Wen Lai

academic-research-skills-codex. Codex-native Academic Research Skills suite for human-in-the-loop academic research workflows

ResearchStudio. ResearchStudio: Our AI co-author, from research problem to final publication.

free-vpn-subscriptions. Free Clash, sing-box, and V2Ray subscription feed with live node status and setup guides

Abstain-R1. Python

academic-research-skills. Academic Research Skills for Claude Code: research → write → review → revise → finalize

thuthesis. LaTeX Thesis Template for Tsinghua University

DiffScore. DiffScore: Text Evaluation Beyond Autoregressive Likelihood

factnet. FactNet: A Billion-Scale Knowledge Graph for Multilingual Factual Grounding

scientific-agent-skills. Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 170,000+ scientists worldwide. 158 ready-to-use skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.

Awesome-Auto-Research-Tools. A curated collection of automated research tools, covering literature search, paper reading, experiment management, and code generation to help researchers accelerate their workflow.

daily-arXiv-ai-enhanced. Automatically crawl arXiv papers daily and summarize them using AI. Illustrating them using GitHub Pages.

research-plugins. 350+ academic research skills, MCP configs, and plugins for Research-Claw and AI agents

EurekaClaw. The official repo of EurekaClaw

lumi. Lumi uses AI-powered features to help you read arXiv papers.

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

EvoScientist. 🔬 Harness Vibe Research with Self-evolving AI Scientists

AI-Researcher. [NeurIPS2025] "AI-Researcher: Autonomous Scientific Innovation" -- A production-ready version: https://novix.science/chat

Awesome-AI-Scientist. This is a survey of research on AI scientists, AI researchers, AI engineers, and a series of AI-driven research studies

learn-claude-code. Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

AI-Scientist-v2. The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

ECC. The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

autoresearch. AI agents running research on single-GPU nanochat training automatically

wikiextractor. A tool for extracting plain text from Wikipedia dumps

LLM-KG4QA. LLM-KG4QA: Large Language Models and Knowledge Graphs for Question Answering

multi-way-llm. Code for "From Unaligned to Aligned: Scaling Multilingual LLMs with Multi-Way Parallel Corpora"

iptv-api. ⚡️IPTV直播源自动更新工具：自动采集、校验、测速并生成可播放结果，支持 M3U/TXT/API 输出、自定义频道、IPv4/IPv6、Docker、GitHub Actions、CLI 与 GUI 多端部署

AIGC-Interview-Book. 【三年面试五年模拟】AIGC/LLM/AI Agent算法工程师面试秘籍。涵盖AIGC、LLM大模型、AI Agent、具身智能、传统深度学习、自动驾驶、机器学习、计算机视觉、自然语言处理、强化学习、大数据挖掘、世界模型、元宇宙、AGI等AI行业面试笔试干货经验与核心知识。

one-small-step. 这是一个简单的技术科普教程项目，主要聚焦于解释一些有趣的，前沿的技术概念和原理。每篇文章都力求在 5 分钟内阅读完成。

MMLongBench. The official repo of the paper "MMLongBench Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly"

TED-Talks. All TED talks narratives extracted and cleaned.

sacrebleu. Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons

DCAD-2000. DCAD-2000 dataset and pipeline | www.arxiv.org/abs/2502.11546

fast_align. Simple, fast unsupervised word aligner

vllm. A high-throughput and memory-efficient inference and serving engine for LLMs

llm_interview_note. 主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

ted_talk_downloader. Easy-to-use codes for downloading transcripts for TED talks.

OpenCursor. Open-source Cursor-like AI coding agent for VS Code — agentic chat, multi-provider LLMs (OpenAI, Ollama, llama.cpp), semantic search, and MCP support

handy-ollama. 动手学Ollama，CPU玩转大模型部署，在线阅读地址：https://datawhalechina.github.io/handy-ollama/

free-llm-api-resources. A list of free LLM inference resources accessible via API.

LLMBook-zh.github.io. 《大语言模型》作者：赵鑫，李军毅，周昆，唐天一，文继荣

hyper. HTTP/2 for Python.

