Shikun Ban

Awesome-VLA-Post-Training. A collection of vision-language-action model post-training methods.

awesome-VLA-WAM. World Action Model, VLA failure detection/correction, Efficient VLA

rlpd. Python

HaWoR. HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos

Humanoid-self-other-distincton-model.

HumanEgo. HumanEgo: Zero-Shot Robot Learning from Minutes of Human Egocentric Videos

GazeVLA. Python

cap-x. A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation

simtoolreal. Official implementation of SimToolReal: An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulation

VGHuman. Official PyTorch implementation of "Visually-grounded Humanoid Agents"

Awesome-Touch. Tactile Sensing • Data Collection • IL/RL/VLA/WM • Manipulation • Simulation • Open Source

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

openpi_pytorch. Pytorch PI-zero and PI-zero-fast. Adapted from LeRobot

pyroki. A Modular Toolkit for Robot Kinematic Optimization

VisualMimic. [arXiv 2025] VisualMimic: Visual Humanoid Loco-Manipulation via Motion Tracking and Generation

holosoma. Python

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

embodied-ai-start. [PKU EPIC Lab] 面向小白的具身智能入门指南

ArticuBot. Official repository for RSS 25 paper: ArticuBot. Project: https://articubot.github.io/

phosphobot. Control AI robots. Community-driven UI middleware for controlling robots, recording datasets, training action models. Compatible with SO-100 and SO-101

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

oculus_reader. C++

loco-mujoco. Imitation learning benchmark focusing on complex locomotion tasks using MuJoCo.

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

Improved-3D-Diffusion-Policy. [IROS 2025] Generalizable Humanoid Manipulation with 3D Diffusion Policies. Part 1: Train & Deploy of iDP3

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.

PHC. Official Implementation of the ICCV 2023 paper: Perpetual Humanoid Control for Real-time Simulated Avatars

GenesisEnvs. Genesis Reinforcement Learning Environments

recognize-anything. Open-source and strong foundation image recognition models.

RL4VLA. Python

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

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

SelfSimRobot. Python

UP-VLA. Official PyTorch implementation for ICML 2025 paper: UP-VLA.

MathVista. MathVista: data, code, and evaluation for Mathematical Reasoning in Visual Contexts

EmbodiedBench. [ICML 2025 Oral] Official repo of EmbodiedBench, a comprehensive benchmark designed to evaluate MLLMs as embodied agents.

v2rayA. A web GUI client of Project V which supports VMess, VLESS, SS, SSR, Trojan, Tuic and Juicity protocols. 🚀

XLeRobot. XLeRobot: Practical Dual-Arm Mobile Home Robot for $660

SimplerEnv-OpenVLA. Evaluating and reproducing real-world robot manipulation policies (e.g., RT-1, RT-1-X, Octo, and OpenVLA) in simulation under common setups (e.g., Google Robot, WidowX+Bridge)

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

cosmos. NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.

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

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

Vision-Language-Models-Overview. A most Frontend Collection and survey of vision-language model papers, and models GitHub repository. Continuous updates.

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

Paper-List. A paper list of my history reading. Robotics, Learning, Vision.

Embodied-AI-Guide. [Lumina具身智能社区] 具身智能技术指南 Embodied-AI-Guide

RoboSpatial-Eval. Evaluation script for RoboSpatial-Home, a benchmark for spatial reasoning in 2D and 3D vision-language models.

open-eqa. OpenEQA Embodied Question Answering in the Era of Foundation Models

InternVL. [CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

awesome-vlm-architectures. Curated visual catalog of 155+ vision-language model (VLM/MLLM) architectures: papers, diagrams, training recipes, datasets, and a release timeline for multimodal AI agents.

awesome-ai4s. AI for Science 论文解读合集（持续更新ing），论文/数据集/教程下载：hyper.ai

ai2thor. An open-source platform for Visual AI.

FLaRe. [ICRA 25] FLaRe: Achieving Masterful and Adaptive Robot Policies with Large-Scale Reinforcement Learning Fine-Tuning

RL-VLM-F. Code for Reinforcement Learning from Vision Language Foundation Model Feedback

navchat. Code for ICRA24 paper "Think, Act, and Ask: Open-World Interactive Personalized Robot Navigation" Paper:https://arxiv.org/abs/2310.07968 Video:https://www.youtube.com/watch?v=rN5S8QIhhQc

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

any4lerobot. 🎁 A collection of utilities for LeRobot.

ReasonFlux. [NeurIPS 2025 Spotlight] LLM post-training suite — featuring ReasonFlux, ReasonFlux-PRM, and ReasonFlux-Coder.

embodied-CoT. Embodied Chain of Thought: A robotic policy that reason to solve the task.

SimplerEnv. Evaluating and reproducing real-world robot manipulation policies (e.g., RT-1, RT-1-X, Octo) in simulation under common setups (e.g., Google Robot, WidowX+Bridge) (CoRL 2024)

openvla. OpenVLA: An open-source vision-language-action model for robotic manipulation.

openpi. Python

R1-V. Witness the aha moment of VLM with less than $3.

