TengboYu

tau-0-wm. Python

DOMINO. [ECCV 2026] Towards Generalizable Robotic Manipulation in Dynamic Environments

SALMONN. SALMONN family: A suite of advanced multi-modal LLMs

PRISM. [IROS2026] PRISM: Precision and contact-rich Real-world Industrial Skill dataset with Multimodal sensing

LAPA. [ICLR 2025] LAPA: Latent Action Pretraining from Videos

glove_to_hand. Python

RynnBrain. RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Models

Awesome-WAM. A curated, continuously updated reading list, paper blogs, and resources for World Action Models (WAMs) in embodied AI.

Awesome-WholeBody-LocoManipulation.

awesome-humanoid-robot-learning. A Paper List for Humanoid Robot Learning.

ProPainter. [ICCV 2023] ProPainter: Improving Propagation and Transformer for Video Inpainting

sam3. The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

LIBERO-plus. Official repository of LIBERO-plus, a generalized benchmark for in-depth robustness analysis of vision-language-action models.

soma-retargeter. SOMA BVH to humanoid robot motion retargeting library built with Newton and NVIDIA Warp

CodePilot. A multi-model AI agent desktop client — connect any AI provider, extend with MCP & skills, control from your phone. Built with Electron + Next.js.

academic-research-skills. Academic Research Skills for Claude Code: research → write → review → revise → finalize

GMR. [ICRA 2026] GMR: General Motion Retargeting. Retarget human motions into diverse humanoid robots in real time on CPU. Retargeter for TWIST.

GR00T-WholeBodyControl. Welcome to GR00T Whole-Body Control (WBC)! This is a unified platform for developing and deploying advanced humanoid controllers. This includes: Decoupled WBC models used in NVIDIA Isaac-Gr00t, Gr00t N1.5 and N1.6 and GEAR-SONIC

TWIST2. [arXiv 2025] TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection System

whole_body_tracking. Python

DexUMI. DexUMI: Using Human Hand as the Universal Manipulation Interface for Dexterous Manipulation

hermes-agent. The agent that grows with you

Auto-claude-code-research-in-sleep. ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.

colleague-skill. 将冰冷的离别化为温暖的 Skill，欢迎加入数字生命1.0！Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶

InternVLA-A-series. InternVLA-A1: Unifying Understanding, Generation, and Action for Robotic Manipulation​

Psi0. [RSS26'] Welcome to Psi-Zero, a Humanoid VLA towards Universal Humanoid Intelligence.

Motus. Official code of Motus: A Unified Latent Action World Model

Wan2.1. Wan: Open and Advanced Large-Scale Video Generative Models

dreamzero. Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals

lingbot-va. [RSS 2026] Causal video-action world model for generalist robot control

cosmos-policy. Cosmos Policy

4DGaussians. [CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

vlash. Real-Time VLAs via Future-state-aware Asynchronous Inference.

DynamicVLA. The official implementation of "DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation". (arXiv 2601.22153)

lingbot-depth. Masked Depth Modeling for Spatial Perception

PointWorld. PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation

cosmos-predict2.5. Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the future state of the world in the form of video.

WritingAIPaper. Writing AI Conference Papers: A Handbook for Beginners

qc. Python

Awesome-RL-VLA. A Survey on Reinforcement Learning of Vision-Language-Action Models for Robotic Manipulation

Awesome-ML-SYS-Tutorial. My learning notes for ML SYS.

siiRL. siiRL: Shanghai Innovation Institute RL Framework for Advanced LLMs and Multi-Agent Systems

sam-3d-objects. SAM 3D Objects

Awesome-Spatial-Intelligence-in-VLM. A paper list for spatial reasoning

MoMaGen. Python

BEHAVIOR-1K. BEHAVIOR-1K: a platform for accelerating Embodied AI research. Join our Discord for support: https://discord.gg/bccR5vGFEx

OpenReal2Sim. A toolbox for real-to-sim reconstruction and robotic simulation

openpi. Python

diffad. Python

RoboOS. 🤖 RoboOS: A Universal Embodied Operating System for Cross-Embodied and Multi-Robot Collaboration

hello-agents. 📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程

DINO-X-API. DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding

mobipi. Official implementation for Mobi-π.

habitat-lab. A modular high-level library to train embodied AI agents across a variety of tasks and environments.