PROXY-List. Get PROXY List that gets updated everyday

deep-translator. A flexible free and unlimited python tool to translate between different languages in a simple way using multiple translators.

jola. Code for ICML 2025 paper | Joint Localization and Activation Editing for Low-Resource Fine-Tuning

Free-GPT4-WEB-API. Not just GPT4! Easy to use, Self-Hosted, Unlimited and Free WEB API of the latest A.I. like Gemini, DeepSeek, Claude and GPT

FActScore. A package to evaluate factuality of long-form generation. Original implementation of our EMNLP 2023 paper "FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation"

tum-dissertation-latex. Latex template for a TUM dissertation/PhD thesis

factool. FacTool: Factuality Detection in Generative AI

Lynx-hallucination-detection. Python

panlex_scraper. Scrape bilingual vocabulary data from PanLex

GENRE. Autoregressive Entity Retrieval

ecoute. Ecoute is a live transcription tool that provides real-time transcripts for both the user's microphone input (You) and the user's speakers output (Speaker) in a textbox.

long-form-factuality. Benchmarking long-form factuality in large language models. Original code for our paper "Long-form factuality in large language models".

DeepLearing-Interview-Awesome-2024. AIGC-interview/CV-interview/LLMs-interview面试问题与答案集合仓，同时包含工作和科研过程中的新想法、新问题、新资源与新项目

LLMs_interview_notes. LLMs interview notes and answers:该仓库主要记录大模型（LLMs）算法工程师相关的面试题和参考答案

LLMs_interview_notes. 该仓库主要记录 大模型（LLMs） 算法工程师相关的面试题

LLMForEverybody. 每个人都能看懂的大模型知识分享，LLMs春/秋招大模型面试前必看，让你和面试官侃侃而谈

awesome-github-profile-readme. 😎 A curated list of awesome GitHub Profile which updates in real time

colors. 科研绘图配色推荐器

factCC. Resources for the "Evaluating the Factual Consistency of Abstractive Text Summarization" paper

AI-Scientist. The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

storm. An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

promptsource. Toolkit for creating, sharing and using natural language prompts.

GEM-metrics. Automatic metrics for GEM tasks

spatten. [HPCA'21] SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning

nlp-phd-global-equality. A repo for open resources & information for people to succeed in PhD in CS & career in AI / NLP

the-story-of-heads. This is a repository with the code for the ACL 2019 paper "Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned" and the ACL 2021 paper "Analyzing Source and Target Contributions to NMT Predictions".

awesome-LLM-resources. 🧑‍🚀 全世界最好的LLM资料总结（多模态生成、Agent、辅助编程、AI审稿、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型） | Summary of the world's best LLM resources.

ml-mkqa. We introduce MKQA, an open-domain question answering evaluation set comprising 10k question-answer pairs aligned across 26 typologically diverse languages (260k question-answer pairs in total). The goal of this dataset is to provide a challenging benchmark for question answering quality across a wide set of languages. Please refer to our paper for details, MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering

deduplicate-text-datasets. Rust

datatrove. Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

DeepClustering. Methods and Implements of Deep Clustering

text-dedup. All-in-one text de-duplication

corpuscrawler. Crawler for linguistic corpora

nlp_course. YSDA course in Natural Language Processing

lo-fit. LoFiT: Localized Fine-tuning on LLM Representations

awesome-multimodal-in-medical-imaging. A collection of resources on applications of multi-modal learning in medical imaging.

Awesome-Multimodal-Large-Language-Models. :sparkles::sparkles:Latest Advances on Multimodal Large Language Models

awesome-hallucination-detection. List of papers on hallucination detection in LLMs.

