, and Tests Circuit Boards on Its Own · 2026-11-19
- Mapping the Design Space of Feature Sampling for Optical Flow · 2026-11-18
- RoboBuilder: Agentic Robot Co-Design with Real-world Video Feedback in the Loop · 2026-11-18
- BiPathCPG: A Novel Load-Sharing Design Architecture for Compound Planetary Gearboxes · 2026-11-18
- Functional Principal Component Analysis: Minimax Optimality from Sparse to Dense Designs and Beyond · 2026-11-18
- Sparse designs via quantization of the uniform measure on high-dimensional hypercubes · 2026-11-18
- Variance-Optimal Counterfactual Policy Design for Sample-Efficient Online A/B Testing · 2026-11-18
| 204 | – | cs.AI 90 · cs.LG 82 |
search- VisSearch-Bench: Evaluating Long Horizon Visual Search in Multimodal Agents · 2026-11-03 · 22 upvotes · code
- LogT: Logically Think with Images for Visual Search · 2026-11-14 · 12 upvotes
- Re-Search: Dissecting LLM Ideation Through a Two-Player Questioning Game · 2026-11-10 · 10 upvotes
- Novel or Not? PatEx-Gym: Agentic Prior-Art Search for Novelty Assessment in Patent Examination · 2026-10-24 · 10 upvotes · code
- SearchHorizonBench: A Benchmark for Search Value in AI Agents · 2026-10-26 · 8 upvotes · code
- Self-Assessment Reinforcement Learning for Search-State Awareness in Retrieval-Augmented Large Language Models · 2026-10-21 · 6 upvotes
- Evidence-Based Credit Assignment for Search-Augmented Language Models · 2026-11-18 · 5 upvotes
- Advancing SVD-based LLM Compression via Layer-Wise Error Model Search · 2026-10-23 · 5 upvotes · code
- RE-CAM: Readout-Enhanced Content-Addressable Memory for Quantitative Similarity Search · 2026-11-19
- Search or Scoring? Diagnosing Why Visual World-Model Planners Fail · 2026-11-19
- Keystone: Judging Previews at Key Steps for Test-Time Search in Diffusion Models · 2026-11-19
- DMT-Attack: Diffusion-Prior Texture Search for Closed-Loop Vision-Language-Action Policies · 2026-11-19
- Limits of local curvature for constructing search subspaces in segmentation models · 2026-11-19
- Many Solutions, One Answer: Search Order Shapes the Default Solutions of Language Models · 2026-11-19
- Web search in Latin America: language models use less local and diverse news than search engines · 2026-11-19
- Bayesian optimization on amortized search space · 2026-11-19
- Monte Carlo Pass Search for Setpieces · 2026-11-19
- Hybrid Retrieval for Government Scheme Search in English and Marathi · 2026-11-19
- Efficient World-Model Planning via Physics-Guided Search Distillation · 2026-11-18
- SearchDiffusion: Information-Guided Diffusion Planning for Object Search · 2026-11-18
- Risk-Triggered Search: Behavior-Preserving Safe Control · 2026-11-18
- When to Refine: Selective Search for Frozen Visual World Models · 2026-11-18
- Study and Improvement of Search Algorithms in Stochastic Perfect-Information · 2026-11-18
- CAIMS: Scalable Cross-Array In-Memory Search · 2026-11-18
- Teaching Language Models to Narrow Boolean Patent Searches from Search Feedback · 2026-11-17
| 166 | – | cs.AI 90 · cs.LG 60 |
robotics- Envisioning Agentic Robotics: A New Era of Robotic Systems · 2026-11-13 · 134 upvotes
- RynnVLA-Latent: Scaling Robotic Manipulation Foundation Models with 3D-Grounded Latent Actions · 2026-10-25 · 10 upvotes · code
- From VLM Planners to Robotic Agents: Self-Evolving Harnesses for History-Dependent Manipulation · 2026-10-21 · 10 upvotes · code
- RoboArchitect: Automating the Design of Robotic Agents with Persistent Memory · 2026-10-30 · 8 upvotes · code
- LEASH: Stay Safe in Agentic Robotics · 2026-11-10 · 5 upvotes · code
- FLORA: An Open Model Suite for Scaling Robotics Data Engines · 2026-10-22 · 1 upvotes · code
- MoRE: Mixture-of-Experts for Multi-Physics Robotic World Models · 2026-11-19
- ActMem: From Latent Memory Reasoning to Grounded Robotic Action · 2026-11-19
- TwoPass: Draft-Guided Few-Step Video Prediction for Robotic Manipulation · 2026-11-19
- FlashX: Scaling Robotic Experience Reuse for Embodied Agents with CBA-Based NAND Flash · 2026-11-19
- SCCV-6D: Sparse Canonical Coordinate Voting for Holistic Multi-View RGB-D 6D Pose Estimation in Robotic Bin Picking · 2026-11-19
- Point Dynamics as Proxy for Robotic World Models · 2026-11-19
- Mind2Act World: A Diagnostic Benchmark for Embodied Mind, Physical Action, and Mind-Action Composition in Robotic Manipulation · 2026-11-19
- A Tutorial on Complementarity-Based Contact Models for Robotics · 2026-11-19
- Assessing Vision-Language Models for Early Prediction of Unsafe Situations in Robotics · 2026-11-18
- Towards Vacuum-Assisted Robotic Needle Interventions: From Fluid Aspiration to Tissue Biopsy · 2026-11-18
- Constructive Infinitely Differentiable Guidance Vector Fields for Robotic Control · 2026-11-18
- OmniFish: A Bioinspired, Modular, Reconfigurable Soft Robotic Fish Enabling Multi-Modal Swimming · 2026-11-18
- TinyARM-X: A Series of Open-Source, Configurable, and Transparent Torque-Controlled Desktop-Scale Robotic Manipulators · 2026-11-18
- Hydrodynamics of robotic micro-swimmers in confinement · 2026-11-18
- Conceptual full-vehicle modeling of a modular all-wheel-drive robotic ADS test platform as a foundation for a digital twin architecture · 2026-11-18
- InteractVLA: Turning VLAs into Interactive Tools for Agentic Robotic Manipulation · 2026-11-17
- Task Convergent Flow Matching for Generative Robotics · 2026-11-17
- Stochastic Diversity Windows: Diagnosing Noise Influence in Robotic Diffusion Sampling · 2026-11-17
- Auditing a Learned Simulator for Legged Robots: The Robotic World Model on ANYmal D · 2026-11-17
| 165 | – | cs.RO 154 · cs.AI 30 |
ai video generation- PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations · 2026-10-27 · 154 upvotes
- Wave Forcing: Towards Speed-of-Light Streaming Video Generation · 2026-10-31 · 127 upvotes · code
- VibePrevisBench: Evaluating Agentic Coding for 4D Scene Generation in Blender · 2026-11-11 · 87 upvotes · code
- Behind Video Generation: Observations and Insights on Multimodal Understanding from Kling · 2026-11-03 · 85 upvotes
- Video Generation Meets Agent Harness: Agentic Video Generation, Agentic World Modeling and Recursive Self-Improvement · 2026-10-29 · 76 upvotes · code
- BirdDreams: Joint Perspective and BEV Video Generation for a Plausible, Reactive Driving World Model · 2026-11-10 · 56 upvotes
- OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images · 2026-10-26 · 52 upvotes · code
- Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation · 2026-10-21 · 47 upvotes · code
- Route Anything: A Study of Model and Policy Routing for General-Purpose AI Systems · 2026-11-03 · 44 upvotes · code
- PhysLoop: Harnessing LLMs' Physics Awareness for Self-Improving Video Generation Models · 2026-11-12 · 42 upvotes · code
- WorldCast: World-Consistent Character Video Generation with Large-Angle Camera Control · 2026-10-23 · 41 upvotes · code
- Self-Distilling Future Video Representations for World Action Models · 2026-10-21 · 38 upvotes · code
- Few-Step Streaming Video Generation via Condition Shifting · 2026-11-10 · 37 upvotes
- FastFrames: Video Generation at Interactive Latency · 2026-11-17 · 30 upvotes · code
- EmoReward: Self-Evolving Reward Calibration for Emotional Video Generation RL · 2026-11-04 · 25 upvotes · code
- Wizard: Manipulate Any World in Real Time via Agentic Control · 2026-10-29 · 25 upvotes
- Making MLLM Latents Matter: Factor-Aware Predictive Learning for Cinematic Video Generation · 2026-10-22 · 24 upvotes · code
- Video-Coder: Reinforcing Agentic Coding for Video Generation · 2026-11-06 · 22 upvotes · code
- WorldRuler: Interactive World Modeling under Configurable Rules · 2026-11-18 · 21 upvotes · code
- History Forcing: Distilling History-Dependent Continuations for Long-Horizon Video World Models · 2026-11-02 · 20 upvotes · code
- VibeVideoBench: Evaluating Multimodal Agents on Code-Driven Video Generation · 2026-10-26 · 20 upvotes
- Code World Model 2.0: Towards Infinite Controllable Video Generation · 2026-11-17 · 19 upvotes · code
- WorldDraft: If Code Builds the World, Can Video Models Just Render It? · 2026-11-12 · 18 upvotes · code
- More Memory, Better Videos? A Controlled Study of Visual Memory in Long-Video Generation · 2026-10-26 · 16 upvotes · code
- Verus-Insight: Towards Explainable Artifact Detection in AI-Generated Videos · 2026-10-22 · 14 upvotes · code
| 163 | – | cs.CV 147 · cs.AI 31 |
llm-as-judge platforms- Terminal-style Mathematical Modeling Bench: The First Agentic and Verifiable Benchmark for Mathematical Modeling · 2026-11-05 · 12 upvotes · code
- PReMind: When Personal Memory Meets Visual Hazards · 2026-11-18 · 9 upvotes
- Invariant-Aware Harness Enforcement to Protect LLM Agents from Silent API Failures · 2026-11-16 · 4 upvotes · code
- Rubric Semantics or Numerical Priors? Auditing Scale-Direction Bias in LLM Judges · 2026-11-19
- ROAM-GRPO: Enforcing Reasoning Diversity in GRPO via Routed Off-mode Approach Mining · 2026-11-19
- AltRA-Test: An Alternative Annotator Test for LLM Judges Without Shared Annotators · 2026-11-19
- Client Exits - A Way to Increase LLM Transparency on the Client Side · 2026-11-19
- One Framework to Diagnose Them All: A Stratified Benchmark for Bengali LLM Hallucination · 2026-11-19
- AutoPI: Taxonomy-Guided Adaptive Red Teaming for Prompt Injection in LLM Agents · 2026-11-18
- LLM-Assisted Multi-Fidelity Bayesian Optimization: Fusing Expert Knowledge with Numerical Data · 2026-11-18
- Can Programs Replace LLM Judges? Executable Program Judges for Scalable and Efficient Relevance Labeling · 2026-11-18
- Calibrated Decision Rewards: Training Language Models with a Judge That Knows How Sure It Is · 2026-11-18
- Blind Spots Travel, Knowledge Stays Home: What RL Inherits from an LLM Judge · 2026-11-18
- What Does an Agent Need? Bundle-Aware Agent Resource Composition · 2026-11-17
- Right Diagnosis, Unsafe Route: Auditing Clinical AI Decision Trajectories and Corrective Oversight for Validity and Potential Harm · 2026-11-17
- Contract-Explicit Evaluation: From Auditing Learned Readers to Scoped Certificates · 2026-11-17
- SEAM: Computer-Use Agents Know the Harm Between Screens, and Commit It Anyway · 2026-11-17
- Mind the Gap: A Deployed Multi-Agent System for Documentation Maintenance · 2026-11-17
- FinVerify: A Verification Framework for Financial Agents · 2026-11-16
- Tight PAC-Bayes Generalisation Guarantees for Large Language Model Judges · 2026-11-16
- Jev-as-a-Reward: Validating Probabilistic Safety Judges for Reinforcement Learning · 2026-11-16
- Optimistic Verifiers Get Hacked: Reward Hacking Under an Exact Process Oracle · 2026-11-16
- Right Reason, Wrong Advice: Evaluating Recourse in LLM Explanations of Denied Requests · 2026-11-16
- Bookkeeping Is Not Judgement: EJBench, an Engineering Judgement Benchmark Built from a Conjugate Heat Transfer Design Campaign · 2026-11-16
- Eight in Ten LLMs Leak System-Prompt Secrets: Nevan, an Agentic Capture-the-Flag Study · 2026-11-16
| 128 | – | cs.AI 91 · cs.CL 73 |
benchmark datasets- TRIO: Task Refinement with Individual Optimization for Retrieval-Augmented Generation · 2026-11-02 · 9 upvotes · code
- WHU-Road3D: A dataset and benchmark towards fine-grained road surface mapping · 2026-11-19
- Text-Aware, Vision-Blind: How Multimodal Image Editing Systems Handle Unsafe Inputs · 2026-11-19
- CROMPT: Adapting CLIP via Cross-Modal Prompting for Robust Zero-Shot Generalization under Adverse Weather · 2026-11-18
- DyNA-Mixer: Decoupling Time and Topology for Scalable Dynamic Node Affinity Prediction · 2026-11-18
- DSADiff: Data Structure-Aware Diffusion for Crystal Structure Prediction via Mitigating Complexity- and Imbalance-Induced Biases · 2026-11-17
- Confidence-Based Materials Data Quality Assessment via Domain Knowledge and Graph-Structured Learning · 2026-11-17
- A Survey on the Use of Machine Learning within Computer Algebra · 2026-11-17
- Trust the Ray, Not the Depth: Ray-Lateral Agreement for Multi-View 3D Human Pose Fusion · 2026-11-17
- BiGSyn: A Bi-Level Heterogeneous Graph Contrastive Learning Framework for Interpretable Drug Synergy Prediction · 2026-11-16
- STARS: Stage-Adaptive Responsibility Separation for Shadow Removal in Remote Sensing Images · 2026-11-16
- SciWorldBench: Do Video World Models Really Understand Scientific Experiments? · 2026-11-16
- MegNIST, A Benchmark for Non-Invasive Inner Speech Decoding · 2026-11-16
- Can a World Model Predict a Deepfake Video? A Consistency Margin Prior for Deepfake Detection · 2026-11-16
- SGIP: Learning Scene-Grounded Interaction Priors for Scene-Aware Human Motion Prediction · 2026-11-15
- MT-RGCN-DTI: A Multi-Task Relational Graph Convolutional Network for Drug-Target Interaction Prediction · 2026-11-15
- Interpreting Random Forests: Comparing Surrogate Models and Rule Extraction Methods · 2026-11-14
- Towards Explainable Sleep Stage Classification using Single-Channel Electroencephalogram · 2026-11-13
- Clustering-Based Artificial Tree Ensembles for Random Forest Approximation · 2026-11-13
- Revealing the Biases of Large Language Models By Inferring Prior Distributions · 2026-11-13
- Flow-CAD: Flow Matching for Contextual Anomaly Detection and Explanation in Tabular Data · 2026-11-12
- RICapBench: A Fine-Grained Visual Understanding Benchmark Dataset for Vision-Language Models in Remote Sensing · 2026-11-12
- What Limits Thermal Infrared Drone Detection? A Cross-Dataset Benchmark Analysis · 2026-11-12
- HeadIO: Body-Frame Heading Decomposition for Neural Inertial Odometry on Head-Mounted Devices · 2026-11-11
- GingivitisSeg: A Public Dataset and Comparative Benchmark for Gingivitis Segmentation in Intraoral Images · 2026-11-11
| 126 | – | cs.LG 60 · cs.CV 52 |
ai image generation · also image generation- Jeveration: System One Models Now Generate · 2026-11-18 · 121 upvotes · code
