Yipeng Gao

Kimi-K3. Open Frontier Intelligence

Articraft. A simple AI agent that turns prompts into articulated 3D objects.

manim. Animation engine for explanatory math videos

videos. Code for the manim-generated scenes used in 3blue1brown videos

Data-Engine-OmniX. UE5-based Data Engine used in OmniX

triton. Development repository for the Triton language and compiler

GLM-5. GLM-5: From Vibe Coding to Agentic Engineering

SWE-IF. SWE-IF: Aligning Code Evaluation with Human Preference (ICML 2026)

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

artiverse. Python

LongLive-RAG. Official Implementation of LongLive-RAG: A general retrieval-augmented framework for long video generation.

cosmos-framework. Our inference and training framework to run on the Cosmos Models

OpenHands. 🙌 OpenHands: AI-Driven Development

3dcodebench. Benchmarking Agentic Procedural 3D Modeling Via Code

articraft. Superseded by https://github.com/articraftresearch/Articraft. This repository is kept for reference.

ECC. The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

kilocode. Kilo is the all-in-one agentic engineering platform. Build, ship, and iterate faster with the most popular open source coding agent.

autoresearch. AI agents running research on single-GPU nanochat training automatically

VibeVoice. Open-Source Frontier Voice AI

humanlm. HumanLM: Simulating Users with State Alignment Beats Response Imitation

VRAG. Multimodal Retrieval-augmented Generation Framework Built by Tongyi Lab, Alibaba Group.

HY3D-Bench. Python

IsaacLab. Unified framework for robot learning built on NVIDIA Isaac Sim

gemma. Gemma open-weight LLM library, from Google DeepMind

lingbot-world. Advancing Open-source World Models

openclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

skills. Public repository for Agent Skills

original_performance_takehome. Anthropic's original performance take-home, now open for you to try!

ShapeR. Code for the ShapeR research paper

VIGA. VIGA: Vision-as-Inverse-Graphics Agent

unity-mcp. Unity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets, control scenes, edit scripts, and automate tasks within Unity.

Qwen3-VL-Embedding. Python

terminal-bench. A benchmark for LLMs on complicated tasks in the terminal

skillsbench. SkillsBench evaluates how well skills work and how effective agents are at using them.

blender-mcp. Open-source MCP to use Blender with any LLM

harbor. Framework for evaluating and improving agents

open-thoughts. Fully open data curation for reasoning models

UltraRAG. A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

VisRAG. Parsing-free RAG supported by VLMs

Awesome-Latent-Space. A paper list of Awesome Latent Space.

Awesome-RAG. 😎 Awesome list of Retrieval-Augmented Generation (RAG) applications in Generative AI.

Awesome-RAG-Vision. Awesome-RAG-Vision: a curated list of advanced retrieval augmented generation (RAG) for Computer Vision

Pancap. [NeurIPS 2025] Panoptic Captioning: An Equivalence Bridge for Image and Text

ragflow. RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

threefiner. An interface for text-guided mesh refinement.

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

fullpart. A part-based 3D generation framework & the largest and most comprehensively annotated 3D part dataset.

PartNeXt. [Neurips DB 2025] PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding

PartCrafter. [NeurIPS 2025] PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers

BesiegeField. Official repo of BesiegeField, an interactive and real-time environment for machine construction and simulation (arXiv:2510.14980).

nanochat. The best ChatGPT that $100 can buy.

lynx. Lynx: Towards High-Fidelity Personalized Video Generation

Hunyuan3D-Part. Hunyuan 3D Part Segmentation and Generation Pipeline

ll3m. LL3M writes Python code that generates 3D assets in Blender.

urdf-visualizer. A VSCode extension for visualizing the URDF file and xacro file.

MeshCoder. Jupyter Notebook

LeetCUDA. LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.

MUSAR.

gpt-oss. gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

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

copart. CoPart (ICCV 2025): A part-based 3D generation framework & the first large-scale part-level 3D dataset.

context7. Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

flux. Official inference repo for FLUX.1 models

MSRVTT-Personalization. Benchmark dataset and code of MSRVTT-Personalization

Phantom-Data. Phantom-Data: Towards a General Subject-Consistent Video Generation Dataset

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

VACE. [ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing

Phantom. Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment

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

MAGI-1. MAGI-1: Autoregressive Video Generation at Scale

python-sdk. The official Python SDK for Model Context Protocol servers and clients

Any2Caption. This is the project for 'Any2Caption', Interpreting Any Condition to Caption for Controllable Video Generation

SkyReels-A2. SkyReels-A2: Compose anything in video diffusion transformers

codex. Lightweight coding agent that runs in your terminal

ArtFormer. [CVPR 2025] ArtFormer: Controllable Generation of Diverse 3D Articulated Objects

X-Dyna. [CVPR 2025 Highlight] X-Dyna: Expressive Dynamic Human Image Animation

SWELancer-Benchmark. This repo contains the dataset and code for the paper "SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?"

langchain. The agent engineering platform.