SAM-Med2D. Official implementation of SAM-Med2D

pyvene. Stanford NLP Python library for understanding and improving PyTorch models via interventions

pyreft. Stanford NLP Python library for Representation Finetuning (ReFT)

IMIS-Bench. Interactive Medical Image Segmentation: A Benchmark Dataset and Baseline

sNeuron-TST. EMNLP 2024 | Style-Specific Neurons for Steering LLMs in Text Style Transfer

data_tooling. Tools for managing datasets for governance and training.

vlm-hallucinations. [ICLR '25] Official Pytorch implementation of "Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations"

mat. Python code for the "Jump to Conclusions" paper

pythia. The hub for EleutherAI's work on interpretability and learning dynamics

tuned-lens. Tools for understanding how transformer predictions are built layer-by-layer

data-selection-survey. A Survey on Data Selection for Language Models

sacremoses. Python port of Moses tokenizer, truecaser and normalizer

PAI. [ECCV 2024] Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs

CSPR. Code of paper 'Advancing 3D Medical Image Analysis with Variable Dimension Transform based Supervised 3D Pre-training'

MedYOLO. A 3D bounding box detection model for medical data.

nnDetection. nnDetection is a self-configuring framework for 3D (volumetric) medical object detection which can be applied to new data sets without manual intervention. It includes guides for 12 data sets that were used to develop and evaluate the performance of the proposed method.

medicaldetectiontoolkit. The Medical Detection Toolkit contains 2D + 3D implementations of prevalent object detectors such as Mask R-CNN, Retina Net, Retina U-Net, as well as a training and inference framework focused on dealing with medical images.

CDAC. Code for "CDAC: Cross-domain Attention Consistency in Transformer for Domain Adaptive Semantic Segmentation" at ICCV 2023.

chinese-opensource-mirror-site. Mirror clone of https://gitee.com/gsls200808/chinese-opensource-mirror-site as the README.md on that repository has been filtered.

hallucination-leaderboard. Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents

FlexAttention. [ECCV 2024] FlexAttention for Efficient High-Resolution Vision-Language Models

multimodal-meta-learn. [ICLR 2023] Official code repository for "Meta Learning to Bridge Vision and Language Models for Multimodal Few-Shot Learning"

MedAdapter. [EMNLP'24] MedAdapter: Efficient Test-Time Adaptation of Large Language Models Towards Medical Reasoning

TDA. [CVPR 2024] Official Repository for "Efficient Test-Time Adaptation of Vision-Language Models"

few-shot-hypernets-public. Jupyter Notebook

Generalizable-Mixture-of-Experts. GMoE could be the next backbone model for many kinds of generalization task.

MoE-LLaVA. 【TMM 2025🔥】 Mixture-of-Experts for Large Vision-Language Models

VLM_survey. Collection of AWESOME vision-language models for vision tasks

0-shot-llm-vision. This repository contains the code for our CVPR 2024 paper,

codeforces-go. 算法竞赛模板库 by 灵茶山艾府 💭💡🎈

bpc_chrome_support.

cld3. C++

cldr-localenames-modern. Archived, see https://github.com/unicode-org/cldr-json.git

L1-Refinement. Code for "Cross-Lingual Word Embedding Refinement by ℓ1 Norm Optimisation" (NAACL 2021)

VLM-Visualizer. Visualizing the attention of vision-language models

GlotLID. [EMNLP 2023] 💬 Language Identification with Support for More Than 2000 Labels

clip-retrieval. Easily compute clip embeddings and build a clip retrieval system with them

Awesome-Medical-Large-Language-Models. Curated papers on Large Language Models in Healthcare and Medical domain

Awesome-LLMs-Datasets. Summarize existing representative LLMs text datasets.

rustdesk. An open-source remote desktop application designed for self-hosting, as an alternative to TeamViewer.

postgres. Mirror of the official PostgreSQL GIT repository. Note that this is just a *mirror* - we don't work with pull requests on github. To contribute, please see https://wiki.postgresql.org/wiki/Submitting_a_Patch

LLaVA. [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

coco-caption. Jupyter Notebook

caption_evaluation. Python

ai-for-grant-writing. A curated list of resources for using LLMs to develop more competitive grant applications.

image-caption-metrics. a py3 lib for NLP & image-caption metrics : BLEU METEOR CIDEr ROUGE SPICE WMD