- WeLM-Image: A Unified Image Generation Model towards Visual Intelligence · 2026-11-05 · 47 upvotes
- G-STAR: Group-Scaled Token Capacity for Deeply Compressed Autoregressive Generation · 2026-11-08 · 46 upvotes · code
- Latent Reasoning in Continuous Space for Unified Multimodal Models · 2026-10-30 · 45 upvotes · code
- FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation · 2026-10-27 · 34 upvotes · code
- LongBanana: An Expert-Verified Benchmark for Long-Context Multi-Reference Image Synthesis · 2026-11-04 · 32 upvotes · code
- Intrinsic Distribution Matching · 2026-10-29 · 29 upvotes · code
- Read, Allocate, Route: Role-Coupled Tokenization for Pixel-Space Generative Transformers · 2026-10-29 · 20 upvotes · code
- UniSpark: Exploring Hybrid Attention for Multimodal Understanding and Generation · 2026-11-12 · 13 upvotes
- Nemotron-Labs-Diffusion-Uni: Elastic Self-Refining Unified Diffusion LLM with Cross-Paradigm On-Policy Distillation · 2026-10-27 · 12 upvotes · code
- Decoding Without a Decoder: Direct Pixel Prediction from Diffusion Transformers · 2026-11-17 · 11 upvotes
- Cross-modal Steering Vectors Exist Across Both Image and Text Generation · 2026-10-26 · 10 upvotes · code
- Is Forgetting Unified? Exploring Concept Unlearning in Unified Multimodal Models · 2026-11-03 · 5 upvotes
- Unified Law for Visual Tasks (The Four Laws of Computer Vision) · 2026-11-18 · 4 upvotes · code
- Learning Anisotropic Prediction Targets for Flow Models · 2026-11-13 · 4 upvotes
- Beyond the Estimate: Wiener-Informed Decoding for Easier Training of Pixel-Space Flow Models · 2026-10-26 · 4 upvotes · code
- FDSML: Formula-Driven Supervised Metric Learning with Parameter-Aware Triplet Loss · 2026-10-29 · 2 upvotes · code
- Why Flat Drafts Stay Flat: Region-Mean Latents Govern Texture in Flow-Based Image Generation · 2026-11-19
- HiUni: Harmonizing Understanding and Generation in Shared Visual Space · 2026-11-19
- Text-Aware, Vision-Blind: How Multimodal Image Editing Systems Handle Unsafe Inputs · 2026-11-19
- ReSynth: Constructing Synthetic Supervision for Multi-Image Understanding · 2026-11-18
- Learning with Unlearning: Synaptic Role Partitioning for Simultaneous Continual Learning and Machine Unlearning · 2026-11-18
- Why Multi-Source Audio Fails to Compose: A Geometric Diagnosis and Its Remedy · 2026-11-18
- MLIE-CoT: Chain-of-Thought Reasoning via Multi-Level Image Editing · 2026-11-18
- Ultimate3D: Teaching Multimodal LLMs 3D Camera-Object Relations by Large-Scale Visual Instruction Data · 2026-11-18
| 123 | – | cs.CV 106 · cs.AI 30 |
speech models- Apriel Voice 27B Preview: An Open Model for Speech, Reasoning, and Tool Use · 2026-10-29 · 36 upvotes
- Marimba: A System One Model for Speech · 2026-11-13 · 6 upvotes · code
- Lipi-Ghor: A Large-Scale, Diarized, Multi-Domain Bengali Speech Corpus and a Scalable Pipeline for Building It · 2026-10-26 · 3 upvotes · code
- GigaSpeech 3: Scaling Multi-Dialect Arabic Speech Recognition with Weakly Labeled Data · 2026-11-02 · 2 upvotes · code
- Joint Language Modeling for In-the-Wild Speech-Scene Generation with Distinct Token Representations · 2026-11-19
- DRVEXO-4B-Unified: Design and Evaluation of a Modular Speech-Vision System · 2026-11-19
- Xing-Audio-NVVASR: Scaling and Refining Supervision for Joint Recognition of Speech and Non-Verbal Vocalizations · 2026-11-19
- Induction Head Origins of SLAM-ASR Speech Recognition Models · 2026-11-18
- Sex Differences in the Detection of Parkinson's Disease from Speech · 2026-11-18
- Gaspard: Expressive unified speech and gesture synthesis with continuous autoregressive flow-matching and decoupled classifier-free guidance · 2026-11-18
- Event-Based Dynamic Lip Region Estimation During Speech · 2026-11-17
- Towards Microphone-Invariant Speech Representations for Transformer-Based Voice Disorder Detection · 2026-11-16
- MegNIST, A Benchmark for Non-Invasive Inner Speech Decoding · 2026-11-16
- DuoFlow: Towards Synchronized Speech and Motion Generation with Fine-Grained Control · 2026-11-16
- An Interpretable Acoustic Coordinate System for Japanese Consonant Morae in Dysarthric Speech · 2026-11-15
- ProTTS: End-to-End Prominence-aware Natural and Controllable Text-to-Speech via Automatic Word Stress Discovery · 2026-11-15
- Grounding Language Models in Speech Does Not Fix "AI Flavor": Calibrated LLM Judges, Goodhart Traps, and a Preference-Tuning Fix · 2026-11-15
- A Dataset for Misogyny Detection in Polish Social Media: Transferability of Hateful Speech Detection from General to Specific Types of Hate · 2026-11-15
- Decode Early, Verify Late: Streaming Offline Speech Recognizers Without Accuracy Loss · 2026-11-15
- Beyond Controllability: Speaker Diversity in Instruction-Guided Text-to-Speech · 2026-11-14
- Latency, Speech Recognition and Turn-Taking in Voice Agents for Spanish Phone Negotiation: An Externally Measured Comparison of Pipecat, LiveKit and GPT-Live · 2026-11-14
- A Systematic Study of Cross-Token Transfer for Data-Efficient Non-Verbal Text-to-Speech · 2026-11-14
- CausalGloss: Multi-Evidence Action Control for a Simultaneous Mandarin Speech-to-ASL Gloss Cascade · 2026-11-14
- Sada-ASR: A Production Multidialectal Arabic Speech Recognition System · 2026-11-14
- What Do Multilingual Self-Supervised Speech Encoders Know About Sentence Meaning? · 2026-11-13
| 109 | – | cs.CL 68 · cs.AI 32 |
ai knowledge graph platforms- From Sequence Uncertainty to Phenotype Hypotheses: Uncertainty-Conditioned Inference over Biomedical Knowledge Graphs · 2026-11-19
- STARK: Moving towards Personalized Agents That Truly Learn and Remember · 2026-11-19
- Verifiable Logic in Medical LLMs: A Critical Review of Agentic Clinical Reasoning Optimization and Neuro-Symbolic Grounding · 2026-11-19
- From Cases to Criteria: Reusing Evaluation Knowledge for Task-Specific Rubric Generation · 2026-11-19
- GenSPARQL: A Generative Extension of SPARQL for Incomplete Knowledge Graphs · 2026-11-19
- Similarity-based OSF Logic for Flexible SPARQL Query Answering · 2026-11-19
- OpenKAGE: Open-Ended Lifelong Learning in the Open World via Knowledge-Sharing Agent-Group Evolution · 2026-11-18
- NaviGATE: Noise-Aware Dual-View Generation for Multimodal Knowledge Graph Reasoning · 2026-11-18
- Ground, Iterate, Trace: Decomposing AI Research Ideation · 2026-11-18
- Deploying a Control-Logic LLM Assistant in Air-Gapped Power Plants: Lessons in Source Authority and Bounded Retrieval · 2026-11-16
- A Generative AI-Driven Architecture for Whole-Home Intelligent Services: Edge Models, Memory Management, and Household Applications · 2026-11-16
- TUSI: A Citation-Grounded Graph-Based Benchmark · 2026-11-16
- Interactive Structured Environment Scaling for Large Language Model Agentic Reasoning · 2026-11-15
- MT-RGCN-DTI: A Multi-Task Relational Graph Convolutional Network for Drug-Target Interaction Prediction · 2026-11-15
- Understanding Contextual Bias in Agricultural CNNs Through Hidden-Neuron Concept Induction · 2026-11-13
- Model Maps: A Documentation Framework for Tracing Foundation Model Ancestry and Understanding AI Entanglement · 2026-11-13
- Causals: An Open Knowledge Graph for Research on Causal Reasoning · 2026-11-12
- Time-Consistent Evaluation of Hierarchical Code Graphs for SWE Agents · 2026-11-12
- Typed Knowledge over Constructive Institutions: A Proof-Relevant Type Theory for Verified Science · 2026-11-11
- AutoOntic: Automatic Ontology Induction from Text for Knowledge Graph Construction · 2026-11-11
- HeriKGQA: Grounded Knowledge-Graph Question Answering over Cultural Heritage Sensor Data · 2026-11-11
- The WoW: A Large-Scale World Knowledge Corpus for Full-Lifecycle LLM Training · 2026-11-10
- Megrez: A Knowledge-Guided Agent for Formal Mathematics over MK Set Theory · 2026-11-10
- Chain of Physics: Supporting Fault Diagnosis with Engineering-Inspired Large Language Model Reasoning · 2026-11-10
- HiddenPathQA: A Benchmark for Knowledge Graph Question Answering When Questions Hide Their Paths · 2026-11-09
| 102 | – | cs.AI 76 · cs.CL 38 |
retrieval-augmented generation rag- Incentivizing Self-Learning in Large Language Models via Reinforcement Learning · 2026-10-29 · 34 upvotes
- Retrieval Augmented Generation Compositionality · 2026-10-21 · 33 upvotes · code
- DeFT-RAG: Decomposing Multi-Hop Questions into Self-Contained Sub-Questions with Reusable Answers · 2026-10-27 · 13 upvotes · code
- TRIO: Task Refinement with Individual Optimization for Retrieval-Augmented Generation · 2026-11-02 · 9 upvotes · code
- Signed but Steerable: Measuring and Closing the Text-Vector Integrity Gap in Offline Retrieval-Augmented Generation · 2026-11-04 · 5 upvotes · code
- Enhancing Stock Market Information Retrieval with Retrieval-Augmented Generation · 2026-11-02 · 2 upvotes · code
- HERIT: Enabling Global Access to Hanja-to-English Historical Translation by Mitigating Temporal Bias · 2026-11-03 · 1 upvotes · code
- AutoRAGBench: A Benchmark for LLM Agents Automating RAG System Development · 2026-11-19
- A Hybrid RAG Framework for Deceptive Review Detection: Integrating RoBERTa-LoRA, FAISS-Based Retrieval, and LLM Reasoning · 2026-11-18
- KnowledgeClaw: Towards Agentic Knowledge Engineering via Omnimodal Hypergraphs · 2026-11-18
- StitchRAG: Constructing Compact and Evidence-Preserving Contexts for RAG with Diffusion-Based Stitching · 2026-11-17
- RagHarnessDebugger: Jev-Guided Agentic RAG in Contract Inference Repair Auditing · 2026-11-17
- TUSI: A Citation-Grounded Graph-Based Benchmark · 2026-11-16
- Bioformer-RetroMAE: retrieval-oriented pretraining of a compact biomedical language model for literature search · 2026-11-15
- Security of Deep Research Agents: Attack Surface, Defenses, Benchmarks, and Agenda Seeding against Research Planning · 2026-11-15
- Estimating Outpatient Visit Prices from Hospital Price Transparency Data using Large Language Models · 2026-11-15
- RAG-FGO: Dynamic Optimization of Query-Rewriting Agents for Generative RAG · 2026-11-13
- RMIT-ADM+S at TREC RAG 2026: Research Agents, Retriever Ablations, and Open-Weight Replication · 2026-11-12
- AstroMemBench: A Benchmark for Memory Systems in Embodied Spacecraft Agents · 2026-11-12
- Edge-Native Multimodal RAG: Hardware-Aware Quantization and Architectural Optimization for Consumer GPUs · 2026-11-11
- DISCERN: Preserve at Write, Resolve at Read for Persistent LLM-Agent Memory · 2026-11-11
- OpticalRAG: Pixel-Space Compression for Token-Efficient Retrieval-Augmented Generation · 2026-11-10
- Chain of Physics: Supporting Fault Diagnosis with Engineering-Inspired Large Language Model Reasoning · 2026-11-10
- ARMOR: Adaptive Curriculum Meta-Learning for Noise-Robust RAG Reasoning · 2026-11-09
- Operation-aware Multimodal Clinical Decision Support System for ICU Discharge Risk Assessment · 2026-11-09
| 76 | – | cs.AI 47 · cs.CL 40 |
mobile- Mobile AI Factory: Building Specialized Language Models for Your Mobile Device · 2026-11-10 · 16 upvotes · code
- iPrefBench: A User-Centric Benchmark for Personalized Mobile Use Agents · 2026-10-26 · 12 upvotes
- HALO: Human-Aligned Data Collection for WhoLe-body MObile Manipulation · 2026-11-12 · 10 upvotes · code
- Learning to Move from and for Manipulation Policies: Spatializing Latent Action Representations for Goal-Pose-Free Mobile Manipulation · 2026-11-19
- MATE: Mobile Agent Trustworthy Execution for Safe and Efficient Mobile Control · 2026-11-19
- MobileWeave: Program-First Synthesis of Dependency-Linked Tasks for Training Mobile GUI Agents · 2026-11-18
- High-Precision Docking of Differential-Drive Mobile Robots Through LiDAR and Vision Collaboration · 2026-11-18
- Single-Controller Teleoperation and Multimodal Dataset Generation for a Mobile Manipulator · 2026-11-18
- Hierarchical Admittance-Impedance Control for Mobile Manipulator Load Transfer · 2026-11-18
- Mapping the Wind to Find the Source: Online Physics-Informed Gas Source Localization with Mobile Robots · 2026-11-18
- Cross3DGS: Unified Vulkan-Based 3D Gaussian Splatting Training from Workstations to Mobile Devices · 2026-11-17
- Technical Report of Mobile Manipulator Robot for Industrial Environments · 2026-11-17
- Tracking Ethological Behaviors of Broiler Chickens Through Computer Vision (YoloV11) Using an Android Mobile Device · 2026-11-17
- AdaModalX: Synchronization-Free MFM Inference for Distributed Multimodal Mobile Sensing via Progressive Data Orchestration · 2026-11-16
- Vision-Language Grounded Semantic Navigation for Autonomous Mobile Robots · 2026-11-16
- UbiHearo: Bringing Scenario-Aware Sound Guidance to DHH Users with Mobile Agents · 2026-11-16
- Cooperative Mobile Manipulation using Learned Dynamical Systems · 2026-11-16
- AdaFlowLite: Scalable and Non-blocking Inference on Asynchronous Mobile Data · 2026-11-16
- dit.xpu : Taming DiT Sparse Inference on Mobile SoCs · 2026-11-14
- PoliMop: Policy-in-the-Loop Motion Planning in 3D Spaces for Mobile Robots · 2026-11-13
- FETTUCCINE: Fast and efficient brain-to-text decoding on mobile devices · 2026-11-13
- Autonomous Mobile Robots on a Computing Field · 2026-11-12
- MobileProbe: Adaptive Security Evaluation of Mobile Agents via Trajectory-Aware Injection · 2026-11-12
- Acoustic Respiratory Phase Detection on Mobile Devices · 2026-11-12
- Report of the 8th LSVOS Challenge: Mobile Unified Multimodal Understanding · 2026-11-12
| 69 | – | cs.RO 37 · cs.CV 23 |
ai video understanding models- StreamVibe: Proactive Video Agents for Evolving User Intent · 2026-10-26 · 75 upvotes
- Turns Matter: Advancing Streaming Video RL via Turn-Level Credit · 2026-11-04 · 28 upvotes · code
- AskStream: When and What to Ask Proactively under Uncertainty in Streaming Video Understanding · 2026-10-28 · 12 upvotes · code
