Yanjiang Guo

SSVAE. official implementation of the paper "Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability".

e2vla. Python

VITRA. [ICRA 2026] VITRA: Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos

Wan2.2. Wan: Open and Advanced Large-Scale Video Generative Models

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

dsrl_pi0. Official implementation for pi0 steering via DSRL, Steering Your Diffusion Policy with Latent Space Reinforcement Learning (CoRL 2025)

VLM4VLA. Implementation of VLM4VLA

large-video-planner. Python

polaris. A real2sim evaluation framework for generalist policies

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

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

Ctrl-World. ICLR 2026 Paper: Ctrl-World

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.

cosmos-predict2. Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.

Self-Forcing. Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)

pytorch-fid. Compute FID scores with PyTorch.

stylegan-v. [CVPR 2022] StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2

world-model-eval. Code for "Evaluating Robot Policies in a World Model".

IRASim. Python

WorldMem. [NeurIPS 2025] WorldMem: Long-term Consistent World Simulation with Memory

DiffSynth-Studio. Enjoy the magic of Diffusion models!

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

openpi. Python

zed-python-api. Python API for the ZED SDK

sim-evals. A simulation evaluation platform for DROID

AdaWorld. [ICML'25] The PyTorch implementation of paper: "AdaWorld: Learning Adaptable World Models with Latent Actions".

Vista. [NeurIPS 2024] A Generalizable World Model for Autonomous Driving

yay_robot. PyTorch implementation of YAY Robot

any4lerobot. 🎁 A collection of utilities for LeRobot.

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

openpoints. OpenPoints: a library for easily reproducing point-based methods for point cloud understanding. The engine for [ASSANet](https://arxiv.org/abs/2110.10538), [PointNeXt](https://arxiv.org/abs/2206.04670)

droid. Distributed Robot Interaction Dataset.

3d-foundation-policy. Jupyter Notebook

Bagel. Open-source unified multimodal model

VQASynth. Compose multimodal datasets 🎹

BLIP3o. Official implementation of BLIP3o-Series

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

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

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

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

act. Python

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

video-prediction-policy. Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations https://video-prediction-policy.github.io

univlg. Unifying 2D and 3D Vision-Language Understanding

LLaVA-3D. [ICCV 2025] A Simple yet Effective Pathway to Empowering LLaVA to Understand and Interact with 3D World

Pandora. Pandora: Towards General World Model with Natural Language Actions and Video States

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

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

RL4VLM. Official Repo for Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning

alfred. ALFRED - A Benchmark for Interpreting Grounded Instructions for Everyday Tasks

RAGEN. RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.

open_x_embodiment. Jupyter Notebook

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

open-r1-multimodal. A fork to add multimodal model training to open-r1

Awesome-Video-Diffusion. A curated list of recent diffusion models for video generation, editing, and various other applications.

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

Janus. Janus-Series: Unified Multimodal Understanding and Generation Models

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)

CogVideo. text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

finetrainers. Scalable and memory-optimized training of diffusion models

Prediction_with_Action. Official PyTorch implementation for NeurIPS 2024 paper: Prediction with Action.

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.

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

mimictest. A simple testbed for robotics manipulation policies

chameleon. Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.

VAR. [NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

ACT. Action Chunking Transformer implementation for low cost robot

Show-o. [ICLR & NeurIPS 2025] Repository for Show-o series, One Single Transformer to Unify Multimodal Understanding and Generation.

awesome-world-models-manipulation. Awesome world models for manipulation

SEED-Voken. SEED-Voken: A Series of Powerful Visual Tokenizers

1xgpt. world modeling challenge for humanoid robots

animate-anything. Fine-Grained Open Domain Image Animation with Motion Guidance

SVD_Xtend. Stable Video Diffusion Training Code and Extensions.

generative-models. Generative Models by Stability AI

VideoCrafter. VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models

DynamiCrafter. [ECCV 2024, Oral] DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

Awesome-Video-Diffusion-Models. [CSUR] A Survey on Video Diffusion Models

jonbarron.github.io. HTML

mdt_policy. [RSS 2024] Code for "Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goals" for CALVIN experiments with pre-trained weights

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

3d_diffuser_actor. Code for the paper "3D Diffuser Actor: Policy Diffusion with 3D Scene Representations"

SwinIR. SwinIR: Image Restoration Using Swin Transformer (official repository)

ResShift. ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting (NeurIPS@2023 Spotlight, TPAMI@2024)

video-keyframe-detector. It is a simple python tool to extract key-frames from a video file using peak estimation from frame difference.