Hunyuan3D-2. High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

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.

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

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

articulate-anything. [ICLR 2025] Official implementation of Articulate-Anything

generative-models. Generative Models by Stability AI

HOISwap. [NeurIPS 2024] HOI-Swap: Swapping Objects in Videos with Hand-Object Interaction Awareness

stretch_ai. Python

HunyuanVideo. HunyuanVideo: A Systematic Framework For Large Video Generation Model

robust-rearrangement. From Imitation to Refinement -- Residual RL for Precise Assembly

furniture-bench. FurnitureBench: Real-World Furniture Assembly Benchmark (RSS 2023)

IKEA-Manuals-at-Work. IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos

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

dexart-release. DexArt: Benchmarking Generalizable Dexterous Manipulation with Articulated Objects, CVPR 2023

scene-language. (CVPR 2025 Highlight) The Scene Language: Representing Scenes with Programs, Words, and Embeddings

LLaMA-Mesh. Unifying 3D Mesh Generation with Language Models

screenpipe. YC (S26) | Record your screen 24/7 and plug into your agents. Local, private, secure. Connect to OpenClaw, Hermes agent and 100+ apps

ShapeAssembly. Public code release for our Siggraph Asia 2020 paper: ShapeAssembly: Learning to Generate Programs for 3D Shape Structure Synthesis

Moore-AnimateAnyone. Character Animation (AnimateAnyone, Face Reenactment)

Holodeck. CVPR 2024: Language Guided Generation of 3D Embodied AI Environments.

ComfyUI. The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

xformers. Hackable and optimized Transformers building blocks, supporting a composable construction.

LGM. [ECCV 2024 Oral] LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation.

diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

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

HPT. Heterogeneous Pre-trained Transformer (HPT) as Scalable Policy Learner.

cage. [CVPR 2024] Official Implementation of the paper "CAGE: Controllable Articulation GEneration"

real2code. Python

Microsoft-Activation-Scripts. Open-source Windows and Office activator featuring HWID, Ohook, TSforge, and Online KMS activation methods, along with advanced troubleshooting.

Awesome-Articulated-Object-Understanding. A curated list of resources for articulated objects understanding.

urdf-viz. visualize URDF/XACRO file, URDF Viewer works on Windows/MacOS/Linux

phobos. An add-on for Blender allowing to create URDF, SDF and SMURF robot models in a WYSIWYG environment.

kubric. A data generation pipeline for creating semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation masks, depth maps, and optical flow.

urdformer. code release for URDFormer

axolotl. Go ahead and axolotl questions

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

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

mujoco-py. MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.

PanoGen. Code and Data for Paper: PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigation

viper_rl. Using advances in generative modeling to learn reward functions from unlabeled videos.

atari-py. A packaged and slightly-modified version of https://github.com/bbitmaster/ale_python_interface

DrawingSpinUp. (SIGGRAPH Asia 2024) This is the official PyTorch implementation of SIGGRAPH Asia 2024 paper: DrawingSpinUp: 3D Animation from Single Character Drawings

DepthCrafter. [CVPR 2025 Highlight] DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos

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

Awesome-Robotics-3D. A curated list of 3D Vision papers relating to Robotics domain in the era of large models i.e. LLMs/VLMs, inspired by awesome-computer-vision, including papers, codes, and related websites

dl-engineer-guidebook. 深度学习工程师生存指南

ModernRobotics. Modern Robotics: Mechanics, Planning, and Control Code Library --- The primary purpose of the provided software is to be easy to read and educational, reinforcing the concepts in the book. The code is optimized neither for efficiency nor robustness.

puppeteer. Code for "Hierarchical World Models as Visual Whole-Body Humanoid Controllers"

easy-rl. 强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/

awesome-reinforcement-learning-zh. 中文整理的强化学习资料（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.

LLM101n. LLM101n: Let's build a Storyteller

behavior-vision-suite.github.io. CSS

infinigen. Infinite Photorealistic Worlds using Procedural Generation

MoE-Adapters4CL. Code for paper "MoE-Adapters" CVPR2024 and "MoE-Adapters++" TPAMI2025

lightplane. Lightplane implements a highly memory-efficient differentiable radiance field renderer, and a module for unprojecting features from images to 3D grids.