- BLIP-Live: Balancing Timeliness & Firing Precision in Proactive Streaming Video Agents · 2026-11-16 · 9 upvotes
- SleuthVLM: Do We Really Need Audio-in-Video for Omni Video Understanding? · 2026-11-04 · 6 upvotes · code
- EVAThink: Evidence Sufficiency-Guided Training for Adaptive Thinking in Video Understanding · 2026-11-10 · 5 upvotes · code
- NexSight: Verifiable Tasks for Fine-Grained Agentic Long-Video Understanding · 2026-11-17 · 4 upvotes
- MemInStream: Memorizing or Merely Recognizing? Rethinking Streaming Video Memory Evaluation · 2026-11-11 · 4 upvotes · code
- ActMem: From Latent Memory Reasoning to Grounded Robotic Action · 2026-11-19
- VidToC: Rethinking Video Token Compression for Multimodal Large Language Models · 2026-11-19
- ForeSeek: Foresight-Driven Reasoning for Long-Form Video Understanding · 2026-11-19
- Better Retrieval, Not Better Binding: Pretraining Exposure in Egocentric Video Retrieval · 2026-11-19
- WeMM-Video: Pushing the Frontiers of Open-Source Omni-Modal Video Understanding · 2026-11-19
- NullTok: empirical-null token selection for training-free long video understanding · 2026-11-18
- SimplePro: A Simple Baseline for Proactive Video Understanding · 2026-11-18
- APS: Adaptive Partitioning-Based Frame Selection for Long Video Understanding · 2026-11-18
- VideoACE: Benchmarking Agentic Video Understanding through High-Frame-Rate Actions · 2026-11-18
- Look Closer, Look Back, or Wait for Agentic Streaming Video Understanding · 2026-11-18
- A$^3$Bench: Compositional Reasoning over Aggressive Interactions in Videos · 2026-11-18
- Cap-and-Track: Optimizing LLM Inference Request Dispatch Across Shifting Capacity · 2026-11-18
- EgoPass-Bench: Identifying Objects That May Affect the Wearer's Passage in Egocentric Video · 2026-11-18
- Cross-Modal StateKV Injection for Communication in Multi-LLM Systems across Temporal Segments · 2026-11-17
- FrameRouter: Frame Budget Routing for Long-Video Understanding on Video-MME-v2 and Beyond · 2026-11-17
- Lost in the Hallway: Benchmarking Persistent Spatial Memory Across Revisits · 2026-11-16
- RAVEN-Bench: A Paired EO-IR Video QA Benchmark for Aerial Multimodal Understanding · 2026-11-13
| 68 | – | cs.CV 63 · cs.AI 20 |
humanoid robot platforms- DyCraft: An Agentic System for Long-Horizon 4D Scene Generation · 2026-10-29 · 6 upvotes · code
- HuGe: Scaling Humanoid Generalist Vision-Language-Action Models with Egocentric Experience · 2026-10-25 · 4 upvotes · code
- ODE Policy: Robot Learning via Action Dynamics, Not Actions · 2026-11-01 · 1 upvotes · code
- Reference-Free Humanoid Skateboarding via Termination-Shaped Reinforcement Learning · 2026-11-19
- Controlling the Humanoid Robot H1-2 With a Simulated Biologically Plausible Network · 2026-11-19
- PhyDEX: A Benchmark for Physical Reasoning in Vision-Language-Action Models via Dynamic Extrinsic Dexterity · 2026-11-19
- PGX: Physically Grounded Execution for Long-Horizon Humanoid Loco-Manipulation · 2026-11-19
- ReLoco: Unified Humanoid Locomotion and Fall Recovery via Behavior-Conditioned Motion Priors · 2026-11-18
- Autonomous Track Racing with a Commercially Available Humanoid: System Design and Real-World Deployment · 2026-11-17
- SG-ODOM: Event-Driven Proprioceptive State Estimation with Stability-Gated Contact Updates for Legged Robots · 2026-11-16
- Driving the Style: Velocity-Conditioned Whole-Body Control from Motion Demonstrations · 2026-11-16
- ROSE: A Shared Cross-Embodiment Facial-Motion Latent Space for Humanoid Robot Expression · 2026-11-16
- MoViC: Real-Time Humanoid Whole-Body Control from Monocular Video Streams · 2026-11-15
- Leaning Over to Reach Far-Away Objects · 2026-11-14
- ImpedanceMimic: Learned Impedance as Action Space for Force-Accurate Motion Imitation · 2026-11-14
- PERA: Plug-in Experts for Robotic Actions in Continual Whole-Body Control · 2026-11-12
- BlinkMimic: Training a Humanoid Motion Tracker in Minutes on a Single GPU · 2026-11-12
- X-Nav Technical Report: Real-World Long-Horizon Indoor-to-Outdoor Navigation on a Humanoid Robot · 2026-11-12
- Can I join you? Extended Social Force Based Model with Predictive Control and Barrier Functions for Humanoid Group Repositioning Amidst Obstacles · 2026-11-11
- From a Single RGB Image to Robot Execution: Metric Scene Alignment and Contact-Guided Retargeting · 2026-11-11
- ILA: A Transferable Interface-Level Adapter for Compliant Humanoid Motion Tracking · 2026-11-11
- Reading the Table: Sim-to-Real Game State Detection for the Chef's Hat Card Game · 2026-11-11
- Runtime Safety and Emergency Stops on a Full-Size Humanoid: Deployment Lessons and a Case for Graduated Force Authority · 2026-11-11
- ReACT: Reflection-Consistent Modulation and Cross-Load Consistency for Humanoid Velocity Tracking Under Asymmetric Loads · 2026-11-10
- Personalized Affective Perception via Continual Learning in Human-Agent Negotiation · 2026-11-10
| 63 | – | cs.RO 62 · cs.AI 11 |
scaling laws- Proving and Improving the Platonic Representation Hypothesis with JEPAs · 2026-10-29 · 79 upvotes · code
- Open-HumanWAM: An Open Recipe for Scaling Human and Robot Experience for Embodied Foundation Models · 2026-11-04 · 36 upvotes
- Ropedia Xperience 2: A Gold Standard for Scaling Physical AI Environments and Behaviors · 2026-11-12 · 35 upvotes · code
- e-means: outperforming k-means (in one-tenth the epochs) · 2026-11-06 · 20 upvotes · code
- Emergent Biological Capabilities in a Foundation Model for Molecular Interactions · 2026-11-10 · 10 upvotes
- Hierarchical Residuals: A Minimalist Decoupling of Residual Width from Compute Width · 2026-10-30 · 9 upvotes
- Latent Feedback Is a Compute and Data Amplifier · 2026-11-16 · 6 upvotes · code
- Blind Variation, Selective Retention: Improving Creative Idea Generation in AI Scientists · 2026-11-09 · 5 upvotes · code
- Know, then Draw: A New Learning Paradigm for Visual Generation · 2026-10-27 · 3 upvotes
- Awaken-HI: Scaling Humanoid Intelligence with Whole-Body Human Experience · 2026-11-19
- Test-Time Symmetrization: Scaling Laws for Model-Agnostic Learning under Structure · 2026-11-18
- Towards Reliable Scaling Laws for Tabular Foundation Models · 2026-11-18
- Scaling Laws for Vision-Language Fusion · 2026-11-17
- QTOP: Scaling Humanoid Motion Tracking with Quantile Critics · 2026-11-16
- Deep Learning for Physicists: From Linear Regression to Reasoning Models · 2026-11-16
- $β$-number and Its Applications to Data Science · 2026-11-14
- A Geometric Understanding of Denoising Autoencoder with Applications to Image Denoising · 2026-11-14
- Condensing Law of Security Information · 2026-11-13
- When and How SignSGD Outperforms SGD: A Functional Scaling Law Perspective · 2026-11-12
- Capacity-Constrained Delayed Feedback for Online Conformal Risk Control · 2026-11-12
- ArchSpace: Recording, Reviewing, and Referencing LLM Architecture Research · 2026-11-12
- Are Scaling Laws of Universal MLIPs Universal? · 2026-11-11
- Curiosity-0826-4B: Generative Medical Event Sequence Modeling Across Pediatric and Adult Populations · 2026-11-11
- Physics-based simulation unlocks scaling laws for generalizable MRI reconstruction · 2026-11-11
- Beyond the Log-Linear Frontier: Pre-Asymptotic Analysis of Finite-Budget Neural Scaling Laws · 2026-11-10
| 61 | – | cs.LG 43 · cs.AI 22 |
diffusion language models- Different Tasks, Different Timesteps: Temporal Task-Aware Quantization for Diffusion Language Models · 2026-10-22 · 17 upvotes · code
- Test-Time Scaling for Diffusion Language Models with Frequency-Aware Remasking · 2026-11-07 · 10 upvotes
- BYOD: Build Your Own DLM - Efficient Autoregressive-to-Diffusion Language Model Conversion · 2026-10-30 · 10 upvotes · code
- What Makes a Good Unmasking Policy? A Controlled Study of Learned Unmasking in Diffusion Language Models · 2026-10-22 · 6 upvotes
- Looped Uniform Diffusion Language Models · 2026-10-21 · 5 upvotes
- TRAC: Efficient Diffusion Language Models for Machine Translation via Length-Aware Decoding · 2026-11-19
- Closing Performance Gap for Diffusion Language Models under Low Inference Budgets · 2026-11-19
- One Schedule Does Not Fit All: Adaptive Inference Schedules for Diffusion Language Models · 2026-11-19
- dLoop: Looped Diffusion Language Models via Recurrent Latent Refinement · 2026-11-19
- Beyond Replacement: Levenshtein Editing for Diffusion Language Models · 2026-11-18
- Clover-35B-A3B-Preview Technical Report · 2026-11-18
- RISA: Recoverable Sparse Attention for Block-Diffusion Language Models · 2026-11-17
- ReMaRL: Learning to Unmask and Remask in Frozen Diffusion Language Models · 2026-11-17
- Fast at the Frontier, Wrong at the Fallback: A Commit-Level Analysis of Threshold Decoding in Diffusion Language Models · 2026-11-16
- The Hidden Cost of MoE Diffusion Decoding: Profiling and Fixing the Sampler · 2026-11-16
- Empowering Masked Diffusion Models to Self-Correct with Leave-One-Out Transformers · 2026-11-14
- SemMask: Semantic-Prioritized Progressive Masking for Diffusion Language Models · 2026-11-14
- See Every Block Once: Variance-Reduced Post-Training for Masked Diffusion Language Models · 2026-11-13
- Learning When Diffusion Language Models Should Regenerate · 2026-11-12
- Schedule-Calibrated Commitment Order in Blockwise Masked Diffusion Language Models · 2026-11-11
- Blurring the Block Boundaries: Overlapping Block Denoising for Efficient Diffusion Language Models · 2026-11-10
- When Should Diffusion Language Models Reconsider Their Commitments? · 2026-11-08
- FEROM: Frontier Endogenous Reveal-Order Marginal Policy Optimization for Masked Diffusion LMs · 2026-11-07
- DUET: Dual-Sparse Inference for Block Diffusion Language Models · 2026-11-06
- PBPO: Prefix-Block Policy Optimization for Diffusion Language Models · 2026-11-05
| 58 | – | cs.CL 40 · cs.AI 27 |
convolutional networks- Life-IQA+: Boosting Blind Image Quality Assessment via GCN-enhanced Layer Interaction and Flexible Hierarchical Expert Specialization · 2026-11-19
- Lightweight Low-Frequency Non-Intrusive Load Monitoring via Karhunen-Loève Feature Distillation and Temporal Convolutional Networks · 2026-11-19
- Phantom of the Masquerade: Graph Neural Network-Based Detection of Masquerade Attacks in Controller Area Networks · 2026-11-19
- A Practical Proprioceptive Data Collection Utility for the Unitree GO1 · 2026-11-19
- Predicting Surface Displacement Fields of Laser Powder Bed Fusion Parts Using STL-Derived Graphs and Part-Level Descriptors · 2026-11-19
- Training Vision Models for LLM-Driven Weight-Space Programming · 2026-11-19
- Supervised Hebbian Class Networks: Learning Without Backpropagation · 2026-11-18
- A Temporal Convolutional Network with Multi-Head Attention Model: A Surrogate for Parallel DEVS Semiconductor Fab Simulation · 2026-11-16
- When Does Discrete Ricci Curvature Help? An Edge-Level Analysis of Curvature-Enhanced GCNs for PPI Prediction · 2026-11-16
- Local Order Matters: A Lightweight CPU-Trainable CNN for Website Fingerprinting on Defended Tor Traffic · 2026-11-15
- MT-RGCN-DTI: A Multi-Task Relational Graph Convolutional Network for Drug-Target Interaction Prediction · 2026-11-15
- Attention U-Net Cellular Automata for Multi-Class Land Use and Land Cover Change Simulation in Lucknow, India: Evaluation Against Null and Classical Baselines · 2026-11-14
- Efficient Poincaré Convolutions through Patch-Statistics Factorization · 2026-11-13
- Multi-Assay Antibody Developability Prediction with Shared Structure-Language Representations · 2026-11-13
- A Dual-Branch Graph and Convolutional Network for Interpretable Movement EEG Classification · 2026-11-12
- Analysis choices decide whether untrained networks beat trained ones at V1: a multiverse analysis of model-brain RSA · 2026-11-11
- CABrain: A Correlation-Aware Brain Foundation Model for EEG Decoding · 2026-11-09
- Benchmarking CNNs, Vision Transformers, and Foundation Models for Explainable Brain Tumor MRI Classification: Calibration, Decision Analysis, and External Validation · 2026-11-09
- Hierarchical Multi-Channel Tip-Over Prediction via Isolated Temporal Models for Planetary Rover Safety · 2026-11-09
- Is a CNN-Transformer Ensemble Worth It When a Chest X-Ray Foundation Model Is Available? · 2026-11-09
- Unified Framework with Convex-Concave Decomposition and Sparse Topological Learning for Skeleton-Based Clinical Assessment · 2026-11-07
- ConwayNet: Interpretability, Activation Coherence, and Noise Resilience via a Game-of-Life-Inspired Lateral Inhibition in Artificial Neural Networks · 2026-11-07
- Trained, Frozen, or Absent: Identifying What a Quantum Layer Contributes to Cross-Sectional Equity Ranking · 2026-11-07
- Interpretable Cyber-Physical Attack Detection in Smart Grids: A Leakage-Controlled Multi-Testbed Evaluation of Fusion, Robustness, and Observability Limits · 2026-11-07
- Network Contention State Aware Dynamic Optimizer for Accelerator Collective Communication Libraries · 2026-11-07
| 55 | – | cs.LG 39 · cs.CV 20 |
ai financial services platform- LLMs Don't Know What They Know: Benchmarking Temporal Self-Knowledge for Financial Backtesting · 2026-11-04 · 35 upvotes
- Human-Centred, Risk-Constrained Evaluation of Financial Document Recognition: Evidence, Critical Errors, and Selective Automation · 2026-11-02 · 6 upvotes
- How Much Does the Hint Matter? Scope Conditions for Hindsight Self-Distillation in Financial Reasoning · 2026-10-26 · 5 upvotes · code
- FinForesight: A Diagnostic Backtesting Benchmark for Deep Research Systems in Financial Forecasting · 2026-11-01 · 4 upvotes
- JFinBench: A Continuously Refreshable Japanese Financial Benchmark from the Latest Certification Exams · 2026-11-13 · 3 upvotes · code
- FinVeriQA: Financial Research Agents for Question Answering: Routing, Retrieval, MCP Tool Use, and Provenance-Aware Evidence Verification · 2026-11-18
