Starred repositories
Skills for writing tilelang and debugging with CUDA toolkits.
Synthetic data annotation for retrieval evaluations by ZeroEntropy
AI Agent Framework, the Pydantic way
🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.
Extract residual-stream activations and apply steering vectors (including activation oracles) to any vLLM model during inference.
Generalist and Lightweight Model for Named Entity Recognition (Extract any entity types from texts)
This is the homepage of a new book entitled "Mathematical Foundations of Reinforcement Learning."
NVIDIA AITune is an inference toolkit designed for tuning and deploying Deep Learning models with a focus on NVIDIA GPUs.
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
A Systematic Analysis and Discussion of Claude Code for Designing Today's and Future AI Agent Systems
"Paper2Slides: From Paper to Presentation in One Click"
Thirteen editorial diagram types for Claude Code. Self-contained HTML + SVG. No shadows, no Mermaid-slop.
Production-grade engineering skills for AI coding agents.
AI code reviews grounded in 12 classic engineering books — decay risk diagnostics with book citations, severity labels, and 6 analysis modes including full-sweep auto-fix
The agent that grows with you
A Claude Code skill that acts as your daily 军师 (strategic research advisor).
Home for "How To Scale Your Model", a short blog-style textbook about scaling LLMs on TPUs
[ICLR 2026] Official Implementation of Embedding-Based Context-Aware Reranker📄
[Nat. Commun.] PatCID: an open-access dataset of chemical structures in patent documents
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
Workshop: Agentic Search for Context Engineering
Wrap Gemini CLI, Antigravity, ChatGPT Codex, Claude Code, Grok Build as an OpenAI/Gemini/Claude/Codex compatible API service, allowing you to enjoy the free Gemini 3.1 Pro, GPT 5.5, Grok 4.3, Claud...
Local API emulation for CI and no-network sandboxes
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
Training library for Megatron-based models with bidirectional Hugging Face conversion capability
Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.