Stars
MAGI-2-preview: Scaling Video Generation Models Efficiently
Skills for Real Engineers. Straight from my .agents directory.
A unified framework for easy reinforcement learning in Flow-Matching models
LLaDA2.0-Uni: Understanding and Generation the World.
Phonon-aware scoring function for fast dynamical-stability ranking and reranking of generated crystal structures.
很多镜像都在国外。比如 gcr 。国内下载很慢，需要加速。致力于提供连接全世界的稳定可靠安全的容器镜像服务。
A framework for efficient model inference with omni-modality models
Enjoy the magic of Diffusion models!
一个基于nano banana pro🍌的原生AI PPT生成应用，迈向＂Vibe PPT＂; 支持上传任意模板图片，上传任意素材&智能解析，一句话/大纲/页面描述自动生成PPT，口头修改指定区域、一键导出可编辑ppt - An AI-native slides generator based on nano banana pro🍌
Create beautiful slides on the web using a coding agent's frontend skills
An Agentic Framework for Reflective PowerPoint Generation
Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞
350+ academic research skills, MCP configs, and plugins for Research-Claw and AI agents
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl!
The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.
The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞
Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
PhononBench is a phonon-based benchmark for large-scale dynamical stability evaluation of AI-generated crystals, featuring 100k+ structures, DFT-level MatterSim phonon calculations, and open-source…
[ICLR 2025] BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval
[ACL 2026 Main] Repo for paper "ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability"
XLeRobot: Practical Dual-Arm Mobile Home Robot for $660
Code and datasets for paper: QSpell 250K: A Large-Scale, Practical Dataset for Chinese Search Query Spell Correction
The discovery of novel functional materials with targeted properties remains a fundamental challenge in materials science. In this work, we propose InvDesFlow-AL, an active learning-based generativ…
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
Joycon-Robotics: Low-Cost, Convenient Teleoperation for One- and Two-Arm Robots