Yifu Yuan

Embodied-R1.5. Official code for "Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models"

AIbijia. 分享便宜靠谱Token，抹平信息差

xiaohongshu-skills. xiaohongshu-skills

OpenSpatial. Python

vla-evaluation-harness. One framework to evaluate any VLA model on any robot simulation benchmark.

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.

scenesmith. Code for "SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes", ICML 2026 Spotlight

awesome-ai-research-writing. Elevate your AI research writing, no more tedious polishing ✨

baoyu-skills. TypeScript

awesome-openclaw-tutorial. 从零开始玩转OpenClaw：最全面的中文教程，涵盖安装、配置、实战案例和避坑指南（github版）

actioncodec. ActionCodec: What Makes for Good Action Tokenizers

Long-RL. Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)

Awesome-MCP-ZH. MCP 资源精选， MCP指南，Claude MCP，MCP Servers, MCP Clients

awesome-mac.  This project is dedicated to collecting high-quality macOS software and organizing them systematically by different categories for easy search and use.

Mole. 🐹 Clean, uninstall, analyze, optimize, and monitor your Mac from the terminal.

videomimic-1.github.io. HTML

sim-evals. A simulation evaluation platform for DROID

AI-Research-SKILLs. Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.

OpenTau. Tensor's VLA Training Infrastructure for Real-World Robotics in PyTorch

LabelAny3D. [NeurIPS 2025] LabelAny3D: Label Any Object 3D in the Wild

vibe-coding-cn. Python

hi-robotics. Python

ICoPro. Python

self-llm. 《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

VLA-Arena. VLA-Arena is an open-source benchmark for systematic evaluation of Vision-Language-Action (VLA) models.

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

LIBERO-PRO. LIBERO-PRO is the official repository of the LIBERO-PRO — an evaluation extension of the original LIBERO benchmark

DepthLM_Official. [ICLR 2026 Oral (top 1.2%)] Official implementation of DepthLM

any4lerobot. 🎁 A collection of utilities for LeRobot.

RoboVerse. RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning

NSFC-LaTex. BibTeX Style

Embodied-R1. Official code for "Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation" (ICLR2026)

bibtex-tidy. Cleaner and Formatter for BibTeX files

tutorial-template. Template for the Read the Docs tutorial

MODULI. Official code for MODULI: Unlocking Preference Generalization via Diffusion Models for Offline Multi-Objective Reinforcement Learning (ICML 2025).

MODA. [ICML 2025 Spotlight] MODA: MOdular Duplex Attention for Multimodal Perception, Cognition, and Emotion Understanding

Awesome-Embodied-AI. Curated embodied AI list: surveys, VLA models, datasets, simulators, humanoids, robot learning, and safety resources.

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

Awesome-VLA-RL. This repository summarizes recent advances in the VLA + RL paradigm and provides a taxonomic classification of relevant works.

awesome-Project-Homepage-template. 🎯 Collect and create an outstanding homepage template that is relevant to your project. 🎀 Create a homepage for your work!

Embodied-FSD. Official code for "From Seeing to Doing: Bridging Reasoning and Decision for Robotic Manipulation" (ICLR2026)

cocos. Official implementation of the paper "Conditioning Matters: Training Diffusion Policies is Faster Than You Think".

SheetAgent. Python

lmms-eval. One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

Open-Reasoner-Zero. Official Repo for Open-Reasoner-Zero

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

ERQA. Embodied Reasoning Question Answer (ERQA) Benchmark

whatsup_vlms. Code and datasets for "What’s “up” with vision-language models? Investigating their struggle with spatial reasoning".

Seg-Zero. Project Page For "Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement"

EasyR1. EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

Awesome-Multimodal-Reasoning. Collections of Papers and Projects for Multimodal Reasoning.

Awesome-RL-based-Reasoning-MLLMs. This repository provides valuable reference for researchers in the field of multimodality, please start your exploratory travel in RL-based Reasoning MLLMs!

edge-TTS-record. 一个可以录制 Microsoft Edge 浏览器的语音合成（TTS）语音并输出为 .wav 音频的（windows平台）工具。

VLM-R1. Solve Visual Understanding with Reinforced VLMs

Open6DOR. Jupyter Notebook

Visual-CoT. [Neurips'24 Spotlight] Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning

Bunny. A family of lightweight multimodal models.

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

LLaVA-NPU. Run LLaVA on a NPU device, e.g. Ascend 910B

robot-3dlotus. Official implementation of "Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-guided 3D Policy."

SpatialBot. The official repo for "SpatialBot: Precise Spatial Understanding with Vision Language Models.

RoboPoint. A Vision-Language Model for Spatial Affordance Prediction in Robotics

rl.beiyang.ren. HTML

samurai. Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

chatgpt-prompts-for-academic-writing. This list of writing prompts covers a range of topics and tasks, including brainstorming research ideas, improving language and style, conducting literature reviews, and developing research plans.

