Lists (2)
Stars
[CVPR 2025] The offical Implementation of "Universal Actions for Enhanced Embodied Foundation Models"
GigaBrain-0: A World Model-Powered Vision-Language-Action Model
GigaWorld-Policy: An Efficient Action-Centered World–Action Model
GigaWorld-0: World Models as Data Engine to Empower Embodied AI
The offical repo for paper "VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers" (ICCV 2025)
LAP: Language-Action Pre-Training Enables Zero-Shot Cross Embodiment Transfer
[ICLR 2026] The offical Implementation of "Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model"
ActionCodec: What Makes for Good Action Tokenizers
One framework to evaluate any VLA model on any robot simulation benchmark.
A opensource, torch-like api framework for dynamic multi-agent workflow.
[ICML 2026] LaST$_0$: Latent Spatio-Temporal Chain-of-Thought for Robotic Vision-Language-Action Model
A test-time method for determining the execution horizon for flow-matching VLAs
Dexbotic: Open-Source Vision-Language-Action Toolbox
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
RoboChallenge Inference example code
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
Official implementation of "OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning"
Re-implementation of pi0 vision-language-action (VLA) model from Physical Intelligence
Tensor's VLA Training Infrastructure for Real-World Robotics in PyTorch
[ICLR 2026🔥] MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
Official repository of LIBERO-plus, a generalized benchmark for in-depth robustness analysis of vision-language-action models.
RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI
[Embodied-AI-Survey-2025] Paper List and Resource Repository for Embodied AI
The code for controlling the Piper robotic arm
Running VLA at 30Hz frame rate and 480Hz trajectory frequency