Deformable-3D-Gaussians. [CVPR 2024] Official implementation of "Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction"

ShareRobot.

starVLA. StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing

3D-R1. 3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding

RLVR-World. Official repository for "RLVR-World: Training World Models with Reinforcement Learning" (NeurIPS 2025), https://arxiv.org/abs/2505.13934

RLinf. RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI

DexGarmentLab. [NeurIPS 2025 Spotlight 🎊] DexGarmentLab: Dexterous Garment Manipulation Environment with Generalizable Policy

GarmentLab. This is the official repository of GarmentLab: A Unified Simulation and Benchmark for Garment Manipulation

MV-Adapter. [ICCV 2025] Official impl. of "MV-Adapter: Multi-view Consistent Image Generation Made Easy"

RoboFactory. [ICCV 2025] RoboFactory: Exploring Embodied Agent Collaboration with Compositional Constraints

VLA-R1. Python

verl. verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

SimpleVLA-RL. [ICLR 2026] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

OmniVLA. Official repository for OmniVLA training and inference code

VLA-Adapter. VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Model

slime. slime is an LLM post-training framework for RL Scaling.

dppo. Official implementation of Diffusion Policy Policy Optimization, arxiv 2024

RDT2. Official code of RDT 2

RynnVLA-001. [ICRA 2026] RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation

unifolm-world-model-action. Python

phantom. Python

Depth-Anything-V2. [NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

E2FGVI. Official code for "Towards An End-to-End Framework for Flow-Guided Video Inpainting" (CVPR2022)

detectron2. Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

TRELLIS. Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

OnePoseviaGen. [CORL 2025 Oral]One View, Many Worlds: Single-Image to 3D Object Meets Generative Domain Randomization for One-Shot 6D Pose Estimation.

modelscope. Python

Grounded-SAM-2. Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

RoboBrain2.5. RoboBrain 2.5: Advanced version of RoboBrain. Depth in Sight, Time in Mind. 🎉🎉🎉

LIBERO. Benchmarking Knowledge Transfer in Lifelong Robot Learning

GenPose2. [ECCV 2024] GenPose++: A generative category-level 6D object pose estimation and tracking approach proposed in Omni6DPose.

Inpaint-Anything. Inpaint anything using Segment Anything and inpainting models.

lama. 🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

dexmv-sim. DexMV: Imitation Learning for Dexterous Manipulation from Human Videos, ECCV 2022

rigvid. Python

rovi-aug. Augment robotics demonstration datasets with different robots and viewpoints

mirage. Mirage: a zero-shot cross-embodiment policy transfer method. Benchmarking code for cross-embodiment policy transfer.

nora. NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks

EgoHOS. Fine-Grained Egocentric Hand-Object Segmentation, ECCV 2022

embodied_reasoner. Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks

hume. 🦾 A Dual-System VLA with System2 Thinking

VLAS. forked from https://github.com/whichwhichgone/VLAS/tree/main

TinyLLaVA-Video-R1. TinyLLaVA-Video-R1: Towards Smaller LMMs for Video Reasoning

ManiGaussian_Bimanual. [IROS 2025] ManiGaussian++: General Robotic Bimanual Manipulation with Hierarchical Gaussian World Model

pytorch3d. PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

RoboTwin. [ICML 2026] RoboTwin 2.0 Offical Repo

vggt. [CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

espnet. End-to-End Speech Processing Toolkit

calvin. CALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks

LLaVA. [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

textgrad. TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.

Voyager. An Open-Ended Embodied Agent with Large Language Models

VLAS. Python

vjepa2. PyTorch code and models for VJEPA2 self-supervised learning from video.

metamorph. Code for "MetaMorph: Learning Universal Controllers with Transformers", Gupta et al, ICLR 2022

egoallo. Estimating Body and Hand Motion in an Ego-sensed World

ManiSkill. SAPIEN Manipulation Skill Framework, an open source GPU parallelized robotics simulator and benchmark, led by Hillbot, Inc.

UniVLA. [RSS 2025] Learning to Act Anywhere with Task-centric Latent Actions

MotionBERT. [ICCV 2023] PyTorch Implementation of "MotionBERT: A Unified Perspective on Learning Human Motion Representations"

robocasa. RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots

MiniCPM. MiniCPM5-1B: A SOTA 1B on-device LLM, small yet powerful.

robotwin. Python

OneTwoVLA. Official implementation of "OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning"

UniSkill. [CoRL 2025] UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations

LlamaFactory. Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

real2render2real. [CoRL 2025] Real2Render2Real: Scaling Robot Data Without Dynamics Simulation or Robot Hardware

FoundationPose. [CVPR 2024 Highlight] FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects

genesis-world. Simulation platform for general-purpose robotics & embodied AI learning.

Isaac-GR00T. NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.

FoundationStereo. [CVPR 2025 Best Paper Nomination] FoundationStereo: Zero-Shot Stereo Matching

hamer. HaMeR: Reconstructing Hands in 3D with Transformers

humor. Code for ICCV 2021 paper "HuMoR: 3D Human Motion Model for Robust Pose Estimation"

openvla-oft. Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success

egoallo. Estimating Body and Hand Motion in an Ego-sensed World

segment-anything. The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

open-pi-zero. Re-implementation of pi0 vision-language-action (VLA) model from Physical Intelligence

egoego_release. Official Implementation of the Paper: Ego-Body Pose Estimation via Ego-Head Pose Estimation (CVPR 2023 Award Candidate)

vq_bet_official. Official code for "Behavior Generation with Latent Actions" (ICML 2024 Spotlight)

ManipTrans. [CVPR 2025] 🎉 Official repository of "ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning"