Thinking-Claude. Let your Claude able to think

Awesome-Robotics-Manipulation. A comprehensive list of papers about Robot Manipulation, including papers, codes, and related websites.

voltron-robotics. Voltron: Language-Driven Representation Learning for Robotics

robots-pretrain-robots. [ICLR 2025🎉] This is the official implementation of paper "Robots Pre-Train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets".

UniDepth. Universal Monocular Metric Depth Estimation

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

lightning-hydra-template. PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡

lang-segment-anything. SAM with text prompt

general_flow. Repository for "General Flow as Foundation Affordance for Scalable Robot Learning"

metaworld2gym. Python

mae. PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

Mini-Uni-RLHF. Minimal implementation for easy-to-use RLHF annotation

OpenRLHF. An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

mimictest. A simple testbed for robotics manipulation policies

3D-PointCloud. Papers and Datasets about Point Cloud.

awe. Waypoint-Based Imitation Learning for Robotic Manipulation

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

BAKU. Code for BAKU: An Efficient Transformer for Multi-Task Policy Learning

pytorch-image-generation-metrics. Pytorch implementation of common image generation metrics.

diffusion-forcing. code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"

robot_descriptions.py. Access 185+ robot descriptions from the main Python robotics frameworks

iVideoGPT. Official repository for "iVideoGPT: Interactive VideoGPTs are Scalable World Models" (NeurIPS 2024), https://arxiv.org/abs/2405.15223

model-based-diffusion. Official implementation for the paper "Model-based Diffusion for Trajectory Optimization". Model-based diffusion (MBD) is a novel diffusion-based trajectory optimization framework that employs a dynamics model to run the reverse denoising process to generate high-quality trajectories.

ScoreDiffusionModel. The Pytorch Tutorial of Score-based and Diffusion Model

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)

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

GR1-Training. Reimplementation of GR-1, a generalized policy for robotics manipulation.

awesome-robot-learning-envs. A list of awesome and popular robot learning environments

Show2Know. 基于科研论文导向的可视化绘图集锦

Uni-RLHF-Platform. Uni-RLHF platform for "Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback" (ICLR2024)

Clean-Offline-RLHF. Offline RLHF codebase implementation for "Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback" (ICLR2024)

git-emoji-guide. :pencil2: git commit emoji guide Git提交注释使用表情指北

AlignDiff-ICLR2024. Python

screenshot-to-code. Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)

ChatGPT-Academic-Prompt. Use ChatGPT for academic writing

annotated_deep_learning_paper_implementations. 🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

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

diffusion_models_minimal_tutorial. Python

LWM. Large World Model -- Modeling Text and Video with Millions Context

dmc_remastered. A version of the DeepMind Control Suite with randomly generated graphics, for measuring visual generalization in continuous control.

DunkCityDynasty_Public. Lujijiao's Solution, #4 in Competitive track https://fuxi.163.com/competition/DunkCity/competitive-ranking https://github.com/FuxiRL/DunkCityDynasty

denoising-diffusion-pytorch. Implementation of Denoising Diffusion Probabilistic Model in Pytorch

InfiAgent. InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks (ICML 2024)

awesome-shields. The list of styled dynamic informational shields, given the ability to exist by the truly amazing work of shields.io 😍

cv. Print-friendly, minimalist CV page

WeChatMsg.

mastering-urlb. [ICML 2023] Pre-train world model-based agents with different unsupervised strategies, fine-tune the agent's components selectively, and use planning (Dyna-MPC) during fine-tuning.

Rofunc. 🤖 The Full Process Python Package for Robot Learning from Demonstration and Robot Manipulation

draw-a-ui. Draw a mockup and generate html for it

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

MV-MWM. Python

PPO-v3. Adding Dreamer-v3's implementation tricks to CleanRL's PPO

VideoRLCS. Learning to Identify Critical States for Reinforcement Learning from Videos (Accepted to ICCV'23)

RT-2. Democratization of RT-2 "RT-2: New model translates vision and language into action"

DunkCityDynasty. Python

MinAtar. Python

awesome-ai-painting. AI绘画资料合集（包含国内外可使用平台、使用教程、参数教程、部署教程、业界新闻等等） Stable diffusion、AnimateDiff、Stable Cascade 、Stable SDXL Turbo

awesome-data-annotation. A list of tools for annotating data, managing annotations, etc.

mujoco-worldgen. Automatic object XML generation for Mujoco

styles. 中文 CSL 样式 - Zotero 中文社区

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

Wandb_Tutorial. How to use wandb?

