Xinyu Wang

jlens-qwen36. J-space / Jacobian-lens visualizer for Qwen3.6-27B (4-bit) on Apple Silicon, ported to Apple MLX

harness-engineering. Harness Engineering 学习指南 — 从概念理解到独立实践的深度学习档案

open-design. 🎨 The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, slides, images & video — real files, HTML/PDF/PPTX/MP4 export. 🤖 Claude Code / Codex / Cursor / Gemini / OpenCode / Qwen & 20+ CLIs via BYOK.

TriEx. Jupyter Notebook

Text-in-the-Dark. Text in the Dark dataset. The first extremely low light text dataset based on SID and LOL datasets with a total of 3,075 images and 59,975 texts annotated.

eidetic-memory. Own eidetic-memory like Sheldon

awesome-design-md. A collection of DESIGN.md files analysis by popular brand design systems. Drop one into your project and let coding agents generate a matching UI.

rembg. Rembg is a tool to remove images background

AWESOME-OCR-LLM. OCR in the Era of Large Language Models

Open-AutoGLM. An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone

sam-3d-objects. SAM 3D Objects

DeepSeek-OCR. Contexts Optical Compression

SASRec. SASRec: Self-Attentive Sequential Recommendation

Agent4Rec. [SIGIR 2024 perspective] The implementation of paper "On Generative Agents in Recommendation"

nanochat. The best ChatGPT that $100 can buy.

AlphaOracle. [Innovation 2026] Oracle bone script decipherment via human-workflow-inspired deep learning

tinker-cookbook. Post-training with Tinker

Awesome-DLMs. The official GitHub repo for the survey paper "A Survey on Diffusion Language Models".

do-not-answer. Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs

colors. 科研绘图配色推荐器

MiniMax-M1. MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.

rlcard. Reinforcement Learning / AI Bots in Card (Poker) Games - Blackjack, Leduc, Texas, DouDizhu, Mahjong, UNO.

json_repair. Repair malformed JSON from LLMs, APIs, logs, and user input in Python.

MultimodalOCR. On the Hidden Mystery of OCR in Large Multimodal Models (OCRBench)

PettingZoo. A standard API for multi-agent reinforcement learning environments, with popular reference environments and related utilities

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

Office-PowerPoint-MCP-Server. A MCP (Model Context Protocol) server for PowerPoint manipulation using python-pptx. This server provides tools for creating, editing, and manipulating PowerPoint presentations through the MCP protocol.

onlook. The Cursor for Designers • An Open-Source AI-First Design tool • Visually build, style, and edit your React App with AI

MinerU. Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

MonkeyOCR. A lightweight LMM-based Document Parsing Model

Evaluation_Code. Python

ICEdit. [NeurIPS 2025] Image editing is worth a single LoRA! 0.1% training data for fantastic image editing! Surpasses GPT-4o in ID persistence~ MoE ckpt released! Only 4GB VRAM is enough to run!

minimind. 🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!

browser-use. 🌐 Make websites accessible for AI agents. Automate tasks online with ease.

SpatialLM. [NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling

SnakeBench. Python

LVLM-Playground. [ICLR2025] Are Large Vision Language Models Good Game Players?

Olares. Olares: An Open-Source Personal Cloud to Reclaim Your Data

LLMs-from-scratch. Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

LLM101n. LLM101n: Let's build a Storyteller

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

HUST-OBC. Oracle Bone Script data collected by VLRLab of HUST

Open-Oracle. AI-assisted Deciphering Oracle Bone Script

flux. Official inference repo for FLUX.1 models

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

VLN-HAMT. Official implementation of History Aware Multimodal Transformer for Vision-and-Language Navigation (NeurIPS'21).

vllm. A high-throughput and memory-efficient inference and serving engine for LLMs

lmdeploy. LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

graphrag. A modular graph-based Retrieval-Augmented Generation (RAG) system

LLaVA-NeXT. Python

OBSD. Deciphering Oracle Bone Language with Diffusion Models (ACL 2024 Best Paper)

tiktoken. tiktoken is a fast BPE tokeniser for use with OpenAI's models.

DeepLearningFlappyBird. Flappy Bird hack using Deep Reinforcement Learning (Deep Q-learning).

ml-ferret. Python

StoryDiffusion. Accepted as [NeurIPS 2024] Spotlight Presentation Paper

VimTS. VimTS: A Unified Video and Image Text Spotter

LEGENT. Open Platform for Embodied Agents

xtuner. A Next-Generation Training Engine Built for Ultra-Large MoE Models

Groma. [ECCV2024] Grounded Multimodal Large Language Model with Localized Visual Tokenization

llama3. The official Meta Llama 3 GitHub site

MGM. Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

open-webui. User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Qwen-VL. The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.

Open-Sora-Plan. This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

public-apis. A collective list of free APIs

ModaVerse. [CVPR2024] ModaVerse: Efficiently Transforming Modalities with LLMs

grok-1. Grok open release

open-instruct. AllenAI's post-training codebase

AppAgent. AppAgent: Multimodal Agents as Smartphone Users, an LLM-based multimodal agent framework designed to operate smartphone apps.

lagent. A lightweight framework for building LLM-based agents

Depth-Anything. [CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

Chinese-Names-Corpus. 中文人名语料库。人名生成器。中文姓名,姓氏,名字,称呼,日本人名,翻译人名,英文人名。可用于中文分词、人名实体识别。

Attack-Bard. Python

ml-for-ancient-languages. Machine Learning for Ancient Languages

awesome-instruction-datasets. A collection of awesome-prompt-datasets, awesome-instruction-dataset, to train ChatLLM such as chatgpt 收录各种各样的指令数据集, 用于训练 ChatLLM 模型。

LESS. [ICML 2024] LESS: Selecting Influential Data for Targeted Instruction Tuning

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

habitat-sim. A flexible, high-performance 3D simulator for Embodied AI research.

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

ICText-AGCL. ICText dataset. The largest dataset for text detection and recognition on integrated circuits with a total of 10,000 images and 100,152 characters annotated.

Monkey. Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models (CVPR 2024 Highlight)

ChatGLM-6B. ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

PokemonRedExperiments. Playing Pokemon Red with Reinforcement Learning

Medusa. Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

pix2video. Code for the paper "Pix2Video: Video Editing using Image Diffusion"

AudioLDM. AudioLDM: Generate speech, sound effects, music and beyond, with text.

OIR. [ICLR 2024] Official PyTorch/Diffusers implementation of "Object-aware Inversion and Reassembly for Image Editing"

i-Code. Jupyter Notebook

llama-cookbook. Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services

LongLoRA. Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)

bubogpt. BuboGPT: Enabling Visual Grounding in Multi-Modal LLMs

Ask-Anything. [CVPR2024 Highlight][VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.

streaming-llm. [ICLR 2024] Efficient Streaming Language Models with Attention Sinks

efficient-stable-diffusion.

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

SPTSv2. The official implementation of SPTS v2: Single-Point Text Spotting

LLaMA2-Accessory. An Open-source Toolkit for LLM Development

gill. 🐟 Code and models for the NeurIPS 2023 paper "Generating Images with Multimodal Language Models".

LLaMA-Adapter. [ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

NExT-GPT. Code and models for ICML 2024 paper, NExT-GPT: Any-to-Any Multimodal Large Language Model