- DDSL: Iterative Self-Labeling for Financial Market States · 2026-11-17
- Can LLMs Understand What They Predict? Evaluating Latent Causal Structure Inference in Financial Markets · 2026-11-17
- FinVerify: A Verification Framework for Financial Agents · 2026-11-16
- FinVision: Multimodal AI for Visualizing Financial Narratives · 2026-11-15
- Can You Trust Your Finance Agent? Drift, Diagnosis and Auditable Intervention on One Shipped Financial Research Agent · 2026-11-13
- How Much Do Foundation Models Add to Gradient Boosting on Financial Event Sequences? · 2026-11-13
- TAPES: Terminal Adjoint-Propagated Error Scheduling for Financial Diffusion Samplers · 2026-11-12
- Quantum Recurrent Architectures for Financial Time Series Prediction · 2026-11-11
- Online-Adaptive Fuzzy Cognitive Maps for Neuro-symbolic Financial Forecasting · 2026-11-10
- Tabular Foundation Models in Financial Predictions · 2026-11-10
- FinCutBench: A Continually Updated Benchmark for Measuring the Temporal Boundaries of LLM Financial Knowledge · 2026-11-08
- TailDART: Compute-Efficient Foundation Models for Financial Time-Series Forecasting · 2026-11-06
- Scenario Augmentation for Rare Financial Events via Multimodal Latent Diffusion · 2026-11-05
- FinEvolveKG: Controlled and Attributable Prompt Evolution for Financial Knowledge Graph Construction · 2026-11-05
- AgenticFinBench: Benchmarking Financial Agents on Diverse Tasks from Real-World Requests · 2026-11-03
- When Self-Verification Hurts: Calibrated Answer Repair for Financial Question Answering · 2026-11-03
- Improving Financial Cybersecurity Through Fraud Transaction Detection with Deep Learning · 2026-11-02
- Can We Stop the Backtest Yet? Anytime-Valid Promotion Tests for Adaptive Financial Research Agents · 2026-11-02
- TrackMem: Tracking Evolving Beliefs in Long-Horizon Financial Dialogue · 2026-11-01
| 50 | – | cs.AI 29 · cs.LG 19 |
ai multimodal reasoning models- Zooming without Zooming v2: From Seeing Details to Connecting Evidence for Generalizable Multimodal Perception · 2026-10-27 · 27 upvotes · code
- Diagnosing the Reference Gap: What Visual Scaffolds Can and Cannot Fix in Multimodal Reasoning · 2026-10-29 · 18 upvotes · code
- SOMA: A Benchmark for Fine-Grained Egocentric Behavior and Body-Motion Understanding · 2026-10-26 · 10 upvotes · code
- AVTR: Adaptive Multimodal Reasoning with Visual Imagination · 2026-11-18 · 3 upvotes · code
- A Cross-Scenario Survey and Analysis of Self-Evolving Multimodal Agents · 2026-11-10 · 3 upvotes · code
- M3OPD-Reasoner: An Open Recipe for Post-Training Multimodal Reasoning with Multi-Teacher On-Policy Distillation · 2026-11-17 · 2 upvotes · code
- ResVision: Spectrum-Matched Resizing and Context-Preserving Inspection for Visual Reasoning · 2026-11-19
- A Hierarchical Onboard Vision-Language-Navigation Framework for Aerial Robots in Complex Environments · 2026-11-18
- NaviGATE: Noise-Aware Dual-View Generation for Multimodal Knowledge Graph Reasoning · 2026-11-18
- Can Vision-Language Models Truly Understand Images? A Benchmark Beyond Commonsense Bias · 2026-11-17
- Eyes in the Update? Learning Where Rewards Land in Multimodal Reasoning · 2026-11-17
- PACD: Provenance-Aware Consensus Decoding for Mitigating Cross-Modal Hallucinations in Omnimodal Large Language Models · 2026-11-17
- Understanding Cross-Modal Inconsistency through Representation Subspaces in Omni Models · 2026-11-17
- ReAccess: Look Once, Stay Focused with Efficient Test Time Memory · 2026-11-16
- Sketch, Don't Paint: Allocating Test-Time Compute in Generative Visual Reasoning · 2026-11-16
- Teach with Blinks: Breaking Linguistic Momentum in On-Policy Distillation for Fine-Grained Multimodal Perception · 2026-11-12
- DisasterAgent: An Evidence-Driven Agent for Verifiable Disaster Report Generation From Remote Sensing Imagery · 2026-11-10
- DISCOVER: Online Variance-Guided Data Discovery for Budgeted Multimodal GRPO · 2026-11-08
- Mental Imagery That Matters: Curing Latent Collapse in Multimodal Reasoning · 2026-11-07
- Annotator-Free Object Detection via Foundation Model Collaboration · 2026-11-04
- Entropogram-guided Visual Realignment Decoding: Capturing the Rhythm of Multimodal Reasoning · 2026-11-04
- Trick-or-Treat: Adversarial Evaluation of Multimodal Medical Reasoning with Synthetic Images · 2026-11-04
- VIGOR: Visual Gain Ordering for Hallucination Mitigation in Multimodal Discrete Diffusion Language Models · 2026-11-03
- Lookahead Prediction-Guided Adaptive Visual Refocusing for Interleaved Multimodal Reasoning · 2026-11-02
- MIRA: Reinforcing Multimodal Reasoning via Deceptive Contextual Augmentation · 2026-11-02
| 39 | – | cs.CV 24 · cs.AI 20 |
ai satellite intelligence- DySENSE: Dynamic Spatiotemporal ENergy Synthesis and Emulation with Satellite Imagery · 2026-11-13 · 14 upvotes · code
- EarthRecord: From Pixels to Land Change with Multimodal Agents over Four Decades of Satellite Imagery · 2026-11-06 · 4 upvotes · code
- Does It Depend on the Split? Frozen Satellite Features vs. Fine-Tuned CNNs for Tree Species Mapping · 2026-11-19
- Monitoring Unplanned Construction Using Satellite Change Detection · 2026-11-18
- Arboreus: A Realistic Boreal Forest Simulator with Topographic Terrain and Satellite-Informed Parametric Tree Distributions · 2026-11-17
- Language Models Meet Vibration Testing for LEO Constellation Satellites with Calibrated Response Prediction from Few-show Sweeps · 2026-11-16
- Deep Learning for Satellite-Based Mountain Hazard Screening: A Retrospective Failure Analysis on the 2021 Chamoli Rock-Ice Avalanche · 2026-11-16
- Illusion of Explainability: A Sanity Check for Spectral Band Attribution in Satellite Time-Series Crop Classification · 2026-11-15
- Kolmogorov-Arnold Lookup Table Demappers for Amplitude Phase-Shift Keying over Nonlinear Satellite Links · 2026-11-15
- PUMA-Former: Uncertainty-Aware Agentic Computation Offloading in MEO-LEO Satellite Networks With Incomplete Information · 2026-11-13
- Lens: Training-Free Semantic Search for Cross-Tile Object and Scene Retrieval in Satellite Imagery · 2026-11-13
- Predicting the Needle in a Petabyte Scale Haystack: Open-Vocabulary Event Anticipation in Satellite Imagery · 2026-11-11
- Satellite Pretraining Is Not One Thing: A Matched-Pair Study of Generic and Earth-Observation Foundation Models for Scene Classification · 2026-11-10
- PARDIG: Global Precipitation Estimates Learned from Sparse Satellite Observations · 2026-11-10
- HaiRuo: Forecasting Ocean Eddies as Fields and Objects with a Satellite-Altimetry Foundation Model · 2026-11-10
- Evaluation of a Multi-Link Machine Learning Approach for Rainfall Detection Using Satellite Microwave Links · 2026-11-06
- Georeferenced Cross-View 3D Reconstruction from Ground and Satellite Images · 2026-11-05
- Detecting Weather Fronts from Satellite Observations: What Does Reanalysis Add? · 2026-11-05
- Generative AI for urban planning: synthesizing land-use maps with satellite imagery via DualControlNet · 2026-11-04
- When Does Risk-Controlled Throughput Forecasting Actually Control Risk? A Reproduction Study on LEO Satellite Link · 2026-11-04
- ReSMap: Recasting Satellite Priors for Robust and Accurate Online HD Map Construction · 2026-11-03
- Large Language Model-Assisted Adaptive Heuristic Search for Agile Earth Observation Satellite Scheduling · 2026-11-03
- Offline Approximate Value Iteration: A Reinforcement Learning Approach for Satellite Constellation Deployment · 2026-11-02
- An intelligent satellite must do nothing well · 2026-11-02
- An Empirical Study on Learning Rooftop Solar Potential from Satellite Imagery Directly Without Explicit Geometry · 2026-10-30
| 37 | – | cs.CV 21 · cs.LG 15 |
right- Multi-Token Prediction Done Right · 2026-10-28 · 23 upvotes · code
- When Do LLMs Model the Right Target? Problem Formulation in High-Stakes Risk Prediction · 2026-11-18
- Finetuning VLAs for Dexterous Manipulation: The Right Checkpoint Is All You Need · 2026-11-18
- What Right-Angle Corners Reveal About an Uncalibrated Camera: Convex Cones, Certified Bounds and Identifiability · 2026-11-18
- Choosing the Right Representations: Task-Aware Fusion for Multimodal Materials Language Models · 2026-11-18
- Right Labels, Wrong Reasons: Signed Feature Attribution for Multi-Label Explainability · 2026-11-17
- Right Diagnosis, Unsafe Route: Auditing Clinical AI Decision Trajectories and Corrective Oversight for Validity and Potential Harm · 2026-11-17
- Get Hint-Augmented GRPO Done Right Through Activation Steering · 2026-11-17
- Right Reason, Wrong Advice: Evaluating Recourse in LLM Explanations of Denied Requests · 2026-11-16
- Asking the right question is key to AI discovery in a chain of hypotheses · 2026-11-15
- Right Goal, Wrong Body: Re-grounding Frozen VLAs under Actuation Shift · 2026-11-15
- With the Right Representation, Classical Machine Learning Rivals Deep Models for Olfactory Mixture Similarity · 2026-11-14
- Right Token, Right Time: From Per-Token Gating to Trajectory-Aware Activation Steering · 2026-11-13
- Right Answers, Inconsistent Evidence: Source-Level Counterfactual Auditing of Large Audio-Language Models · 2026-11-11
- Where Do Vision-Language Models Get Left and Right? Position-Code Counterfactuals in Qwen2.5-VL, Qwen3-VL and InternVL3 · 2026-11-10
- Right for the Wrong Reasons? Evaluating Plausibility and Behavioral Change in Explanation-Guided Learning · 2026-11-10
- Everything in its right place: attention is a radio head · 2026-11-09
- Left-Right-Consistent Iterative Stereo Matching via Cross-Injection · 2026-11-06
- Attend at the Right Resolution: Head-Adaptive Sparse Attention via Query-Key Interaction Structure · 2026-11-06
- PACE: Keeping the Right Tokens in the KV Cache Is Not Enough for Long-Horizon LLM Agents · 2026-11-06
- Do unlearning algorithms learn the right features? · 2026-11-04
- The Right Source Is Not Enough: Understanding History Interference in Speech-LLM Memory · 2026-11-03
- Right Ranking, Wrong Scale: Reproducing the Robotic World Model's Dynamics Model and Testing the Uncertainty of Its Follow-up · 2026-11-02
- World Models Need Not Be Right to Rank Policies Right: Relative Bounds and Audit Limits · 2026-10-31
- When the Same Prompt Gives Different Answers (and the Same Answer Isn't Always Right): A Taxonomy of Failure Mechanisms, Testing, and Mitigation Strategies for LLM-Assisted Evidence Synthesis Read-and-Evaluate Tasks · 2026-10-29
| 36 | – | cs.LG 20 · cs.AI 16 |
conversational ai platforms- Nemotron 3.5 Bolt E4B 4GB: An Open and Efficient Small Language Model for Fast Conversational Agents · 2026-11-16
- Conversing with a Conversational Agent: A Real Conversation, Not a Simulated One · 2026-11-16
- Seeing Isn't Resolving: Visual and Linguistic Disambiguation with Conversational Grounding · 2026-11-16
- Beyond Bilingual: Studying Quadrilingual Code-Switching with Conversational AI · 2026-11-16
- It's My Turn! Interpretable Methods Reveal Developmental Differences from Mother-Child Conversational Dynamics · 2026-11-16
- Can Agents Keep Up with Time? An Empirical Analysis of Temporal Adaptation After a Conversational Hiatus · 2026-11-13
- Scalable Conversational Assessment: Chat-Based Exams with a Two-Agent LLM Pipeline · 2026-11-12
- Human-Likeness and Conversational Preference Diverge for Synthesized Agent Speech in Customer-Service Calls · 2026-11-11
- Hx2Dx: From Anamnesis to Diagnosis - A Multimodal Arena for Conversational Clinical Reasoning in LLMs · 2026-11-10
- Lilo: A Multi-Agent Conversational Sandbox for Children's Digital Communication · 2026-11-10
- When Audio and Video Mislead: Evaluating Multimodal AI for Conversational Emotion Recognition · 2026-11-09
- SCorPion: A Strategic, Controllable and Personified Conversational Companion · 2026-11-07
- Mind the Divergence: Divergence-Guided Reliability-Aware Fusion and Adaptive LLM Prompting for Conversational Emotion Recognition · 2026-11-06
- Ontology-Driven Control of Conversational Agents with a Use-Case for Job Interview Practice · 2026-11-06
- Compaction, decay and reinforcement in a two-tier conversational memory: a paired evaluation against retrieval-augmented generation · 2026-11-06
- Where Did the Evidence Go? Diagnosing Proof-Set Loss in Long-Term Conversational Memory · 2026-11-06
- Persistent Retrieval for Conversational Agents: A Study of Retrieval Efficiency · 2026-11-05
- Memory-Aware Multi-Agent Architecture with LLM-based Orchestration for Conversational Recommendation · 2026-11-05
- Information-Matched Auditing of Conversational Emotion-Shift Forecasting: A Leakage-Safe Evaluation Protocol · 2026-11-04
- Before You Continue: Evaluating Time-Sensitive Safety Awareness in Conversational Assistants · 2026-11-04
- τ-bench-LILT: Evaluating Conversational Agents on Realistic Multilingual Tool-Use Tasks · 2026-11-04
- Do Multi-Turn Conversational Capabilities Carry Over from Text to Speech? A Parallel Multilingual Benchmark · 2026-11-03
- Chain on Demand: Deferred Evidence Organization for Long-Term Conversational Memory · 2026-11-02
- Scalaris: A Scalable Enterprise Memory Architecture for Conversational AI Assistants · 2026-11-02
- Conversational Interaction for LLM-Based Clinical Text-to-SQL: A User Study with Healthcare Professionals · 2026-10-31
| 35 | – | cs.CL 22 · cs.AI 19 |
transformers & attention- Fast and Exact Relative-Position Attention via Structure-Aware Kernels · 2026-10-31 · 24 upvotes
- Zero-Dimensional Attention Topology for Linguistic Acceptability · 2026-11-17
- A Transformer-Derived Iterative Preconditioner · 2026-11-17
- Attention Sinks as Spectral Spikes: A Mechanism Analysis of Gated Attention · 2026-11-16
- Architectures and KV Replay for Depth-Recurrent Language Models · 2026-11-14
- Pattern-Based Matrix Analysis Under Permutations · 2026-11-13
- MaskSCD: Bitemporal Mask Classification for Semantic Change Detection in Remote Sensing Images · 2026-11-13
- ISLA: A Coordinate-Free, Measure-Weighted Transformer for Boundary-Driven PDEs · 2026-11-12
- Objects as Addresses: Instance Binding in Vision Transformer Attention · 2026-11-12
- Pyramidal Columns Acting as Attention Heads · 2026-11-11
- Beyond Head Importance: Collective Computation in Video Transformers · 2026-11-09
- Multimodal Road Closure Mapping via Cross-Modal Graph Attention · 2026-11-09
- A Geometric Theory for Nonequilibrium Transformer Dynamics · 2026-11-07
- A Parametric Linear Conic Projection for Structured Sparse Attention · 2026-11-03
- Exploiting Biases in Attention for Transformers · 2026-11-03
- Inner-Speech Decoding from EEG Across Three Corpora Under a Fixed Architecture and Protocol · 2026-11-01
- SASFormer: Stage-Aware Selective Attention Transformer for All-in-One Blind Image Restoration · 2026-10-31
- Conic Certification of Transformer Attention · 2026-10-31
- Dynamical Memory Transformer: Selective Recurrent Memories with Constant Cost Attention · 2026-10-30
- Learning from Points and Patches: A Pre-trained Hybrid Attention Transformer for Time Series Analysis · 2026-10-27
- LayoutMamba: Efficient Document Layout Analysis with Hybrid Mamba-Transformer Networks · 2026-10-26
- TriTile: Three-Tier Attention for Video Diffusion Transformers · 2026-10-26
- INTRA: Interleaved Non-contiguous Token spaRse Attention · 2026-10-25
- From Document Layout to Causal Topology: An End-to-End Architecture for Temporal Causal Reasoning · 2026-10-25
- Quantifying Meaning with SCAPE-T: Semantic Complexity from Encoder-Only Transformer Attention · 2026-10-24
| 27 | – | cs.LG 15 · cs.AI 9 |
ai red teaming- PIPETTE: Prompt Injection Purple-Teaming for Robust LLM Agents · 2026-11-18 · 6 upvotes
- Learning to Coordinate: LLM-Guided Workflow Evolution for Token-Efficient Red Teaming · 2026-11-18
- AutoPI: Taxonomy-Guided Adaptive Red Teaming for Prompt Injection in LLM Agents · 2026-11-18
- Attacker Diversity Reduction in Adaptive LLM Red Teaming · 2026-11-15
- Singularity-Bench: Can Agents Build Agents? · 2026-11-12
- MobileProbe: Adaptive Security Evaluation of Mobile Agents via Trajectory-Aware Injection · 2026-11-12
- Comparative Analysis of Agent Evaluation Frameworks: Stability, Detection, and Discovery in Enterprise Analytics Agents · 2026-11-10
- Scaling Adaptive Prompt Injection Attacks with Agent Swarms · 2026-11-09
- Generating Diverse and Verified Synthetic Clinical Notes with Labels by Construction · 2026-11-07
- AUTEUR: Acoustic Plan Learning for Red-Teaming Text-to-Audio Models · 2026-11-06
- Stress Testing Chain-of-Thought Monitoring Against Covert Misalignment · 2026-11-05
- Multimodal-SEA: Benchmarking AI Agent Security under Multimodal Social Engineering Attacks · 2026-11-05
- Benchmarks as Software: Terminal-Bench and the Case for Continuous Benchmarks · 2026-11-05
- CloakFEM: Agentic FEM Code Generation for Red-Teaming Computational Resource Exhaustion · 2026-11-03
- HaloGuard 2.0: An Open-Weights Constitutional Output Guard for Multilingual Response Safety · 2026-11-01
- ANGLER: Verifier-Grounded Benchmarking with an Adaptive Attacker for Web Agents · 2026-10-30
- On the Framing Effect of AI Red-Teaming Instructions: Evidence from Prior Exercises and Controlled Simulations · 2026-10-30
- Not All Steps Matter: Temporally Adaptive Spectral Control for Concept Removal in Diffusion Models · 2026-10-30
- Red-Teaming Large Language Models in Low-Resource African Languages: A Case Study of Yoruba and Nigerian Pidgin · 2026-10-29
- CoFiBreak: A Coarse-to-Fine Diversity Reward for Effective Multi-Turn Jailbreak · 2026-10-29
- Value Probes: Learned Value Functions for Beam-Search Red Teaming · 2026-10-28
- FlipJev: Fast Black-Box Red Teaming Finds Universal Adversarial Suffixes for Typed Decision Models · 2026-10-28
- Safe by Benchmark, Unsafe in Practice: Lessons from 1331 Child-Related AI Incidents · 2026-10-26
- The Target Agent Is Its Own Best Critic but a Poor Proposer: Self-Improved Red Teaming · 2026-10-26
- The Watchtower Imperative: Lifespan-Calibrated Evaluation for Frontier AI · 2026-10-26
| 26 | – | cs.AI 20 · cs.LG 9 |
computer use models- CUA-Master: Scaling Computer-use Agents through Open-World Recursive Improvements · 2026-11-02 · 49 upvotes · code
- NorthCUA Technical Report: Turbocharging Computer-Use Agents through Experience at Scale · 2026-11-01 · 29 upvotes · code
- Mage-VL-Cowork: A Full Training Recipe to Learn Hybrid Computer Use From Evolved Harnesses · 2026-10-29 · 23 upvotes
- Hybrid Computer Use: A Unified Programmatic, Semantic, and Visual Interface for General Agents · 2026-10-30 · 19 upvotes · code
- Multimodal Embodied Agents: A Unified Capability-centric Perspective from Computer-Use to Robot-Use · 2026-10-21 · 17 upvotes · code
- iPrefBench: A User-Centric Benchmark for Personalized Mobile Use Agents · 2026-10-26 · 12 upvotes
- SEAM: Computer-Use Agents Know the Harm Between Screens, and Commit It Anyway · 2026-11-17
- CANDID: Candidate-Driven Intervention for Disciplined Execution in Local Computer-Use Agents · 2026-11-17
- Design of the Secure Smart Scooter with Automatic Lane Detection · 2026-11-16
- StreamEmbed: Real-Time Indexing from Pixels for Screenshot Retrieval · 2026-11-13
- Training Reasoning Models in Simulation to Natively Use Real Robots · 2026-11-13
- Trained on What Screen Readers Cannot Read: Accessibility Debt in the GUI Corpora Behind Computer-Use Agents · 2026-11-11
- Video-as-Experience: Learning Computer Use via Audio-Visual Understanding · 2026-11-11
- Deep Personalization: Continuous Context Observation for Local Proactive Agents · 2026-11-10
- Rational Use of Time for Social Coordination in Humans and AI · 2026-11-10
- Computer-Use Agents Are Embodied Generalists · 2026-11-06
- Visual Token Routing: Learning to keep tokens that matter · 2026-11-04
- ScienceCUA: Resource-to-Skill Construction and Execution-Guided Skill Evolution for Scientific Computer Use Agents · 2026-11-02
- Computer-Use Agents Gain Little Benefit from a World Model When Conditioned on Tutorials · 2026-11-02
- Cross-Interface Authorization for AI Computer-Use Agents · 2026-10-30
- What Does "Now" Mean to Your Computer-Use Agent? Stale Screenshots, Page Loads, and Which Check to Run Before a Click · 2026-10-29
- EnvOS: Auditing Computer-Use Agents When the World Moves On : Phenomenon-Based Task Construction, Certification, and Evidence-Based Evaluation · 2026-10-29
- When to Intervene? An Empirical Study of Errors and Self-Recovery in LLM Agents · 2026-10-27
- HobbyLM: A Sparse Mixture-of-Experts Model Family on a Hobby Budget · 2026-10-25
- PointerBench: A Diagnostic Benchmark for Fine-Grained GUI Grounding · 2026-10-22
| 26 | – | cs.AI 15 · cs.LG 8 |
ai interpretability- Glyph: An Interpretability Engine for AI-Driven Scientific Discovery from Clinical Data · 2026-11-06 · 7 upvotes · code
- Abstention Direction in Large Language Models: Mechanistic Interpretability of Abstention Across Query Ambiguity, Knowledge Limits, and Safety Alignment · 2026-11-16 · 5 upvotes
- Separating Interpretability and Reconstruction in Sparse Autoencoders · 2026-11-18
- ONAM: Fitting Orthogonal Neural Additive Models for Post-Hoc Interpretability of Black-Box Predictions · 2026-11-16
- DECODE: Diagnosing Interpretability Failures in Automated Interpretation Process · 2026-11-13
- Can Mechanistic Interpretability Help Explain LLM Agent Failures? A Case Study on Web Element Hallucination · 2026-11-13
- When can an interpretability claim be trusted? Stability and certification of feature dimensionality, ridge leverage and the feature recovery rate · 2026-11-12
- A Mechanistic Interpretability Study of an Astronomy Foundation Model · 2026-11-11
- Mechanistic Interpretability of Deep Neural Networks: Methods, Frameworks, and Perspectives · 2026-11-10
- Mechanistic Interpretability Needs a Logic of Inference · 2026-11-10
- Interpretability Is Not Model-Specific · 2026-11-09
- ConwayNet: Interpretability, Activation Coherence, and Noise Resilience via a Game-of-Life-Inspired Lateral Inhibition in Artificial Neural Networks · 2026-11-07
- Controllable Molecule Generation via Sparse Representation Editing: An Interpretability-Driven Perspective · 2026-11-06
- Understanding AI from the Inside: The State of Mechanistic Interpretability for AI Safety · 2026-11-05
- Bridging Singular Learning Theory and Mechanistic Interpretability at the Billion-Parameter Scale · 2026-10-31
- Benchmarking Machine-Learning Classifiers for Neoantigen Immunogenicity Prediction and the Limits of SHAP Interpretability · 2026-10-31
- Mechanistic Interpretability for End-to-End Self-Driving · 2026-10-30
- Improving the Intrinsic Interpretability of Differentiable Decision Trees through Euclidean Feature-Concentration Regularisation · 2026-10-29
- Can LLMs Faithfully Solve Ontology Engineering Tasks? A Mechanistic Interpretability Study · 2026-10-28
- What Survives Distillation? A Mechanistic Interpretability Study of GPT-2 and DistilGPT-2 · 2026-10-27
- INTR++: INterpretable TRansformer with better Accuracy, Interpretability, and Adaptability · 2026-10-27
- A Lightweight Attention-Based CNN with Saliency-Map Interpretability for Skin Cancer Detection · 2026-10-27
- ReForest: Interpretability Meets Reasoning in Isolation Forest · 2026-10-27
- Post-Hoc Feature Selection Layer for Neural Networks Interpretability · 2026-10-22
| 24 | – | cs.LG 13 · cs.AI 12 |
music- A Tutorial on Generative Models for Music Audio · 2026-10-28 · 5 upvotes
- Sample-efficient end-to-end Optical Music Recognition through Active Learning · 2026-11-19
- Harmonic Circuit: Chord Progression Lies in a Sparse Principal Information Flow in Symbolic Music Models · 2026-11-18
- Evaluating the Evaluation of Music Generation Models with Generative Psychometrics · 2026-11-16
- MusicRWKV: A Multimodal RWKV Framework for Music Representation Learning · 2026-11-12
- Reliable Near-Field Source Enumeration and Positioning Informed by Two-Stage MUSIC · 2026-11-11
- The BEATS Dataset: Towards Understanding Music-Physiology Dynamics in Real-World Scenarios · 2026-11-11
- MusicFlux: Flexible Conditioning for Text-Guided Music Generation and Editing · 2026-11-10
- Exploring Post-Hoc Disentanglement of Audio Foundation Models for Music Similarity · 2026-11-10
- Music Inpainting With Similarity-Guided Latent Diffusion · 2026-11-08
- Functional Dependency beyond Similarity: Hierarchical Decomposition of Training Data Attribution in Music Generative Models · 2026-11-06
- Concordance-Optimal Continuous Music Emotion Estimation: Variance Decomposition, Dual-Branch Temporal Fusion, and Conformal Prediction Intervals · 2026-11-06
- SPDMX: Large-Scale Open Stem Audio From Symbolic Music · 2026-11-06
- FFMT: Frequency-Factorized Multi-Rate Tokenization for Music-to-Dance Generation · 2026-11-05
- When Music Needs Meaning: Semantic Communication as a Transformative Enabler for the Musical Metaverse · 2026-11-02
- ResMamba: A Dual-Path Convolution-Mamba Model for Music Genre Classification · 2026-10-31
- How Close to the Theme? Similarity-Label Conditioning for Game Music Generation · 2026-10-31
- Parameter-Efficient Fine-Tuning of Transformer Encoders for Audio-Image-Symbolic Music Retrieval · 2026-10-30
- SMEBENCH: Benchmarking Neural Music Editing with Synthetized MIDI Edits · 2026-10-27
- Does Notation Matter? MusicXML Tokenisation for Symbolic Music Generation and Understanding · 2026-10-25
- ChoreoStudio: Planning What, When, and Who in Music-Driven Group Choreography · 2026-10-23
- MQAScore: Fine-Grained Text-Music Alignment Evaluation via Large Audio Language Model · 2026-10-22
- Predicting Music Valence and Arousal via Textual and Multimodal In-Context Learning in Large Language Models · 2026-10-22
- Agentic Music Post-Production · 2026-10-21
| 24 | – | cs.AI 13 · cs.LG 11 |
ai drug discovery platforms- TabBioMed: A Large-Scale Benchmark for Biomedical Tabular Learning · 2026-11-18 · 9 upvotes · code
- GPU-Accelerated Secure Inference for Drug--Target Interaction Prediction · 2026-11-19
- From Benchmarks to the Bench: Preference, Correspondence and Selectivity in Bidirectional Drug-Target Screening · 2026-11-19
- STORM: A Lightweight Structure-Free Model for Binding Affinity Prediction · 2026-11-18
- MT-RGCN-DTI: A Multi-Task Relational Graph Convolutional Network for Drug-Target Interaction Prediction · 2026-11-15
- Multi-Assay Antibody Developability Prediction with Shared Structure-Language Representations · 2026-11-13
- Binding Mode Matters: Hotspot-Aware Drug Discovery via Explorative Preferences · 2026-11-11
- The Dose Makes the Poison: Exposure-Aware Evaluation of Generative Drug Design · 2026-11-10
- DrugCoding: A Scientific Programming Agent for Drug Discovery · 2026-11-10
- Pyrite: Building and Benchmarking Protein-Ligand Pose Ranking Agents · 2026-11-10
- MICE: Multi-animal Interaction Context Encoder - A Hierarchical Foundation Model for Mouse Behavior · 2026-11-08
- Controllable Molecule Generation via Sparse Representation Editing: An Interpretability-Driven Perspective · 2026-11-06
- PharmAgents2: Towards Autonomous End-to-End Drug Discovery · 2026-11-05
- Molecular Prior Networks · 2026-11-03
- The DynaCell Evaluation Suite for Dynamic 3D Virtual Staining of Live Cells · 2026-11-02
- El Agente Fármaco: A Scalable AI Scientist for Drug Discovery · 2026-11-02
- Transferring Peptide-Target Interaction Patterns to Small Molecules by Joint Guidance for Diffusion and Flow Matching · 2026-10-30
- TACFormer: Transformer-Based Generative Model for Target-Conditioned De Novo PROTAC Design · 2026-10-29
- EVA-Flow: Learning Shared Chemistry for Unified Environment-Aware Molecular Conformation Generation · 2026-10-26