CQL. Code for conservative Q-learning

pytorch-soft-actor-critic. PyTorch implementation of soft actor critic

tcrl. Jupyter Notebook

SimpleDreamer. A Simplified Pytorch Version of the Dreamer Algorithm

CORL. High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

overcooked_ai. A benchmark environment for fully cooperative human-AI performance.

robohive. A unified framework for robot learning

PEDA. Scaling Pareto-Efficient Decision Making via Offline Multi-Objective RL, published in ICLR 2023

MO-Gymnasium. Multi-objective Gymnasium environments for reinforcement learning

d4rl-atari. Datasets for data-driven deep reinforcement learning with Atari (wrapper for datasets released by Google)

CSD-locomotion. Controllability-Aware Unsupervised Skill Discovery (ICML 2023)

choreographer. [ICLR 2023] Choreographer: a world-model-based agent that discovers and learns unsupervised skills in latent imagination, and it's able to efficiently coordinate and adapt the skills to solve downstream tasks.

SACMPC. SAC+TDMPC

dreamerv3-torch. Implementation of Dreamer v3 in pytorch.

LightZero. [NeurIPS 2023 Spotlight] LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios (awesome MCTS)

PreferenceTransformer. Preference Transformer: Modeling Human Preferences using Transformers for RL (ICLR2023 Accepted)

BPref. Official codebase for "B-Pref: Benchmarking Preference-BasedReinforcement Learning" contains scripts to reproduce experiments.

Open-Ended-Reinforcement-Learning-with-Neural-Reward-Functions. Python

Grounding_LLMs_with_online_RL. We perform functional grounding of LLMs' knowledge in BabyAI-Text

lamorel. Lamorel is a Python library designed for RL practitioners eager to use Large Language Models (LLMs).

nerfies.github.io. JavaScript

videoboard. Simple video server using python

muax. A project that provides help for using DeepMind's mctx on gym-style environments.

cleangpt. Python

AgentGPT. 🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.

AutoGPT. AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

reflexion-draft. Reflexion: an autonomous agent with dynamic memory and self-reflection

awesome-RLHF. A curated list of reinforcement learning with human feedback resources (continually updated)

cleanrl. High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

crafter-baselines. Docker containers of baseline agents for the Crafter environment

crafter. Benchmarking the Spectrum of Agent Capabilities

alfworld. ALFWorld: Aligning Text and Embodied Environments for Interactive Learning

gpt_academic. 为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。

wordcraft. An environment for benchmarking commonsense agents

ChatPaper. Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复

transformers_tasks. ⭐️ NLP Algorithms with transformers lib. Supporting Text-Classification, Text-Generation, Information-Extraction, Text-Matching, RLHF, SFT etc.

awesome-chatgpt-api. Curated list of apps and tools that not only use the new ChatGPT API, but also allow users to configure their own API keys, enabling free and on-demand usage of their own quota.

v-d4rl. Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations

arxiv-latex-cleaner. arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

dst-admin. Steam平台的Don't Starve Together 饥荒联机版管理后台

dreamerv3. Mastering Diverse Domains through World Models

Hands-on-RL. https://hrl.boyuai.com/

director. Deep Hierarchical Planning from Pixels

prompts.chat. f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

minGPT. A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

google-research. Google Research

mbpo. Code for the paper "When to Trust Your Model: Model-Based Policy Optimization"

research-lightning. A lightweight research framework

AI-Optimizer. The next generation deep reinforcement learning tookit

marathon-envs. A set of high-dimensional continuous control environments for use with Unity ML-Agents Toolkit.

brisket. A diversity-based deep RL system for fighting game behaviour generaton.

decqn. Python

XTRA. On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning

plan2explore-pytorch. Python

cascade. Implementation of CASCADE in Learning General World Models in a Handful of Reward-Free Deployments (NeurIPS 22).

avalon. A 3D video game environment and benchmark designed from scratch for reinforcement learning research

hsd3. Code for "Hierarchical Skills for Efficient Exploration" HSD-3 Algorithm and Baselines

rliable. [NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.

awesome-rl-envs.

iris. Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.

trajectory_mcl. Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning (NeurIPS 2020)

Soft-Module. Code for "Multi-task Reinforcement Learning with Soft Modularization"

awesome-multi-task-learning. A curated list of DATASETS, CODEBASES and PAPERS on Multi-Task Learning (MTL), from Machine Learning perspective.

lshort-zh-cn. A Chi­nese edi­tion of the Not So Short Introduction to LaTeX2ε

wjx. 使用selenium自动化填写问卷星问卷，2022年8月

Efficient-Task-Adaptation. Python

paper2gui. Convert AI papers to GUI，Make it easy and convenient for everyone to use artificial intelligence technology。让每个人都简单方便的使用前沿人工智能技术

stable-baselines3. PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

SMARTS. Scalable Multi-Agent RL Training School for Autonomous Driving

pytorch_sac. PyTorch implementation of Soft Actor-Critic (SAC)

garage. A toolkit for reproducible reinforcement learning research.

D4RL. A collection of reference environments for offline reinforcement learning

gflownet. Generative Flow Networks