fast-DiT. Fast Diffusion Models with Transformers

Open-Sora. Open-Sora: Democratizing Efficient Video Production for All

DiT. Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

serl_franka_controllers. Cartesian impedance controller with reference limiting for Franka Emika Robot

serl. SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning

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

PVM-Robotics. The repository for a thorough empirical evaluation of pre-trained vision model performance across different downstream policy learning methods.

relay-policy-learning. Python

Gymnasium-Robotics. A collection of robotics simulation environments for reinforcement learning

Gymnasium. A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

r3m. Pre-training Reusable Representations for Robotic Manipulation Using Diverse Human Video Data

humanoid-gym. Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer https://arxiv.org/abs/2404.05695

DRL-code-pytorch. Concise pytorch implements of DRL algorithms, including REINFORCE, A2C, DQN, PPO(discrete and continuous), DDPG, TD3, SAC.

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

dreamerv2. Pytorch implementation of Dreamer-v2: Visual Model Based RL Algorithm.

PALM-E. Implementation of "PaLM-E: An Embodied Multimodal Language Model"

LIBERO. Benchmarking Knowledge Transfer in Lifelong Robot Learning

scalingup. [CoRL 2023] This repository contains data generation and training code for Scaling Up & Distilling Down

dreamerv3-torch. Implementation of Dreamer v3 in pytorch.

mvp. Masked Visual Pre-training for Robotics

ROT. Code for Watch and Match: Supercharging Imitation with Regularized Optimal Transport

robotic-transformer-pytorch. Implementation of RT1 (Robotic Transformer) in Pytorch

Conference-Acceptance-Rate. Acceptance rates for the major AI conferences

language-table. Suite of human-collected datasets and a multi-task continuous control benchmark for open vocabulary visuolinguomotor learning.

LAVIS. LAVIS - A One-stop Library for Language-Vision Intelligence

ai2thor. An open-source platform for Visual AI.

Awesome-LLM-RL. A comprehensive list of PAPERS, CODEBASES, and, DATASETS on Decision Making using Foundation Models including LLMs and VLMs.

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

iGibson. A Simulation Environment to train Robots in Large Realistic Interactive Scenes

virtualhome. API to run VirtualHome, a Multi-Agent Household Simulator

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

auto-login-script-for-tunet. An automatically login script for Tsinghua net based on GoAuthing.

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

online-diffuser. Python

FastChat. An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

llama. Inference code for Llama models

BLIP. PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

OFA. Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

ravens. Train robotic agents to learn pick and place with deep learning for vision-based manipulation in PyBullet. Transporter Nets, CoRL 2020.

cliport. CLIPort: What and Where Pathways for Robotic Manipulation

MotionCLIP. Official Pytorch implementation of the paper "MotionCLIP: Exposing Human Motion Generation to CLIP Space"

EnvInteractiveLMPapers. Paper collections of methods that using language to interact with environment, including interact with real world, simulated world or WWW(🏄).

Awesome-LLM-Robotics. A comprehensive list of papers using large language/multi-modal models for Robotics/RL, including papers, codes, and related websites

IIIS-preliminary. Jupyter Notebook

IsaacGymEnvs. Isaac Gym Reinforcement Learning Environments

AMP_for_hardware. Code for "Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions"

legged_gym. Isaac Gym Environments for Legged Robots

DeepMimic_mujoco. DeepMimic Mujoco version; Python only; No Bullet, No C++

DexterousHands. This is a library that provides dual dexterous hand manipulation tasks through Isaac Gym

thuthesis. LaTeX Thesis Template for Tsinghua University

gail-airl-ppo.pytorch. PyTorch implementation of GAIL and AIRL based on PPO.

PyTorch-VAE. A Collection of Variational Autoencoders (VAE) in PyTorch.

Benchmark-Efficient-Reinforcement-Learning-with-Demonstrations. Benchmark present methods for efficient reinforcement learning. Methods include Reptile, MAML, Residual Policy, etc. RL algorithms include DDPG, PPO.

drqv2. DrQ-v2: Improved Data-Augmented Reinforcement Learning

DRL-Pytorch. Clean, Robust, and Unified PyTorch implementation of popular Deep Reinforcement Learning (DRL) algorithms (Q-learning, Duel DDQN, PER, C51, Noisy DQN, PPO, DDPG, TD3, SAC, ASL)

spinningup. An educational resource to help anyone learn deep reinforcement learning.

Deep-reinforcement-learning-with-pytorch. PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....

