Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

轻量级大语言模型MiniMind的源码解读，包含tokenizer、RoPE、MoE、KV Cache、pretraining、SFT、LoRA、DPO等完整流程

🚀 「大模型」1小时从0训练67M参数的视觉多模态VLM！🌏 Train a 67M-parameter VLM from scratch in just 1 hours!

🚀🚀 「大模型」2小时完全从0训练64M的小参数GPT！🌏 Train a 64M-parameter GPT from scratch in just 2h!

Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment

基于 Playwright 和AI实现的闲鱼多任务实时/定时监控与智能分析系统，配备了功能完善的后台管理UI。帮助用户从闲鱼海量商品中，找到心仪产品。

Crack LeetCode, not only how, but also why.

Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. ACM Computing Surveys, 2026.

Let your Claude able to think

Awesome papers about generative Information Extraction (IE) using Large Language Models (LLMs)

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).

Open-Pandora: On-the-fly Control Video Generation

Improving Pseudo Labels with Global-Local Denoising Framework for Cross-lingual Named Entity Recognition (IJCAI 2024)