GRAPE. GRAPE: Guided-Reinforced Vision-Language-Action Preference Optimization

AgiBot-World. [IROS 2025 Best Paper Award Finalist & IEEE TRO 2026] The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems

bypy. Python client for Baidu Yun (Personal Cloud Storage) 百度云/百度网盘Python客户端

HOI4D-Instructions. The official instructions of HOI4D dataset.

RoboVLMs. Python

stable-diffusion. A latent text-to-image diffusion model

diffuser. Code for the paper "Planning with Diffusion for Flexible Behavior Synthesis"

octo. Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.

DiffusionAsShader. [SIGGRAPH 2025] Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control

ManiGaussian. [ECCV 2024] ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulation

FreeCloth. [CVPR 2025 Highlight] Official PyTorch implementation of "FreeCloth: Free-form Generation Enhances Challenging Clothed Human Modeling"

VLM_survey. Collection of AWESOME vision-language models for vision tasks

prismatic-vlms. A flexible and efficient codebase for training visually-conditioned language models (VLMs)

sotopia-pi. Sotopia-π: Interactive Learning of Socially Intelligent Language Agents (ACL 2024)

6d-object-pose-estimation. This repository summarizes papers and codes for 6D Object Pose Estimation.

DenseMatcher. Official Repository for DenseMatcher Learning 3D Semantic Correspondence for Category-Level Manipulation from One Demo

Autoregressive-Models-in-Vision-Survey. [TMLR 2025🔥] A survey for the autoregressive models in vision.

Human-Aware-Assistance-Codespace. Python

CleanDiffuser. CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Making

DLInterview. Deep Learning Interview 深度学习面试题目汇总

awesome-phd-advice. Collection of advice for prospective and current PhD students

SAT-HMR. [CVPR 2025] SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens

co-tracker. CoTracker is a model for tracking any point (pixel) on a video.

DINO. [ICLR 2023] Official implementation of the paper "DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection"

dino. PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

dinov2. PyTorch code and models for the DINOv2 self-supervised learning method.

awesome-urdf. A curated list of Unified Robot Description Format (URDF) libraries, tools and resources.

point_odyssey. Official code for PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking (ICCV 2023)

act. Python

diff-gaussian-rasterization-w-depth. Cuda

robocook. Python

OP-Align. Python

TexPose. [CVPR 2023] Official repository for "TexPose: Neural Texture Learning for Self-Supervised 6D Object Pose Estimation"

Social-CH. [NeurIPS 2023] PyTorch Implementation of "Social Motion Prediction with Cognitive Hierarchies"

YPPF. Yuanpei Profile

pymc. Bayesian Modeling and Probabilistic Programming in Python

3D-Diffusion-Policy. [RSS 2024] 3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations

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

ElasticReconstruction. 3D reconstruction system to creating detailed scene geometry from range video.

Open3D-ML. An extension of Open3D to address 3D Machine Learning tasks

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

pytorch_kinematics. Robot kinematics implemented in pytorch

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

awe. Waypoint-Based Imitation Learning for Robotic Manipulation

DriveDownloader. Download resources from online storage with ONLY ONE command line!!

DaXBench. Python

softagent. Algorithms for deformable object manipulation benchmarked in SoftGym

SoftMAC. Code repository for our paper SoftMAC: Differentiable Soft Body Simulation with Forecast-based Contact Model and Two-way Coupling with Articulated Rigid Bodies and Clothes

softgym. SoftGym is a set of benchmark environments for deformable object manipulation.

VGPL-Dynamics-Prior. [ICML 2020] Visual Grounding of Learned Physical Models (Dynamics Prior)

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

smalldiffusion. Simple and readable code for training and sampling from diffusion models

DPI-Net. [ICLR 2019] Learning Particle Dynamics for Manipulating Rigid Bodies, Deformable Objects, and Fluids

Holistic-Robot-Pose-Estimation. [ECCV 2024] PyTorch implementation of "Real-time Holistic Robot Pose Estimation with Unknown States"

PhysDreamer. Code for PhysDreamer

diffusion-literature-for-robotics. Summary of key papers and blogs about diffusion models to learn about the topic. Detailed list of all published diffusion robotics papers.

rh20t_api. Python

d3fields. [CoRL 24 Oral] D^3Fields: Dynamic 3D Descriptor Fields for Zero-Shot Generalizable Rearrangement

SpacetimeGaussians. [CVPR 2024] Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis

Dynamic3DGaussians. Python

gaussian-splatting. Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

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

PhysGaussian. [CVPR 2024 Highlight] PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics

awesome-3D-gaussian-splatting. Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.

RoboEXP. [CoRL 2024] RoboEXP: Action-Conditioned Scene Graph via Interactive Exploration for Robotic Manipulation

.tmux. Oh my tmux! My self-contained, pretty & versatile tmux configuration made with 💛🩷💙🖤❤️🤍

SAMforMedPic. 北京大学2023年秋季学期 机器学习大作业

final-vcl. final project

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

Awesome-Robotics-Foundation-Models.

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

RoboGen. A generative and self-guided robotic agent that endlessly propose and master new skills.

GNFactor. [CoRL 2023 Oral] GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields

Awesome-Generalist-Robots-via-Foundation-Models. Paper list in the survey paper: Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis