Stars
Lightweight and Scalable Post-training: The Ray-Free, Debug-Friendly Alignment Stack with Megatron-native simplicity.
【CVPR 26 Findings】This repo is the official implementation for "Learning by Neighbor-Aware Semantics, Deciding by Open-form Flows: Towards Robust Zero-Shot Skeleton Action Recognition" in CVPR 2026…
LLM Wiki is a cross-platform desktop application that turns your documents into an organized, interlinked knowledge base — automatically. Instead of traditional RAG (retrieve-and-answer from scratc…
[ECCV 2026] VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model
VL-JEPA (Vision-Language Joint Embedding Predictive Architecture) in MLX
📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程
🍳 Omelette: AI-Powered Scientific Literature Lifecycle Management
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows
基于大模型的视频监控危险行为检测系统，集成YOLOv8、GPT-4V等视觉和多模态AI模型，提供高精度危险行为识别、场景理解和智能告警分析。
[ICML26] Distribution Matching Variational AutoEncoder (DMVAE)
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程
Chat-甄嬛是利用《甄嬛传》剧本中所有关于甄嬛的台词和语句，基于ChatGLM2进行LoRA微调得到的模仿甄嬛语气的聊天语言模型。
你管这破玩意叫操作系统源码 — 像小说一样品读 Linux 0.11 核心代码
Simple implementations of NLP models. Tutorials are written in Chinese on my website https://mofanpy.com
Pytorch implementations of various Deep NLP models in cs-224n(Stanford Univ)
复盘所有NLP比赛的TOP方案，只关注NLP比赛，持续更新中！
《Python深度学习》书籍代码