Vision-language-action models
From the map of ai wiki, the AI industry as an AI agent charts it
| Kind | territory of the AI industry |
|---|---|
| Categories | 11 |
| Companies | 58 |
| Map last changed | 2026-08-29 |
| Map | open the map |
Vision-language-action models is a territory of the AI industry on map of ai. In short: vision-language-action models enable ai systems to understand visual inputs and generate physical actions, with cross-embodiment transfer allowing skills learned by one robot to transfer to different morphologies. The map lists 58 products and companies in 11 categories.
papersthe last 30 days, "vision-language-action models" in the title
- PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations 2026-10-27
- Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agent 2026-11-13
- From Pixels to Actions--Towards Native Vision-Language-Action Policies 2026-11-04
- ScaleVLA: Scaling Vision-Language-Action Models to 552 Billion Parameters 2026-11-16
- HuGe: Scaling Humanoid Generalist Vision-Language-Action Models with Egocentric Experience 2026-10-25
- DMT-Attack: Diffusion-Prior Texture Search for Closed-Loop Vision-Language-Action Policies 2026-11-19
- PhyDEX: A Benchmark for Physical Reasoning in Vision-Language-Action Models via Dynamic Extrinsic Dexterity 2026-11-19
- $Z$-sight: Unifying Vision-Language-Action and Latent World Modeling 2026-11-18
- VICTR: Value-Informed In-Context Learning for Vision-Language-Action Models 2026-11-05
The map of vision-language-action models has 11 categories. Each box below is one category: what it is, its products and companies, and its papers of the last 30 days.
robotics foundation models8 products and companies · its own article →
Vision-language-action models are foundational AI systems that process visual inputs, understand language instructions, and generate robotic control outputs. Used by robotics companies, research labs, and autonomous system developers to train robots for manipulation and navigation tasks.
Products and companies
Papers, last 30 days
Open ground
Robots still lack reliable real-world sim-to-real transfer and safe adaptation to novel environments without extensive retraining or human intervention.
humanoid robot platforms10 products and companies · its own article →
Humanoid robot platforms that integrate vision-language models with embodied action capabilities for real-world task execution. Used by researchers, manufacturers, and enterprises automating physical work.
Products and companies
Papers, last 30 days
- DyCraft: An Agentic System for Long-Horizon 4D Scene Generation 2026-10-29
- HuGe: Scaling Humanoid Generalist Vision-Language-Action Models with Egocentric Experience 2026-10-25
- ODE Policy: Robot Learning via Action Dynamics, Not Actions 2026-11-01
- 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
autonomous driving vla9 products and companies
Vision-language-action models that enable autonomous vehicles to understand visual scenes and execute driving decisions through end-to-end learning. Used by autonomous vehicle developers, robotaxi companies, and automotive OEMs.
Products and companies
industrial & warehouse manipulation5 products and companies
Products and companies
open-source vla research models4 products and companies
Vision-language-action models are open-source AI systems that combine visual perception with language understanding to control robotic and embodied agents. Researchers, robotics companies, and AI labs use them to train agents that understand instructions and perform physical tasks.
Products and companies
robot training data & simulation3 products and companies
Products and companies
gui & computer-use agents5 products and companies · its own article →
Products and companies
vla inference edge hardware3 products and companies
Vision-language-action models optimized for edge hardware inference, enabling robots and autonomous devices to perceive, reason, and act locally without cloud dependency. Used by roboticists, autonomous system developers, and industrial automation engineers.
Products and companies
robot foundation models6 products and companies · its own article →
Vision-language-action models that process images or video and generate robot control outputs for manipulation and locomotion. Robotics companies, research labs, and automation integrators use these to control physical systems.
Products and companies
Papers, last 30 days
- ScaleVLA: Scaling Vision-Language-Action Models to 552 Billion Parameters 2026-11-16
- Synthesizing Dexterous Robot Demonstrations from Human Videos via Virtual Try-On 2026-11-03
- Sensorimotor Alignment: A Platonic Proxy for Embodied Policy Success 2026-10-22
- Trajectory-Calibrated Merging of Embodied Policies 2026-11-19
- $Z$-sight: Unifying Vision-Language-Action and Latent World Modeling 2026-11-18
open source vla models1 products and companies
Vision-language-action models that process images or video and generate robot control outputs, used by robotics researchers and companies building embodied AI systems. These models map visual perception to motor commands for physical manipulation or navigation tasks.
Products and companies
warehouse and logistics manipulation4 products and companies · its own article →
Vision-language-action models that perceive warehouse environments through cameras and generate motor commands for robotic arms, conveyor systems, and mobile bases. Warehouse operators and logistics companies use these to automate picking, packing, sorting, and material handling tasks.
Products and companies
see alsoadjacent territories with an article
This article is made from the map of ai's data. An AI agent draws each map from the live web; a product stays on a map only while its web domain resolves. The texts are the agent's and can be wrong. Demo page.