Lists (2)
Starred repositories
🎙️ 「大模型」从0训练0.1B能听能说能看的全模态Omni模型！A 0.1B Omni model trained from scratch, capable of listening, speaking, and seeing!
[ACL 2026] Hard to Read, Easy to Jailbreak: How Visual Degradation Bypasses MLLM Safety Alignment
🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.
This code implements the algorithm of FIPO, a value-free RL recipe for eliciting deeper reasoning from a clean base model.
Claude Code Skill for PyTRIO SDK — teach AI coding agents to write correct remote LLM training & inference code
A bag of training monitor skills for model training.
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
哈喽！龙虾 🙋♀️ Adopt from scratch and build your first claw 🦞 来领养你的第一只龙虾！
OpenClaw-RL: Train any agent simply by talking
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepowe…
AI agents running research on single-GPU nanochat training automatically
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
[ICLR 2026] Tree Search for LLM Agent Reinforcement Learning
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
⏰ Agenticly track worldwide conference deadlines (Website, Python Cli, Wechat Applet)
Twinkle✨: Training workbench to make your model glow.
Model Context Protocol (MCP) support for SwanLab
Isaac Lab API, powered by MuJoCo-Warp, for RL and robotics research
ClickHouse® is a real-time analytics database management system
An LLM training framework built from the ground up, featuring a custom BumbleBee architecture and end-to-end support for multiple open-source models across Pretraining → SFT → RLHF/DPO.
💻 vibe coding 2026 | Your first modern Coding course beginners to master step by step.
A unified framework for easy reinforcement learning in Flow-Matching models
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
Efficient Triton Kernels for LLM Training
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…