🌴
Highlights
Starred repositories
CTF challenges designed and implemented in machine learning applications
[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling
The BusTub Relational Database Management System (Educational)
A lightweight, powerful framework for multi-agent workflows
Apple Silicon devices emulated on QEMU, currently only iPhone 11.
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
Vector (and Scalar) Quantization, in Pytorch
Official Implementation for STAG4D: Spatial-Temporal Anchored Generative 4D Gaussians
(CVPR 2025) Code of "Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models"
[CVPR 2024] EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion
Six Degrees of Domain Admin
[AAAI 2025🔥] Official implementation of Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle
Bringing Characters to Life with Computer Brains in Unity
CTF Archives: Collection of CTF Challenges.
A capture-the-flag exercise based on data analysis challenges
verl: Volcano Engine Reinforcement Learning for LLMs
Get started with building Fullstack Agents using Gemini 2.5 and LangGraph
KAG is a logical form-guided reasoning and retrieval framework based on OpenSPG engine and LLMs. It is used to build logical reasoning and factual Q&A solutions for professional domain knowledge ba…
The Cursor for Designers • An Open-Source Visual Vibecoding Editor • Visually build, style, and edit your React App with AI
Code release for NeRF (Neural Radiance Fields)
The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.
Official implementation of the paper: "FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models"
Next Generation Experimental Tracking for Machine Learning Operations
official repo for Asyrp : Diffusion Models already have a Semantic Latent Space (ICLR2023)
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Official code for 4Diffusion: Multi-view Video Diffusion Model for 4D Generation.
A research prototype of a human-centered web agent
Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.