AWAC. Advantage weighted Actor Critic for Offline RL

DDPGfD. DDPGfD: This is our implementation project for the Reinforcement Learning course in NCTU.

robohive. A unified framework for robot learning

hand_dapg. Repository to accompany RSS 2018 paper on dexterous hand manipulation

kPAM. kPAM: Generalizable Robotic Manipulation

SimSR. AAAI-22 paper: SimSR: Simple Distance-based State Representationfor Deep Reinforcement Learning

deep_bisim4control. Learning Invariant Representations for Reinforcement Learning without Reconstruction

CVRL. code for CoRL 2020 paper "Contrastive Variational Model-Based Reinforcement Learning for Complex Observations"

ICRA2021PaperList. ICRA 2021 paper list

oprl. A Modular Library for Off-Policy Reinforcement Learning with a focus on SafeRL and distributed computing

procgen. Procgen Benchmark: Procedurally-Generated Game-Like Gym-Environments

spr. Code for "Data-Efficient Reinforcement Learning with Self-Predictive Representations"

belief-grounded-network. [CoRL 2020] Belief-Grounded Networks for Accelerated Robot Learning under Partial Observability

ray. Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

varibad. Implementation of VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning - Zintgraf et al. (ICLR 2020)

curl. CURL: Contrastive Unsupervised Representation Learning for Sample-Efficient Reinforcement Learning

webhole. THU Hole react frontend

thuhole_memories.

dreamer. Dream to Control: Learning Behaviors by Latent Imagination

dreamer-pytorch. pytorch-implementation of Dreamer (Model-based Image RL Algorithm)

robosuite. Python

slac.pytorch. PyTorch implementation of Stochastic Latent Actor-Critic(SLAC).

Metaworld. Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning

slac. Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model

pytorch_rl2. My implementations of 'RL^2: Fast Reinforcement Learning via Slow Reinforcement Learning' and 'A Simple Neural Attentive Meta-Learner'

garage. A toolkit for reproducible reinforcement learning research.

ProMP. Implementation of Proximal Meta-Policy Search (ProMP) as well as related Meta-RL algorithm. Includes a useful experiment framework for Meta-RL.

oyster. Implementation of Efficient Off-policy Meta-learning via Probabilistic Context Variables (PEARL)

meld. MELD: Meta-Reinforcement Learning from Images via Latent State Models https://arxiv.org/abs/2010.13957

PaddleRobotics. PaddleRobotics is an open-source algorithm library for robots based on Paddle, including open-source parts such as human-robot interaction, complex motion control, environment perception, SLAM positioning, and navigation.

tianshou. An elegant PyTorch deep reinforcement learning library.

SMERL. Python

SimGAN. Pytorch Implementation of SimGAN: Hybrid Simulator Identification for Domain Adaptation via Adversarial Reinforcement Learning, ICRA 2021

pytorch-a2c-ppo-acktr-gail. PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).

dart. Research-focused C++23 physics engine for robotics, animation, and machine learning, with Python bindings

mbbl. Python

Model-Based-RL. 这是一个关于基于模型的强化学习的资料，包括一些代码地址、paper、slide等。

CalibratedModelBasedRL. Code for "Calibrated Model-Based Deep Reinforcement Learning", ICML 2019.

motion_imitation. Code accompanying the paper "Learning Agile Robotic Locomotion Skills by Imitating Animals"

MetaGym. Collection of Reinforcement Learning / Meta Reinforcement Learning Environments.

pytorch-maml-rl. Reinforcement Learning with Model-Agnostic Meta-Learning in Pytorch

handful-of-trials. Experiment code for "Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models"

BREMEN. Codebase of Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization (ICLR2021)

MOReL. Model-Based Offline Reinforcement Learning

rlkit. Collection of reinforcement learning algorithms

mbpo_pytorch. A pytorch reprelication of the model-based reinforcement learning algorithm MBPO

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

google-research. Google Research

awesome-offline-rl. An index of algorithms for offline reinforcement learning (offline-rl)

tiny-differentiable-simulator. Tiny Differentiable Simulator is a header-only C++ and CUDA physics library for reinforcement learning and robotics with zero dependencies.

pytorch-CycleGAN-and-pix2pix. Image-to-Image Translation in PyTorch

Reinforcement-Implementation. Implementation of benchmark RL algorithms

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

Deep-Learning-Papers-Reading-Roadmap. Deep Learning papers reading roadmap for anyone who are eager to learn this amazing tech!

fast-style-transfer. TensorFlow CNN for fast style transfer ⚡🖥🎨🖼

deeplearning-assignment. 深度学习笔记

tensorflow-windows-wheel. Tensorflow prebuilt binary for Windows

REKCARC-TSC-UHT. 清华大学计算机系课程攻略 Guidance for courses in Department of Computer Science and Technology, Tsinghua University

resource. Resource provied by EESAST