Vision-language-action models

Research

Code of "MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulation"

Research

MobileVLA-R1: Reinforcing Vision-Language-Action for Mobile Robots

Research

OmniVLA provides training and inference code for multimodal robot navigation.

Research

OpenDM provides an open-world foundation-model research project for embodied intelligence.

Research

Openpi Dexterous studies pi0 LoRA adaptation for Shadow Hand manipulation and reports experimental limitations.

Research

Open Pi Zero is a reimplementation of Physical Intelligence's pi0 VLA model.

Research

OpenVLA Reproduction documents setup and evaluation of OpenVLA on LIBERO tasks.

Research

O-VLA studies VLA transfer through semantic primitive learning.

Research

Official implementation of ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver.

Research

Official repo of Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Robotics

Research

Native-video memory for vision-language-action models, using timestamped visual history and exact streaming inference for long-horizon robot manipulation.

Research

Spirit-v1.5: A Robotic Foundation Model by Spirit AI

Research

VIRENA demonstrates a small VLA policy on ManiSkill PickCube with LeRobot integration resources.

Research

VITRA: Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos

Research

VLA From Scratch compares action representations on multimodal demonstrations and obstacle-routing tasks.

Research

Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representations

Research

A vision-language-action research model for robot manipulation.

Research

A robot foundation model from Physical Intelligence.