ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…

收集所有"语音转文字"工具

Rediscover your social memories with local, AI-powered analysis. 本地化的聊天记录分析工具，通过 AI Agent 回顾你的社交记忆。

Easy Data Preparation with latest LLMs-based Operators and Pipelines.

VisJudgeBench: A comprehensive benchmark for aesthetics and quality assessment of visualizations, featuring 3,090 expert-annotated samples with six-dimensional quality scores.

🥢像老乡鸡🐔那样做饭。主要部分于2024年完工，非老乡鸡官方仓库。文字来自《老乡鸡菜品溯源报告》，并做归纳、编辑与整理。CookLikeHOC.

MarkLLM: An Open-Source Toolkit for LLM Watermarking.（EMNLP 2024 System Demonstration)

2025年程序员找工作求职最新总结，学生阶段的困境解决，从简历到面试的全方位解析，从实习到全职的学习规划，就业必备技能与资源推荐。

mcts-simple is a Python3 library that implements Monte Carlo Tree Search and its variants to solve a host of problems, most commonly for reinforcement learning.

A large-scale curated dataset of Visual.ly infographics with metadata and additional crowdsourced annotations for research applications in computer vision and natural language processing.

bilibili video course src code

🚀🀄️ A fast and strong AI for riichi mahjong, powered by Rust and deep reinforcement learning.

LLM101n: Let's build a Storyteller

每天阅读过的论文的简要笔记

MarkLLM: An Open-Source Toolkit for LLM Watermarking.

EPFL MATH-517 course materials 2022/23

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

A curated list of recent and past chart understanding work based on our IEEE TKDE survey paper: From Pixels to Insights: A Survey on Automatic Chart Understanding in the Era of Large Foundation Mod…

Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型

This is a sparse iterative parallel linear solver I developed during my PhD. The solver works by splitting the matrix into blocks which are then solved in parallel. The solver assumes the input mat…

Example models using DeepSpeed