- Interpretable and Steerable Molecular Graph Generation using Concept Bottlenecks · 2026-10-25
- xVGAE: A Hierarchical Variational Graph Autoencoder for Exchangeable Graphs · 2026-10-22
| 21 | – | cs.LG 17 · cs.AI 8 |
ai narrative intelligence- The Narrative Gap: Can LLMs Help Us Navigate Diverse Narratives Across Languages? · 2026-11-09 · 3 upvotes · code
- Adaptive LLM-Driven Honeypots vs. LLM-Driven Attackers: Does Narrative Coherence Improve Deception? · 2026-11-17
- FACET - Facet Aware Contrastive Embeddings for Traits- Big Five Estimation from Life Narratives · 2026-11-17
- FinVision: Multimodal AI for Visualizing Financial Narratives · 2026-11-15
- MeReader: An Offline, Privacy-Preserving, Progress-Aware AI Assistant for Narrative eBook Reading · 2026-11-13
- CineMME: From Dialogue Grounding to Narrative Reasoning in Multimodal Video Understanding · 2026-11-11
- From Counterfactual Edits to Human Narratives: LLM-Driven Interpretations for Recommender System Explanations · 2026-11-10
- SadaqahStories: A Verified English-Arabic Corpus of Charity Stories for Children, with an Audit of Errors in AI-Drafted Religious Narratives · 2026-11-09
- Fairness in Explainable AI Narratives: Decomposing Social Disparities in LLM-Generated Explanations · 2026-11-09
- Deterministic Narrative Gravity: Bridging Theory of Mind and Historical Simulation through ABM-LLM Architectures · 2026-11-08
- Analysing the Narrative Paradox through Formal Models and Properties in Interactive Narrative · 2026-11-02
- Creating Hybrid Interactive Narrative Systems with LLM: From Formal Description to Evaluation · 2026-11-02
- Towards Self-Evolving Narrative Systems: Real-Time Adaptation and Long-Term Optimization with LLMs · 2026-11-01
- Statutory Article Retrieval from Arabic Judicial Narratives: Family Law and Law of Evidence in Saudi Arabia · 2026-10-28
- Modeling Preference Dependencies with Directed Acyclic Graphs for Narrative-Driven Recommendation · 2026-10-27
- AskGLP1: A Knowledge Graph LLM Agent for Exploring GLP-1 Experience from Online Patient Narratives · 2026-10-26
- Beyond Physical Illness: Can Clinical Narratives Reveal Emerging Mental Health Risks in Chronically Ill Patients? · 2026-10-26
- From Structured Records to Patient Narratives: Preserving Clinical Alignment in LLM-Generated Health Summaries · 2026-10-22
- IRON-Meme: A Benchmark for Structured Understanding of Identities and Roles in Online Meme Narratives · 2026-10-22
| 19 | – | cs.AI 12 · cs.CL 11 |
theoretical foundations- Route Anything: A Study of Model and Policy Routing for General-Purpose AI Systems · 2026-11-03 · 44 upvotes · code
- AG-BFGS: Foundations for Accelerated Geometry Learning · 2026-11-18
- Diffusion Models are Provably Efficient Priors for Sparse Recovery · 2026-11-18
- Margin Dynamics for Large Language Model Alignment · 2026-11-16
- f-Divergence Self-Play for Tabular Anomaly Detection via Large Language Models · 2026-11-13
- Earth Embeddings in Environmental Remote Sensing · 2026-11-10
- A Theory of Cross-Validation Variance · 2026-11-10
- A Theory of Policy Optimization in Post-Training: Coverage Collapse and Reference Resets · 2026-11-10
- Continuous Horizon Forecasting · 2026-11-09
- Disentangled Stylized Image Generation via IP-Cross-Attention Rearrangement · 2026-11-07
- Projected Neural Additive Models as Universal Approximators · 2026-11-06
- RGDM: Robust Graph Diffusion Model · 2026-11-03
- A Parametric Linear Conic Projection for Structured Sparse Attention · 2026-11-03
- Unifying and Beyond the Theory of Pervasive Capability Degradation in LLM Post-training SFT from Feature Interference · 2026-11-03
- Going deep, reaching further: What can Boltzmann machines efficiently represent? · 2026-10-29
- From Deliberately Constructed Systemic Representations of the World of Activity to Dialogue: A Five-Level Communication Architecture for Strong Language-Based ASI · 2026-10-23
- Bridging Number-Theoretic Primality Testing And Algorithmic Optimization: An Adaptive Cryptographic Framework · 2026-10-22
- When and How Does Muon Precondition? The Role of Structured Gradient Noise · 2026-10-22
- A Decade of Learning-Based Control: From Theoretic Foundations to Practical Deployment · 2026-10-21
| 19 | – | cs.LG 14 · cs.AI 4 |
large-scale pretraining- TeleChat to Xing4: Advancing Frontier Agentic Models on Domestic Chips and Frameworks · 2026-11-17 · 162 upvotes
- DepthGraft: Structural Regularization through Hierarchical Cross-Layer KV Reconstruction · 2026-11-02 · 14 upvotes · code
- WorldFlow: Joint Video and 3D Motion Prediction via Large-Scale Pretraining · 2026-10-29 · 5 upvotes · code
- Scribble Once, Segment the Sequence: Bidirectional Temporal Consistency for Weakly Supervised Segmentation in Echocardiography Sequences · 2026-11-16
- LangDepth: Vision-Language Scene Priors for Semantic Binning and Cross-Domain Monocular Depth Estimation · 2026-11-09
- ForeAct: Geometry-Guided Action Learning from World Representations · 2026-11-08
- Daily Emergency Call Volume Forecasting using Univariate and Multivariate TimeGPT · 2026-11-08
- FlowEval: How Much Adaptation Does an Embodied Foundation Model Need at Deployment? · 2026-11-08
- PoseBench: Probing Pose Awareness in Visual Foundation Models · 2026-11-07
- BrainCoT: A Multi-Task Zero-Shot Brain Signal Foundation Model with Neurometric-Anchored Chain-of-Thought Reasoning · 2026-11-06
- MonoLaDN: Language-Guided DeNoising for Monocular 3D Object Detection · 2026-11-04
- Do Pretrained Backbones Transfer to Physical Sensors? A Systematic Study of Multimodal Initialization Across the Sensor Stack · 2026-11-02
- Chronos-2: A foundation model for multivariate time series forecasting · 2026-10-30
- There Is No Free Loop: When Does Looping a Trained Model Pay for Its Inference Compute? · 2026-10-30
- TUON: A Tensor-Aware Optimizer Utilizing Tensor-SVD and Polarization for Large Language Model Pretraining · 2026-10-26
- Scaling Dexterous Manipulation via Action Representation Pretraining · 2026-10-25
- Random Initialization as a Baseline for Time Series Foundation Models · 2026-10-22
- How Far Can Foundation Models Be Distilled for Efficient Jet Tagging? · 2026-10-21
| 18 | – | cs.CV 7 · cs.LG 7 |
art- Novel or Not? PatEx-Gym: Agentic Prior-Art Search for Novelty Assessment in Patent Examination · 2026-10-24 · 10 upvotes · code
- Learning Martial Arts Motion Skills for Animating Opponents in VR Sparring Games · 2026-11-18
- ART: Bridging the Embodiment Gap in 3D Human-to-Robot Affordance Transfer · 2026-11-18
- Fiberpose: state-of-the-art fiber morphometry and instance segmentation with a distance-transform neural network · 2026-11-17
- RageVLA: Augmentation-Trained Perception and Action for State-of-the-Art Robustness on LIBERO · 2026-11-17
- PixelBench: Evaluating Language Models for Pixel-Art Creation · 2026-11-16
- From State of THE ART to Human Prediction Algorithms · 2026-11-12
- ARTS: An Open-Source, Reproducible Three-Arm Platform for Autonomy Research in Minimally Invasive Surgery · 2026-11-11
- Same Physics, Different Gradients: A State-of-the-Art Report on Differentiable Physics Simulation · 2026-11-09
- The RenAIssance: Caption-Guided Diffusion Models for Historical-Art Visual Media · 2026-11-07
- What Is the Value of AI-Involved Art? Evidence From a Juried In-Person Exhibition · 2026-11-06
- Computer Vision Applications for Art History: Reflections and paradigms for future research · 2026-11-02
- MedPsy: State-of-the-Art Small Medical Language Models for Efficient Edge Deployment · 2026-11-01
- ART of PIV: Agentic Real-Time Particle Image Velocimetry for Active Flow Control · 2026-10-30
- Beauty Is Human: When People Love AI-Generated Art, They Think a Human Made It · 2026-10-28
- Forging Emotions: a deep learning experiment on emotions and art · 2026-10-23
- ART-MPG: Autoregressive R/T Manifold Path Guiding · 2026-10-21
| 17 | – | cs.CV 10 · cs.AI 6 |
sound- When Sounds Turn Heads: Recovering Event Timing That Audio LLMs Fail to Say · 2026-11-19
- Strong Fused Performance Can Mask Branch Collapse in a Dual-View Heart-Sound Classifier: A Three-Part Diagnostic Protocol · 2026-11-17
- Language Models Make New Research Sound Old · 2026-11-17
- UbiHearo: Bringing Scenario-Aware Sound Guidance to DHH Users with Mobile Agents · 2026-11-16
- Direct Conditioning of Audio Diffusion Transformers on fMRI Reveals Cortical Contributions to Sound Reconstruction · 2026-11-09
- From Sound to Occupancy: Privacy-Aware Audio Sensing for Buildings · 2026-11-08
- FoleyForge: Free-form, Controllable, Rectified-flow Editing of Sound Effects · 2026-11-05
- A Human-Verified AI Workflow for Annotating Environmental Sound Data · 2026-11-02
- Metadata-Conditioned Audio Transformers for Adaptive Respiratory Sound Classification · 2026-11-02
- CAST-Bench: Tracing Every Sound to Its Source in Multi-Shot Audio-Video Generation · 2026-11-02
- AVPS-360: A Spatial Audio-Visual Benchmark for Instance Segmentation and Tracking of Sound-Producing Persons · 2026-10-29
- MCCL: Training Pytorch models across a fleet of Macs at Skywalker Sound · 2026-10-28
- A Hierarchical Method for Environmental Sounds Recognition in Complex Acoustic Scenes · 2026-10-26
- EARS: Evidence-Aware Retrieval via Sound and Motion for Budgeted Video Reasoning · 2026-10-26
- Towards User Simulators That Stay On Task And Still Sound Natural · 2026-10-22
- Clinical radar heart sounds with echocardiographic phenotypes of ventricular dysfunction and valvular disease · 2026-10-21
- Solving Go under Positional Superko: Sound Proof Transfer and New Board Values · 2026-10-21
| 17 | – | cs.AI 6 · cs.CV 5 |
robot foundation models- ScaleVLA: Scaling Vision-Language-Action Models to 552 Billion Parameters · 2026-11-16 · 39 upvotes
- Synthesizing Dexterous Robot Demonstrations from Human Videos via Virtual Try-On · 2026-11-03 · 14 upvotes · code
- Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success · 2026-10-22 · 7 upvotes · code
- Trajectory-Calibrated Merging of Embodied Policies · 2026-11-19
- $Z$-sight: Unifying Vision-Language-Action and Latent World Modeling · 2026-11-18
- Can LLMs Debug Robots by Editing Their Weights? · 2026-11-06
- La-JEPA: Compact Robot Policies with Latent World Modeling · 2026-11-05
- VICTR: Value-Informed In-Context Learning for Vision-Language-Action Models · 2026-11-05
- Reinforcement Learning Enables Scaling Generalist Robot Policy Improvement · 2026-11-04
- When Delay Meets Drift: Physical Safety of Robot Foundation Models Is a Cross-Layer Problem · 2026-11-01
- Editing the Goal: Per-Token SAE Steering and Its Depth Limits in $π_{0.5}$ · 2026-10-31
- From Concepts to Actual Causes: Toward Closing the Concept-Malfunction Gap in Robot Foundation Models · 2026-10-30
- Learning Safe Flow Matching Robot Policies from Binary Feasibility Oracles · 2026-10-29
- Confidence-Modulated Safety Filtering for End-to-End Policies · 2026-10-29
- When Black-Box Robot Policies Fail: Online Sensor Diagnosis and Repair with a Transparent Surrogate · 2026-10-27
- Training in Deployment: Human-in-the-loop Online Post-Training for Robot Manipulation · 2026-10-21
| 16 | – | cs.RO 15 · cs.AI 5 |
ai pricing intelligence- StaleBench: Isolating Stale Retrieval in Agent Memory, and Pricing the Fix · 2026-11-15
- Conditional Asset Pricing Transformer · 2026-11-15
- PIRanNN: Random-Feature Pricing and Calibration under Jump-Diffusion and Stochastic-Volatility Models · 2026-11-15
- Locational Marginal Pricing of Compute: Co-optimizing Compute and Energy for Transparent Data Center Flexibility · 2026-11-15
- PMR: MoE Routing with Shared Prototypes and Congestion Pricing · 2026-11-14
- Robustness Evaluation of GPU Cloud Pricing Benchmarks under Incomplete Observations: A Controlled Missingness Study · 2026-11-13
- Quantifying structural stability of transparent models for general insurance pricing · 2026-11-12
- Pricing Symbolic Rules by What GNNs Leave Unlearned · 2026-11-09
- Recursive Pricing and Incumbent Subtree Column Generation for Solving Optimal Classification Trees · 2026-11-08
- The Power of Two Choices in Dynamic Pricing: As Good As Full Feedback, Instance-Wise · 2026-11-07
- Pricing Today, Shaping Tomorrow: Contextual Dynamic Pricing in Purchase-Driven Evolving Systems · 2026-10-31
- Optimal Contextual Pricing in Non-Stationary Environments · 2026-10-29
- Pricing Cross-Bank Context in Federated Anti-Money Laundering · 2026-10-26
- From Explaining to Enabling: Actionable Transparency in Algorithmic Insurance Pricing · 2026-10-25
- Doubly Robust Distributionally Robust Offline Contextual Pricing · 2026-10-22
| 15 | – | cs.LG 11 · cs.AI 6 |
image-to-video- Behind Video Generation: Observations and Insights on Multimodal Understanding from Kling · 2026-11-03 · 85 upvotes
- Route Anything: A Study of Model and Policy Routing for General-Purpose AI Systems · 2026-11-03 · 44 upvotes · code
- WeMM-Video: Pushing the Frontiers of Open-Source Omni-Modal Video Understanding · 2026-11-19
- Pixel is All You Need · 2026-11-17
- Lasso: Towards Sustainable AI-Generated Media Detection with Intel QAT On-Chip Compression · 2026-11-13
- Deterministic, Reproducible Inference in Exact Integer Arithmetic, and Verifiable Distributed Inference as Its Consequence · 2026-11-10
- Isekai3D SDG: A Platform for Diverse Synthetic Gameplay Visual Data · 2026-11-02
- Synthetic Realities: Evaluating Human Ability to Distinguish AIGenerated Videos from Real Footage · 2026-11-01
- Reflex: Fast Robot Policy Serving by Reusing and Correcting Past Actions · 2026-10-31
- Real-VAS: a Real-World Video Amodal Segmentation Dataset · 2026-10-30
- Nemotron 3.5 Super and Lightning: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Models for Agentic AI · 2026-10-28
- Hierarchical Multimodal Interaction Reasoning for Dyadic Relationship Recognition · 2026-10-26
- HobbyLM: A Sparse Mixture-of-Experts Model Family on a Hobby Budget · 2026-10-25
- MOSAIC: An Omni-Modal Benchmark for Long-Term Memory and Cross-Modal Reasoning in Conversational Agents · 2026-10-21
| 14 | – | cs.CV 9 · cs.AI 5 |
ai materials discovery- Reward misalignment as an opportunity for materials discovery · 2026-11-19
- SPARC: Evidence-guided adaptive model composition for materials discovery · 2026-11-14
- Benchmarking language models and agents for scientific reasoning in evolving materials laboratories · 2026-11-09
- Out-of-the-Box Tabular Foundation Models for Bayesian Optimization in Materials Discovery · 2026-11-09
- ZeoBench: A Benchmark for Self-Supervised Learning on 3D Zeolite Representations · 2026-11-06
- Organizational Learning in Materials Discovery Campaigns: Which Databases, Calculations, and Agent Teams Pay Off · 2026-11-02
- ElectroChemLLM: A Multimodal LLM Pipeline for High-Fidelity Electrochemical Informatics · 2026-10-31
- FrontierMat: Benchmarking Language Models at the Frontier of Materials R&D · 2026-10-30
- Framework-Conditional Open Materials Generation · 2026-10-29
- Deep Scientific Reasoning under Physical Constraints: Structure-Aware Spectrum Prediction · 2026-10-25
- Probing the limits of materials design via a comprehensive crystal database of 14.6 million structures with 140 properties · 2026-10-23
- Exploring Joint-Embedding Predictive Architectures for Self-Supervised Representation Learning of Powder X-ray Diffraction Patterns · 2026-10-23
- Automated Materials Data and Knowledge Extraction using Machine Learning and Large Language Models · 2026-10-21
| 13 | – | cs.LG 10 · cs.AI 6 |
ai search engines- From Fragmentation to Fusion: A Survey and Roadmap for Omnimodal Embeddings · 2026-10-30 · 24 upvotes · code
- Web search in Latin America: language models use less local and diverse news than search engines · 2026-11-19
- CRAFT: Constrained Route planning with Adaptive Framework and Template-based code generation · 2026-11-18
- SpecSearch: Towards Hardware-Aware Efficient Speculative Decoding · 2026-11-17
- TabDAG: Structured Evolutionary Search for Tabular Feature Engineering · 2026-11-17
- How Developer Personality Shapes the Use of AI Coding Assistants · 2026-11-16
- Hybrid Product Search Without the Copy: Lexical, Semantic and Filtered Retrieval Served Directly from a Data Lake · 2026-11-08
- LEGIT: Live Eligibility Gating over Identifier Tries for Constrained Decoding of Heterogeneous Pages · 2026-11-07
- The Popular Get More Popular: Auditing Brand Bias in Generative Search · 2026-11-05
- Characterizing Adversarial GEO via Implicit Brand Injection · 2026-11-02
- Discussing politics with a chatbot: How political beliefs shape prompt formulation for generative AI · 2026-10-31
- Automated Keyword Generation Using LLMs in a High-Volume Data Virtualization Service · 2026-10-30
- Lean Finder V2: Semantic Search for Mathlib That Disambiguates User Queries · 2026-10-22
| 13 | – | cs.AI 9 · cs.LG 4 |
backpropagation- Supervised Hebbian Class Networks: Learning Without Backpropagation · 2026-11-18
- Truncated backpropagation through time induces a two-sided gradient turnpike property · 2026-11-05
- CAPSkip: Cancellation-Aware Prefix Skipping for Selective Backpropagation · 2026-11-03
- Nearest Is Not Safest: Fluid-Antenna Port Selection for Over-the-Air Backpropagation in Urban Multipath · 2026-11-02
- Which Chains to Calibrate for Physical Backpropagation: Per-User Factors Versus Base-Station Chains · 2026-11-02
- 3D-BBDA: Backpropagation-Free Black-Box Domain Adaptation for Robust 3D Point Cloud Recognition · 2026-11-02
- ReWY: Faster Backpropagation for Delta-Rule Attention - From 7 to 3 Matrix Multiplications · 2026-11-01
- Detailed Derivation of The Backpropagation Algorithm · 2026-11-01
- Backpropagation-free Deep Learning for Time-Series Classification · 2026-10-30
- Deeper Backpropagation or More Updates? Training Looped Language Models Across Budgets · 2026-10-28
- Nonlinear Direct Feedback Alignment for Scalable Backpropagation-Free Training · 2026-10-27
- Interactive image diagnosis using test-time backpropagation from the auxiliary task · 2026-10-23
- Forward-Only Learning for Shared-Kernel Wavelet Neural Networks without Backpropagation · 2026-10-21
| 13 | – | cs.LG 8 · cs.CV 3 |
synthetic data generation- Reducing Batch Makespan for LLM Agent Workloads through Inference-Environment Coordination · 2026-11-12 · 3 upvotes
- Synthetic Crystal Data Generation for Diffusion Pretraining in Material Property Prediction · 2026-11-17
- Arboreus: A Realistic Boreal Forest Simulator with Topographic Terrain and Satellite-Informed Parametric Tree Distributions · 2026-11-17
- Automated Annotation-Free Synthetic Data Generation for Underwater Litter Detection: A Comparison of Generative Approaches · 2026-11-17
- AI-Based Multi-View Echocardiographic Image Synthesis using Dynamic Shape Control · 2026-11-13
- Model Maps: A Documentation Framework for Tracing Foundation Model Ancestry and Understanding AI Entanglement · 2026-11-13
- Beyond Similarity Entropy: A Rank-Guided Data-Free Quantization Framework for Vision Transformers · 2026-11-08
- RAD-TFM: Robust and Domain-Adapted Tabular Foundation Models · 2026-11-06
- 4D Point Splatting for mmWave Radar Micro-Doppler Differentiable Rendering · 2026-11-05
- ReXMo: End-to-End Video Character Replacement with Expression and Motion Preservation · 2026-11-03
- Isekai3D SDG: A Platform for Diverse Synthetic Gameplay Visual Data · 2026-11-02
- Faithful Federated Tabular Data Synthesis · 2026-10-24
- Inference-Time Prior Adaptation for Imbalanced Data Streams under Concept Drift · 2026-10-23
| 13 | – | cs.CV 6 · cs.LG 5 |
ai test generation- UniVEP: Unifying Velocity and Endpoint Prediction for Robot Manipulation · 2026-11-19
- Systematic Mapping Protocol. Generative AI-Augmented Requirements Engineering: A Systematic Mapping Study of Practices, Specifications, and Reuse in Software Development · 2026-11-17
- Scientific Coding with Large Language Models: Evidence from Finite Element Analysis · 2026-11-16
- ADAPT: Agentic Diff-Aware Patch Testing for Pull Requests · 2026-11-11
- AUTEUR: Acoustic Plan Learning for Red-Teaming Text-to-Audio Models · 2026-11-06
- How Should Agents See Code? Rethinking Code Representations for Agentic Software Engineering · 2026-11-05
- Symmetry-Aware Surrogate-Assisted Testing of UAVs · 2026-11-05
- Analysis of Local Open-Weight LLM Agents on Vulnerability-Reproduction Tasks · 2026-11-04
- Benchmarking LLM Agents for Behaviorally Adequate Test Generation from Software Requirements · 2026-10-27
- Beyond QASecClaw: Agent Scaling, Verifier Feedback, and Evidence Reliability in Software Assurance · 2026-10-27
- Can AI Guide Testing Without Generating Tests? A Comparative Study of AI-Assisted Unit Testing · 2026-10-26
- FaultGene: LLM-Assisted Fault-Augmented Test Generation for Hardware-in-the-Loop Validation of Autonomous Driving Systems · 2026-10-21
| 12 | – | cs.AI 9 · cs.RO 2 |
ai theorem proving models- h1: A Taste of the Bitter Lesson in Automated Theorem Proving · 2026-10-25 · 20 upvotes
- Scaling Lean Theorem Proving for Real-World Code Verification · 2026-10-28 · 8 upvotes
- From Pen-and-Paper to Machine-Checked Proofs: Lean for System Identification · 2026-11-13
- daVinci-Prover: Agent-Native Mid-Training for Formal Theorem Proving · 2026-11-12
- ProofCoder: Continuous Reasoning for Automated Software Verification · 2026-11-10
- LeanDojo-v2: A Comprehensive Library for AI-Assisted Theorem Proving in Lean · 2026-11-06
- TCSExam: Evaluating Frontier LLMs on the Full Range of TCS Research · 2026-11-05
- LeanContext: Disentangling Mathematical Resources from Local Formal Context in Lean Whole-Proof Generation · 2026-11-05
- DAPS: Dependency-Aware Premise Selection for LLM Theorem Proving · 2026-10-30
- GTFormer: A Syntax-Free Graph Network Alternative to Transformers for 8192$\times$ Length Extrapolation in Linear Time · 2026-10-27
- The Paired Thermal Channel Is Two Orthogonal Axes: A Controlled Attribution Study of Calibration Cost and Detection Gain in Infrared Person Detection · 2026-10-23
- Lean Finder V2: Semantic Search for Mathlib That Disambiguates User Queries · 2026-10-22
| 12 | – | cs.AI 5 · cs.LG 5 |
ai content moderation- Building Auditable AI Text Detectors with Sparse Autoencoders · 2026-10-21 · 13 upvotes · code
- SCOPE: Compiling Natural-Language Policies into Neurosymbolic Predicate Programs · 2026-10-22 · 12 upvotes
- What Majority Labels Hide: Annotator Disagreement and Model Errors in Multi-Dialect Arabic Sexism Detection · 2026-11-18
- CaseLaw: A Policy-Decoupled Framework for Training-Free Content Moderation · 2026-11-09
- TrustMod-SM: A Multi-Axis Benchmark for Evaluating Trustworthiness of LLMs in Social Media Content Moderation · 2026-11-07
- Policy Over Purpose: Auditing LLM Content Moderation of Reclaimed Slur Usage · 2026-11-06
- Beyond Hash Matching: AI-Based Detection of Previously Unidentified CSAM and its Legal Implications in the EU · 2026-11-05
- When the Text Is Silent: Memory Shortcuts and the Validity of LLM Annotation under Evidence Insufficiency · 2026-11-01
- Two Uncertainties Are Not One: Disagreement versus Decision-Risk in Cheap Structured Content Moderation · 2026-10-23
- Interpretive Variation and Discourse Structure in Detecting Enthymemes in Controversial Political Discourse · 2026-10-22
- Omni-UBench: Benchmarking Omni-Modal LLM-based Guardrails Across Safety, Utility, and Reliability · 2026-10-22
| 11 | – | cs.CL 9 · cs.AI 4 |
ai voice agents- Confucius4-R2T2: A Stable-Prefix Streaming ASR Model for Real Real-Time Transcription · 2026-11-04 · 70 upvotes · code
- When Should a Voice Agent Speak? End-of-Turn Detection in Turkish · 2026-11-19
- RehearsalBench: Can AI Predict What Happens When You Change a Company? · 2026-11-17
- Does the Voice Matter? Evaluating Frustration Detection on Deployed Clinical Voice-Agent Calls · 2026-11-16
- Decode Early, Verify Late: Streaming Offline Speech Recognizers Without Accuracy Loss · 2026-11-15
- Latency, Speech Recognition and Turn-Taking in Voice Agents for Spanish Phone Negotiation: An Externally Measured Comparison of Pipecat, LiveKit and GPT-Live · 2026-11-14
- Sada-ASR: A Production Multidialectal Arabic Speech Recognition System · 2026-11-14
- Earlybird: Predictive Streaming Speech Recognition in 29M Parameters · 2026-11-10
- Joi-Bench-Task: Benchmarking Task Coordination in Full-duplex Voice Agents through Interactive Simulation · 2026-11-09
- LongCap: Hour-Scale Timestamped Audio Captioning via Chunk-wise Processing · 2026-11-08
- Gabor Gabor: E-Gaborformer, a Strictly Causal Speech Recognizer with Gabor-Dictionary Convolutions and Delta-Rule Memory · 2026-11-05
| 11 | – | cs.CL 8 · cs.AI 6 |
environmental- Sustainable Federated Fine-Tuning with LoRA: Environmental Impact and Performance Footprint · 2026-11-12
- EJAI: Judgment-Preserving Civic AI for Data Center Environmental Justice · 2026-11-10
- Earth Embeddings in Environmental Remote Sensing · 2026-11-10
- Camera equalisation of an 11.5x drop in environmental illuminance: four imitation-learning policies on an SO-101 arm · 2026-11-10
- Deep learning-guided discovery reveals the diversity and mutational potential of environmental beta-lactamases · 2026-11-09
- Small Data in Long-Term Environmental Vision: Annotation Noise, Gamification, and Label-Budget Scaling · 2026-11-06
- A Human-Verified AI Workflow for Annotating Environmental Sound Data · 2026-11-02
- How Green Is Your Manifesto? Scoring Environmental Positions in the 2024 EU Elections with an LLM Panel · 2026-11-01
- A Hierarchical Method for Environmental Sounds Recognition in Complex Acoustic Scenes · 2026-10-26
- EvoBench: An Evolving, Diagnostic Benchmark Framework for Environmental Modeling · 2026-10-26
- Whale You Go Green? Immediate and Longitudinal Effects of Embodied Conversational AI Avatars on Sustainable Behavioral Tendencies and Pro-Environmental Attitudes · 2026-10-23
| 11 | – | cs.AI 4 · cs.LG 4 |
ai network intrusion detection- Network Intrusion Detection Adaptability under Spurious Labels: A Noise-Aware Few-Shot Class-Incremental Learning Framework · 2026-11-16
- ST-GAT: A Leakage-Free Spatio-Temporal Graph Attention Framework for Robust Network Intrusion Detection · 2026-11-14
- Protocol-Aware Auditing of Domain-Blind Feature Attribution in Network Intrusion Detection · 2026-11-11
- An Empirical Evaluation of Quantum Kernel Stability in Network Intrusion Detection · 2026-11-09
- DeepChronos: Temporal Neuro-Symbolic Reasoning for Multi-Step Attack Detection · 2026-11-09
- Leakage-free evaluation of residual graph convolutional networks for network intrusion detection · 2026-11-03
- Adversarial Robustness Is Not Zero-Day Generalization: A Controlled Evaluation of Flow-Based Intrusion Detectors on Corrected CIC-IDS2017 · 2026-10-31
- DeepWeave: Weaving Neural and Symbolic Evidence for ML-Based Network Intrusion Detection System · 2026-10-30
- FGSM Attack Transferability from Simulation to Quantum Hardware in Network Intrusion Detection · 2026-10-28
- Recall or Relearn? A Mixture of In-Context Experts for Recurring Concept Drift · 2026-10-27
| 10 | – | cs.LG 9 · cs.AI 3 |
api- Invariant-Aware Harness Enforcement to Protect LLM Agents from Silent API Failures · 2026-11-16 · 4 upvotes · code
- Visual Attribution Limits and Graded Provenance Auditing in Commercial Video-Generation APIs · 2026-11-19
- Pl@ntNet machine-to-machine identification service with Pl@ntNet API: enabling automated biodiversity monitoring through large-scale plant identification · 2026-11-12
- Testing Conversation Preservation Across LLM APIs: A Rule-Based Oracle for Detecting Silent Information Loss · 2026-11-11
- What the Middleman Delivers: Answer Behavior, Tool Permissions, and Billed Usage in LLM API Relays · 2026-11-05
- Accepted but Wrong: Silent Failures of LLM Code Repairs after API Migrations · 2026-11-05
- SLATE: A Large-Scale Benchmark for Long-Horizon API Selection in E-commerce Tool Use · 2026-11-02
- WAR-CRAFT: Refining Web API Recommendations through Requirement Auditing · 2026-10-31
- Answer-Only Disclosure: Private-Context LLM Assistance over Web APIs with a Leakage Ledger · 2026-10-28
- API-TAIL: Detecting Model Substitution in LLM APIs through Temperature-Aligned Likelihood Tails · 2026-10-27
| 10 | – | cs.AI 6 · cs.CL 3 |
education- Validating LLM-Based Essay Scorers: A Comparative Analysis in Critical Online Reasoning in Medical Education · 2026-11-16
- Generative AI and the Crisis of Higher Education Assessments: Examining 'AI-Proofing' Strategies for College-Level Assessments · 2026-11-16
- AI-aided Decision-Making in Education - Uncertainty, Explainability, and Human Responsibility · 2026-11-13
- Developing an Operational Model for an Internet of Data Based Trusted Data Space for Vocational Education · 2026-11-10
- Analyzing Code Provenance in LLMs for Programming Education · 2026-11-06
- Agibot: An Open-Source Modular Swerve-Drive Robot Platform for Agricultural Robotics Research and Education · 2026-11-06
- ArSciKids: Arabic Curriculum-Aligned Datasets for Scientific Experiment and Multiple-Choice Question Generation in Primary Education · 2026-10-31
- Data Provenance and Ethics in the Curricula of U.S. Health AI Education Programs · 2026-10-29
- EDU-Jev Training System-One Decision Models for Education · 2026-10-29
- From AI-Free Gates to AI-First Work: How Engineering Students in India Navigate University Education and Career Preparation Without AI Guidelines · 2026-10-21
| 10 | – | cs.AI 7 · cs.CL 3 |
frontier large language models- InclusionMed: Benchmarking AI for Inclusive Healthcare · 2026-11-16 · 104 upvotes · code
- Structured AI ideation yields physical strategies for epithelial barrier repair · 2026-11-17
- Replicating and Extending Weight-Space Programming: Frontier LLMs Compile Programs into Weights and Read Input Layers · 2026-11-16
- Agent-written heuristics versus commercial solvers on unsolved job-shop benchmark instances · 2026-11-13
- Smart Model Routing for Order-of-Magnitude LLM Cost Reduction · 2026-11-11
- Computation, not weight access: large language models as auditors of clinical prediction networks · 2026-11-05
- A Case Study of a Multi-Agent Kernel-Optimization Loop That Learns a New AI Accelerator · 2026-10-28
- A Quantitative Approach to Asch Conformity in Frontier Large Language Models · 2026-10-27
- RAQ-MLA: Role-Aware Quantization for Multi-Head Latent Attention Caches · 2026-10-24
| 9 | – | cs.AI 8 · cs.LG 4 |
reinforcement fine-tuning services- Teaching VLMs What to Say, Not How to Reason: Rethinking Counterfactual Reasoning in Autonomous Driving · 2026-11-18
- Sideslip-Conditioned Drift Trajectory Planning with Flow Matching and Control Barrier Functions · 2026-11-17
- CARE-Drive: Coupled Alternating Refinement for Ego-trajectories · 2026-11-11
- SLIC: Reinforcement Fine-Tuning Small LMs for Multi-Turn Analog Circuit Optimization · 2026-11-10
- Measuring the Marginal Value of Verifier-Based RL Beyond Supervised Fine-Tuning · 2026-11-05
- SAFTAC: Simulation-Augmented Fine-Tuning of Open-Source LLMs for Analog Circuit Design · 2026-11-05
- SQLoom: Set-Contrastive Learning of Syntactic, Semantic, and Logical Dependencies for Text-to-SQL · 2026-11-02
- When Does Closed-Loop Curriculum Adaptation Help GRPO? An Analysis on Countdown · 2026-10-28
- LocalAgent: Collaborative Agentic Verification for Fine-Grained Instance-Level Consistency · 2026-10-21
| 9 | – | cs.AI 5 · cs.LG 3 |
speech translation- Machine interpreting competitiveness: a discourse-sensitive comparison of meaning and target-language quality in English-Chinese simultaneous interpreting · 2026-11-15
- Walrus Technical Report · 2026-11-10
- Text Grouping Changes Completion-Time Comparisons in Long-Form Simultaneous Speech Translation · 2026-11-09
- Holistic Parallel Supervision for Expressive Speech to Speech Translation · 2026-11-04
- CRESiST: Self-Enhancing Explorative Policy Learning for Simultaneous Speech Translation · 2026-11-04
- Learning Timeline-Preserving Speech-to-Speech Translation · 2026-10-31
- SimPOTrans: Self-Adaptation for Offline-to-Simultaneous Speech Translation via Reinforcement Learning · 2026-10-26
- X-Dubbing: Speech-to-Speech Translation under Temporal and Visual Constraints · 2026-10-23
- DIAL-S2ST: Learning Latency Control for Simultaneous Speech-to-Speech Translation · 2026-10-23
| 9 | – | cs.CL 9 · cs.AI 1 |
threat intelligence platforms- Measuring Hallucination in Large Language Models for Cyber Threat Intelligence: An Exploratory Study · 2026-11-19
- How Reliable Are Explanations of Language Models That Detect Insider Threats? · 2026-11-19
- Vision Language Models for Primary Structure Threat Identification in Wildland Urban Interface Fires · 2026-11-07
- Consensus-Constrained Dual-Federated Optimization with Client-Side Dynamic Weighting for Distributed Android Device Threat Defense · 2026-11-06
- Threat Modeling Intimate Partner Abuse in Agentic Systems · 2026-10-31
- When AI Investigators Cannot Trust Their Tools: Conflict-Aware Evidence Verification for Cyber Threat Investigation · 2026-10-30
- Quantifying and Prioritizing Stealthy Source-Manipulation Threats Against Multi-Source Anomaly Detectors · 2026-10-27
- Adversary Brains: Hypothesis-Based Logical Signatures for Threat Actor Detection with LLMs · 2026-10-26
- AIRO: A Streaming-Based Machine Learning Framework for Threat Detection and Security in Industrial Internet of Things · 2026-10-22
| 9 | – | cs.LG 6 · cs.AI 2 |
ai learning skills platforms- $Δτ$-Bench: Pushing Agents Toward a Moving Capability · 2026-10-25 · 23 upvotes · code
- Alignment Drives Reuse: Learning Generalizable Robot-Use Agents from Heterogeneous Experience · 2026-11-19
- Learning Martial Arts Motion Skills for Animating Opponents in VR Sparring Games · 2026-11-18
- SHAPE: Discrete Supervision and Parallel Continuous Streams for Learning Dexterous Manipulation from Egocentric Human Data · 2026-11-18
- EfficientSkill: Learning Skills for Token-Efficient Multi-Turn Agents · 2026-11-15
- AceAction-5M: Hierarchical Goals for Generalist Action Learning Across 3D Game Worlds · 2026-11-03
- SkillShift-Bench: Benchmarking Skill Learning under Environment Evolution for Web Agents · 2026-10-24
- Lifelong Context Adaptation through Bidirectional Memory-Skill Learning · 2026-10-23
| 8 | – | cs.AI 6 · cs.CL 3 |
ai optical character recognition- SEAF: Selective Semantic Enrichment and Visual Evidence Fusion for Multimodal Sarcasm Detection · 2026-11-19
- Syllable- and Word-Level Evaluation of Tibetan OCR · 2026-11-16
- Video recordings and play behaviour annotations of group-housed dairy calves on two Dutch farms · 2026-11-16
- OCR in the Foundation Model Era: From Specialist Models to Unified Models · 2026-11-03
- Digital sovereignty in professional translation workflows: a case study of migrating from Windows to Linux · 2026-10-30
- Mobilizing the Archive: Bitext Extraction at Scale from Archival Documents for Extremely Low-resource Languages · 2026-10-29
- MuSTEL: A Large-Scale Multilingual Synthetic Text-Line Image Dataset for OCR · 2026-10-25
- Reading Between the Layers: Cross-Modal Alignment and Representational Hierarchy in Vision Transformers · 2026-10-23
| 8 | – | cs.CL 5 · cs.CV 4 |
ai smart glasses- Learning What to Degrade: A Recoverability-Aware Curriculum for Reliable Smart-Glasses Super-Resolution · 2026-11-18
- Edge-Efficient Joint RAW Image Compression and Restoration for Smart Wearable Devices · 2026-11-18
- EgoPass-Bench: Identifying Objects That May Affect the Wearer's Passage in Egocentric Video · 2026-11-18
- MNN-Pocket-0.3B Technical Report · 2026-11-09
- EgoVeil: Personalized Privacy Reasoning for Egocentric Video · 2026-11-07
- Self-Supervised Pretraining for Label-Efficient Facial Expression Recognition using Smart Glasses · 2026-11-03
- Hawkeye: Reading Illegible Text with Vision Language Models · 2026-10-30
- No Frames, Just Frequencies: Bandwidth-Efficient Deployment-Time Adaptation for Smart Glasses · 2026-10-21
| 8 | – | cs.CV 6 · cs.AI 1 |
ai training infrastructure- TeleChat to Xing4: Advancing Frontier Agentic Models on Domestic Chips and Frameworks · 2026-11-17 · 162 upvotes
- Toward the Era of Agentic Embodied Intelligence · 2026-11-06 · 54 upvotes · code
- InfraRSI: Harnessing Recursive Self-Improvement for Training Infrastructure · 2026-11-08 · 27 upvotes · code
- Training Foundation Models with a Single Algorithm · 2026-10-29 · 15 upvotes · code
- LoongForge-Embodied: A Unified Framework for Training Heterogeneous Embodied Models · 2026-11-19
- Neural Circuit Architectural Priors for Rat Locomotion · 2026-11-17
- No Second Run: Does RSI Stop at Frontier Pre-training? · 2026-11-07
- Kolibri: A Sovereign European Model on the Pareto Frontier · 2026-10-22
| 8 | – | cs.AI 6 · cs.LG 3 |
enterprise ai agent platforms · also enterprise agent platforms- ARISE: Practical Self-Evolving Memory for Accurate and Cost-Efficient Enterprise Agents · 2026-11-17
- DISCERN: Preserve at Write, Resolve at Read for Persistent LLM-Agent Memory · 2026-11-11
- Compile-Gated Lean Proof Refactoring with Enterprise Agent Practices: A Model per Step under a US\$3 Cap, Followed by Programmatic Rewrite Rules · 2026-11-09
- From Process Models to Composable Agentic Workflows: Combining BPMN, Agents and Enterprise Knowledge · 2026-11-09
- DEPUTYBENCH: Evaluating Contextual Safety in Enterprise Agents · 2026-11-09
- An Alignment Benchmark for Enterprise Agents on Era by Eon · 2026-10-28
- AgentOrch: How Close Can Global Orchestration Come to Step-by-Step Interaction? · 2026-10-24
- What the Author Wrote, What the Agent Reads: Silent Cue Loss in Enterprise Document Ingestion · 2026-10-21
| 8 | – | cs.AI 7 · cs.CL 1 |
high bandwidth memory- Verify Before You Fetch: Reliable KV Cache Compression for LLM Inference · 2026-11-08
- FlashOffloading: Low-Latency KV Cache Offloading for Long-Context LLM Serving · 2026-11-05
- TACT-KV: Tri-Axis Cosine Transform for Compressing Volumetric KV Caches in Medical VLMs · 2026-11-05
- Shallow Encoding Emits Deep Memories · 2026-11-04
- Systolic Linear Attention: Co-Designing Tile-Grouped Gated Delta Attention for TPUs · 2026-11-04
- Scheduling Data to Compute: Hierarchical Data Pipelining for LLM Training on AMD GPUs · 2026-11-03
- VLA-HWBench: Where the Time Goes When VLA Models Run on Edge Hardware · 2026-10-26
- LLMs in Cloud: A Discussion on Architecture, Orchestration, and Inference · 2026-10-24
| 8 | – | cs.AI 5 · cs.LG 3 |
align- Negotiating Control and Accountability among Stakeholders in High-Risk AI Use Cases: Development and Evaluation of the Method ALIGN · 2026-11-18
- Generate, Align, and Restore: MLLM-Empowered Diffusion for Generalizable Low-light Image Enhancement · 2026-11-14
- Look Closer, Align Better: Explicit Visual Attributes for Robust EEG-to-Image Decoding · 2026-11-06
- Align Before Aggregation: Basis-Consistent Federated LoRA under Heterogeneous Ranks · 2026-11-05
- Fuse To Align: Multimodal Representation Learning for Retrieval via Hypergraph Regularization · 2026-11-02
- Align Once to Explain: Feature Alignment for Scalable B-cosification of Foundational Vision Transformers · 2026-11-02
- To Align Long, Plan Short: Simulating Diverse Profile-Aligned Students by Realizing Short-Term Plans in Long-Horizon Learning Environments · 2026-11-01
| 7 | – | cs.CV 4 · cs.AI 3 |
text-to-image generation- Breaking Visual Conventions: Spectrally Coupled Weight Perturbation for Creative Image Generation · 2026-11-17
- UniWeaver: Harnessing Unified Multimodal Models for Interleaved Text-Image Generation · 2026-11-10
- T2I Models Rarely Invert Negation but Often Fail to Suppress Negated Concepts: Benchmarking Negation Suppression in Text-to-Image Generation · 2026-11-06
- Whose Values Are Generated? Measuring Visual Value Leakage in Multilingual Text-to-Image Generation · 2026-11-03
- T-DIG: Text-Conditioned Diversity for Image Generation · 2026-10-21
- CCG Diffusion: Combinatory Categorial Grammar-Driven Compositional and Syntactically Disambiguated Text-to-Image Generation · 2026-10-21
- Spatially Gated Demographic Steering for Debiasing Multi-Person Text-to-Image Generation · 2026-10-21
| 7 | – | cs.CV 7 · cs.CL 1 |
agent swarm- SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization · 2026-11-05 · 13 upvotes · code
- ReGE: Stronger Agents through Experience Synthesis · 2026-10-24 · 13 upvotes · code
- Scaling Adaptive Prompt Injection Attacks with Agent Swarms · 2026-11-09
- XLA from the Trenches: Correctness on TPU Workloads at Scale · 2026-10-31
- Test-Time Communication in Trading Agent Swarms · 2026-10-27
- A Deterministic Security Runtime for LLM Agents on MPI and Batch-Scheduled HPC Systems: Consensus-Governed, Hardware-Rooted Supervision of Every Rank · 2026-10-23
| 6 | – | cs.AI 5 · cs.LG 2 |
ai music generation- A Tutorial on Generative Models for Music Audio · 2026-10-28 · 5 upvotes
- Evaluating the Evaluation of Music Generation Models with Generative Psychometrics · 2026-11-16
- MusicFlux: Flexible Conditioning for Text-Guided Music Generation and Editing · 2026-11-10
- How Close to the Theme? Similarity-Label Conditioning for Game Music Generation · 2026-10-31
- Does Notation Matter? MusicXML Tokenisation for Symbolic Music Generation and Understanding · 2026-10-25
- Piano2Pop: Expanding Piano Demos into Pop Productions Without Aligned Supervision · 2026-10-22
| 6 | – | cs.LG 4 · cs.AI 3 |