Vision-language-action models

Research

Code and model resources for Physical Intelligence robot policies.

Research

Robot foundation-model resources for humanoid learning workflows.

Research

NVIDIA Alpamayo 1.5 Nano is an open 10B reasoning VLA model for autonomous vehicles with reinforcement-learning enhanced reasoning, navigation guidance, and visual question answering.

Research

DeeR-VLA studies dynamic multimodal-model inference for robot execution.

Research

Fine-tuning tools for adapting OpenVLA action prediction.

Research

InternVLA-M1 provides a spatially guided vision-language-action framework for robot policies.

Research

Official code and checkpoint release for mobile robot foundation models: GNM, ViNT, and NoMaD.

Open source

RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation

Research

This repository is the implementation of "NaVILA: Legged Robot Vision-Language-Action Model for Navigation"

Research

A framework for connecting vision-language models to robotic actions.

Research

Robot policy research using latent action representations.

Research

InternNav provides a platform for developing navigation foundation models.

Research

Implementation of π₀, the robotic foundation model architecture proposed by Physical Intelligence

Research

GraspVLA provides grasping-model research pretrained with synthetic action data.

Research

🔥 SpatialVLA: a spatial-enhanced vision-language-action model that is trained on 1.1 Million real robot episodes. Accepted at RSS 2025.

Research

official implementation for our paper Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance (CoRL 2024)

Research

Official code for MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation

Research

BAAI UniVLA provides a unified vision-language-action model research project.

Research

UniAct studies universal action representations for embodied foundation models.

Research

X-VLA studies soft-prompted transformers for cross-embodiment vision-language-action learning.

Research

HiMoE-VLA studies hierarchical mixture-of-experts policies for vision-language-action learning.

Research

SimpleVLA-RL provides reinforcement-learning training resources for VLA policies.

Research

VLAC: A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning

Research

VLA-RL provides reinforcement-learning code for adapting VLA models to robotic manipulation.