DriveAGI. [CVPR 2024 Highlight] GenAD: Generalized Predictive Model for Autonomous Driving

DreamView. (ECCV 2024) Official implementation of Paper ''DreamView: Injecting View-specific Text Guidance into Text-to-3D Generation''

grok-1. Grok open release

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

awesome-tips.

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

objaverse_filter. naive filter of objaverse

OLMo. Modeling, training, eval, and inference code for OLMo

awesome-3d-diffusion. A collection of papers on diffusion models for 3D generation.

stable-dreamfusion. Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

PointLLM. [ECCV 2024 Best Paper Candidate & TPAMI 2025] PointLLM: Empowering Large Language Models to Understand Point Clouds

mamba. Mamba SSM architecture

mamba.py. A simple and efficient Mamba implementation in pure PyTorch and MLX.

WonderJourney. Python

GPTs. leaked prompts of GPTs

Apple-Silicon-Guide. Apple Silicon Guide. Learn all about the A17 Pro, A16 Bionic, R1, M1-series, M2-series, and M3-series chips. Along with all the Devices, Operating Systems, Tools, Gaming, and Software that Apple Silicon powers.

consistencydecoder. Consistency Distilled Diff VAE

MixCon3D. [CVPR 2024] The official implementation of paper "Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training"

Wonder3D. Single Image to 3D using Cross-Domain Diffusion for 3D Generation

Awesome-Anything. General AI methods for Anything: AnyObject, AnyGeneration, AnyModel, AnyTask, AnyX

awesome-instruction-learning. Papers and Datasets on Instruction Tuning and Following. ✨✨✨

ml-visuals. 🎨 ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.

opencsapp.github.io. Open CS Application | 开源CS申请

Uni3D. [ICLR'24 Spotlight] Uni3D: 3D Visual Representation from BAAI

DiT-3D. 🔥🔥🔥Official Codebase of "DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation"

PointCLIP_V2. [ICCV 2023] PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning

PointCloudDatasets. 3D point cloud datasets in HDF5 format, containing uniformly sampled 2048 points per shape.

MVTN. pytorch implementation of the ICCV'21 paper "MVTN: Multi-View Transformation Network for 3D Shape Recognition"

objaverse-xl. 🪐 Objaverse-XL is a Universe of 10M+ 3D Objects. Contains API Scripts for Downloading and Processing!

objaverse. Python

objaverse-rendering. 📷 Scripts for rendering Objaverse

pytorch. Tensors and Dynamic neural networks in Python with strong GPU acceleration

dgl. Python package built to ease deep learning on graph, on top of existing DL frameworks.

tuning_playbook. A playbook for systematically maximizing the performance of deep learning models.

METER. METER: A Multimodal End-to-end TransformER Framework

academicpages.github.io. Github Pages template based upon HTML and Markdown for personal, portfolio-based websites.

3D-LLM. Code for 3D-LLM: Injecting the 3D World into Large Language Models

llm-attacks. Universal and Transferable Attacks on Aligned Language Models

ReSTE. Official implementation of Rectified Straight Through Estimator (ReSTE).

RandBox. [ICCV 2023] PyTorch implementation of RandBox

point-e. Point cloud diffusion for 3D model synthesis

Semantic-SAM. [ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"

accelerate. 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

xla. Enabling PyTorch on XLA Devices (e.g. Google TPU)

awesome-point-cloud-analysis-2023. A list of papers and datasets about point cloud analysis (processing) since 2017. Update every day!

Summer2027-Internships. Summer 2026 software engineering, data science, AI, quant, product management, and hardware internship postings. Updated daily by Simplify and Pitt CSC.

grounded-segment-any-parts. Grounded Segment Anything: From Objects to Parts

VLPart. [ICCV2023] VLPart: Going Denser with Open-Vocabulary Part Segmentation

MinkowskiEngine. Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors

open_flamingo. An open-source framework for training large multimodal models.

OpenShape_code. official code of “OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding”

Cap3D. [NeurIPS 2023] Scalable 3D Captioning with Pretrained Models

ULIP. Python

stanford-shapenet-renderer. Scripts for batch rendering models using Blender. Tested with models from stanfords shapenet library.

OmniObject3D. [ CVPR 2023 Award Candidate ] OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation

jax. Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

shap-e. Generate 3D objects conditioned on text or images

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

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

open_clip. An open source implementation of CLIP.

flax. Flax is a neural network library for JAX that is designed for flexibility.

GroundingDINO. [ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

MiniGPT-4. Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

x-clip. A concise but complete implementation of CLIP with various experimental improvements from recent papers

awesome-computer-vision. A curated list of awesome computer vision resources

Image2Paragraph. [Image 2 Text Para] Transform Image into Unique Paragraph with ChatGPT, BLIP2, OFA, GRIT, Segment Anything, ControlNet.