Stars
Official implementation of the paper: "MPRL: Multi-Perspective Reinforcement Learning for Enhancing Format Adherence Capability of Large Language Models" (PAKDD 2026, Full Paper & Oral).
Policy Split: Incentivizing Dual-Mode Exploration in LLM Reinforcement with Dual-Mode Entropy Regularization
Benchmarking Living-Screen-Native GUI Agents on Short-Video Platforms
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini C…
网页自动化工具，油管等视频下载，一键搬家，视频多平台发布，一键发布到tiktok、小红书、快手、抖音、油管、B站等等平台
Code for "From Context to Skills: Can Language Models Learn from Context Skillfully? "
🦞+🔬 NanoResearch: The Autonomous AI Research Assistant
Open implementation of Attention Residuals (Kimi Team, arXiv:2603.15031)
[ACL 2026 Findings] PEC-Home: Interpretation of Progressively Elliptical Commands in Smart Homes
Official implementation of "Continuous Autoregressive Language Models"
Seoul World Model: Grounding World Simulation Models in a Real-World Metropolis
"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/
🌐 Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
"ClawWork: OpenClaw as Your AI Coworker - 💰 $15K earned in 11 Hours"
"AI-Trader: 100% Fully-Automated Agent-Native Trading"
Ultra-lightweight, open-source, self-hosted personal AI agent framework in Python with WebUI, tools, memory, MCP, multi-agent workflows, automation, and chat apps
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
Give your agents the power of the Hugging Face ecosystem
Synthetic data annotation for retrieval evaluations by ZeroEntropy
Baichuan-M3 Modeling Clinical Inquiry for Reliable Medical Decision-Making
[AAAI 2026] SIFThinker: Spatially-Aware Image Focus for Visual Reasoning
A Survey of Reinforcement Learning for Large Reasoning Models