Qwen3. Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

TesserAct. ICCV 2025 | TesserAct: Learning 4D Embodied World Models

DexGraspVLA. [AAAI'26 Oral] DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping

lerobot_source. 🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

anygrasp_sdk. Python

EgoH4. Official code releasse for "The Invisible EgoHand: 3D Hand Forecasting through EgoBody Pose Estimation"

fakemailaddress. Python

RoboSplat. [RSS 2025] Novel Demonstration Generation with Gaussian Splatting Enables Robust One-Shot Manipulation

Dummy-Robot. 我的超迷你机械臂机器人项目。

lerobot_piper. 🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

UniHSI. [ICLR 2024 Spotlight] Unified Human-Scene Interaction via Prompted Chain-of-Contacts

OpenHomie. Open-sourced code for "HOMIE: Humanoid Loco-Manipulation with Isomorphic Exoskeleton Cockpit".

mimicgen. This code corresponds to simulation environments used as part of the MimicGen project.

dexmimicgen. This code corresponds to simulation environments used as part of the DexMimicGen project.

TeleVision. [CoRL 2024] Open-TeleVision: Teleoperation with Immersive Active Visual Feedback

Open-Teach. A Versatile Teleoperation framework for Robotic Manipulation using Meta Quest3

ASAP. [RSS 2025] "ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills"

unitree_lerobot. The unitree_il_lerobot open-source project is a modification of the LeRobot open-source training framework, enabling the training and testing of data collected using the dual-arm dexterous hands of Unitree's G1 robot.

roboengine. Official Reporsitory of "RoboEngine: Plug-and-Play Robot Data Augmentation with Semantic Robot Segmentation and Background Generation"

Depth-Anything. [CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

HSMR. [CVPR25 Oral (Top 3.3%)] Official code for paper "Reconstructing Humans with a Biomechanically Accurate Skeleton".

vlarl. Single-file implementation to advance vision-language-action (VLA) models with reinforcement learning.

sam2. The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

MiniCPM-V. A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone

robotics_arXiv_daily. Fetching Embodied AI Paper from ArXiv automatically

Awesome-RL-for-LRMs. A Survey of Reinforcement Learning for Large Reasoning Models

human-policy. Python

smplify-x. Expressive Body Capture: 3D Hands, Face, and Body from a Single Image

boss. Code for the paper Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidance, accepted to CoRL 2023 as an Oral Presentation.

lemon_3d. Python

posenet-pytorch. A PyTorch port of Google TensorFlow.js PoseNet (Real-time Human Pose Estimation)

RNNPose. RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimization, CVPR 2022

yt-dlp. A feature-rich command-line audio/video downloader

agora_evaluation. Python

smplx. SMPL-X

Deep3D. Real-Time end-to-end 2D-to-3D Video Conversion, based on deep learning.

deep3d. Automatic 2D-to-3D Video Conversion with CNNs

open_x_embodiment. Jupyter Notebook

Ego4d. Ego4d dataset repository. Download the dataset, visualize, extract features & example usage of the dataset

ReconX. [TIP 2026] ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model

awesome-embodied-vla-va-vln. A curated list of state-of-the-art research in embodied AI, focusing on vision-language-action (VLA) models, vision-language navigation (VLN), and related multimodal learning approaches.

guided-diffusion. Python

graspnetAPI. Toolbox for our GraspNet-1Billion dataset.

SoM. [arXiv 2023] Set-of-Mark Prompting for GPT-4V and LMMs

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

Hybrid-VLA. HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model

LIFT3D. [CVPR 2025]Lift3D Foundation Policy: Lifting 2D Large-Scale Pretrained Models for Robust 3D Robotic Manipulation

mediapy. This Python library makes it easy to display images and videos in a notebook.

dummy_ctrl. Python

Dita. ICCV2025

Customize-it-3D. [ICRA 2025] Official implementation of Customize-It-3D: High-Quality 3D Creation from A Single Image Using Subject-Specific Knowledge Prior

universal_manipulation_interface. Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots

EXPRESS-Bench. Embodied Question Answering (EQA) benchmark and method (ICCV 2025)

vscodium. binary releases of VS Code without MS branding/telemetry/licensing

Bimanual_ur5e_joystick_control. Python

robomimic. robomimic: A Modular Framework for Robot Learning from Demonstration

act. Python

mujoco_menagerie. A collection of high-quality models for the MuJoCo physics engine, curated by Google DeepMind.

mujoco. Multi-Joint dynamics with Contact. A general purpose physics simulator.

CogACT. A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation

diffusion_policy. [RSS 2023] Diffusion Policy Visuomotor Policy Learning via Action Diffusion

google-research. Google Research

nomad. Nomad is an easy-to-use, flexible, and performant workload orchestrator that can deploy a mix of microservice, batch, containerized, and non-containerized applications. Nomad is easy to operate and scale and has native Consul and Vault integrations.

lerobot. 🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

ros2. The Robot Operating System, is a meta operating system for robots.

RoboFlamingo. Code for RoboFlamingo

act-plus-plus. Imitation learning algorithms with Co-training for Mobile ALOHA: ACT, Diffusion Policy, VINN