Stars
A curated collection of papers and resources on On-Policy Distillation for Large Language Models.
STAR: Similarity-guided Teacher-Assisted Refinement for Super-Tiny Function Calling Models
AI agents running research on single-GPU nanochat training automatically
[browser-agent] Never send a human to do a machine's job.
Official repository for the paper "LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code"
Reference code for the Meta-Harness paper.
🌟100+ 原创 LLM / RL 原理图📚，《大模型算法》作者巨献！💥（100+ LLM/RL Algorithm Maps ）
Minimal and readable coding agent harness implementation in Python to explain the core components of coding agents.
The agent that grows with you
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
Collaboration infrastructure for AI coding agents | AI 编程代理的协作基础设施
[CVPR 2023] DepGraph: Towards Any Structural Pruning; LLMs, Vision Foundation Models, etc.
原汁原昧 Claude Code 可运行,可构建, 可调试版; 生产级工程化, 企业级可靠性; 安全无毒, 内存泄露修复
LiteRT-LM is Google's production-ready, high-performance, open-source inference framework for deploying Large Language Models on edge devices.
🤖 The analysis of Claude Code
The simplest, fastest repository for training/finetuning medium-sized GPTs.
[CVPR2026]We present FlashPortrait, an end-to-end video diffusion transformer capable of synthesizing ID-preserving, infinite-length videos while achieving up to 6$\times$ acceleration in inference…
The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞
[CVPR 2026] Official implementation of VLM-Grounded Online RL for Compositional Multi-Subject Video Generation
MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.
HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation
Astro template to help you build a website for your research paper, based on the Nerfies project page
[CVPR 2026] Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models.
mobilenetv3 with pytorch，provide pre-train model
[ECCV 2024] ShareGPT4V: Improving Large Multi-modal Models with Better Captions
A curated collection of fun and creative examples generated with Nano Banana & Nano Banana Pro🍌, Gemini-2.5-flash-image based model. We also release Nano-consistent-150K openly to support the commu…
📖 This is a repository for organizing papers, codes and other resources related to Visual Reinforcement Learning.