Stars
AHN: Artificial Hippocampus Networks for Efficient Long-Context Modeling
A list of goodies for your Supernote tablet. Sharing awesome tips and tricks.
A self-hosted dashboard that puts all your feeds in one place
"DeepCode: Open Agentic Coding (Paper2Code & Text2Web & Text2Backend)"
开源白板工具（SaaS），一体化白板，包含思维导图、流程图、自由画等。All in one open-source whiteboard tool with mind, flowchart, freehand and etc.
A minimal tensor processing unit (TPU), inspired by Google's TPU V2 and V1
一个专注于 NAS 和 Docker 部署的开源项目合集，覆盖 AI、开发、数据管理、多媒体、运维等场景，提供一键式部署指南和实用教程，让 NAS 变身全能生产力工具！
📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools lik…
Learning Deep Representations of Data Distributions
A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.
Zotero MCP: Connects your Zotero research library with Claude and other AI assistants via the Model Context Protocol to discuss papers, get summaries, analyze citations, and more.
The official repo for LIFT: Language-Image Alignment with Fixed Text Encoders
MAGI-1: Autoregressive Video Generation at Scale
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Easy no-frills Pytorch implementations of common abstractions for simple diffusion models.
Optimizing the way of contrastive learning in PyTorch-DDP(DistributedDataParallel) multi-GPU training
When do we not need larger vision models?
A tool to fix damaged cover of Kindle ebook.
⛷ Lightweight Markdown app to help you write great sentences. 轻灵的 Markdown 笔记本伴你写出妙言
程序员延寿指南 | A programmer's guide to live longer
Official code for the paper "Task2Vec: Task Embedding for Meta-Learning" (https://arxiv.org/abs/1902.03545, ICCV 2019)
Official Implementation of Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction (2020)
Fast and Easy Infinite Neural Networks in Python