LLMs-from-scratch. Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

DeepSeek-LLM. DeepSeek LLM: Let there be answers

NeuroRA. A Python Toolbox for Multimode Neural Data Representation Analysis - A Representational Analysis Toolbox for Neuroscience, including Representational Similarity Analysis (RSA), & Inter-Subject Correlation (ISC)

dclm. DataComp for Language Models

Llama-Chinese. Llama中文社区，实时汇总最新Llama学习资料，构建最好的中文Llama大模型开源生态，完全开源可商用

ColossalAI. Making large AI models cheaper, faster and more accessible

unsloth. Unsloth is a local UI for training and running Gemma 4, Qwen3.6, DeepSeek, Kimi, GLM and other models.

llama-cookbook. Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama model family and using them on various provider services

axolotl. Go ahead and axolotl questions

llm-datasets. Curated list of datasets and tools for post-training.

Llama-X. Open Academic Research on Improving LLaMA to SOTA LLM

OLMo. Modeling, training, eval, and inference code for OLMo

text_style_transfer_transformer. Extracting style with pretrained language model

ood_coverage. [ICLR 2024 Spotlight] Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalization

mergekit. Tools for merging pretrained large language models.

fucking-algorithm. Crack LeetCode, not only how, but also why.

iptv-m3u-maker. IPTV 国内+国外 电视台直播源m3u文件, 收集&汇总&本地源脚本

tencent-ml-images. Largest multi-label image database; ResNet-101 model; 80.73% top-1 acc on ImageNet

IPTV. 每天自动更新IPTV直播源，支持IPV4/IPV6双栈访问！自定义频道，高质量直播源，❌不含有广告。Automatically update IPTV live streaming sources every day, supporting IPV4/IPV6 dual stack access! Custom channels, high-quality live streaming sources, ❌ Does not contain advertisements.

Tvlist-awesome-m3u-m3u8. 直播源相关资源汇总 📺 💯 IPTV、M3U —— 勤洗手、戴口罩，祝愿所有人百毒不侵

live. ✯ 可直连访问的电视/广播图标库与相关工具项目 ✯ 🔕 永久免费 直连访问 完整开源 不断完善的台标 支持IPv4/IPv6双栈访问 🔕

IPTV. IPTV直播源抓取 自动整合hao趣网直播源+TVBox直播源+其他网上直播源 择取分辨率、速度最佳视频流 定期更新

xlm-t. Repository for XLM-T, a framework for evaluating multilingual language models on Twitter data

textdetox_clef_2024. Human annotation and evaluation results materials for the TextDetox @ CLEF-2024 Shared Task

DomainBed. DomainBed is a suite to test domain generalization algorithms

BLIP. PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

ttt-lm-pytorch. Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States

NICO-plus. The Official Repository for CVPR2023 Paper "NICO++: Towards Better Benchmarking for Domain Generalization".

py-googletrans. (unofficial) Googletrans: Free and Unlimited Google translate API for Python. Translates totally free of charge.

OPUS-translator. Translation demonstrator

nllb200translator. Python web interface for the Facebook NLLB-200 language model

nllb-serve. Meta's "No Language Left Behind" models served as web app and REST API

NLP-Lab. This repository contains the programs that I worked out in Natural Language Processing lab

ml-visuals. 🎨 ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.

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

paradetox. Data and info for the paper "ParaDetox: Text Detoxification with Parallel Data"

llm2vec. Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

pudb. Full-screen console debugger for Python

deq. [NeurIPS'19] Deep Equilibrium Models

style-vectors-for-steering-llms. Code release for the paper "Style Vectors for Steering Generative Large Language Models", accepted to the Findings of the EACL 2024.

AlgoNote. ⛽️「算法通关手册」：从零开始的「算法与数据结构」学习教程，200 道「算法面试热门题目」，1000+ 道「LeetCode 题目解析」，持续更新中！

grok-1. Grok open release

args. Python

CrossConST-SR. Code for EMNLP 2023 industry track paper "Learning Multilingual Sentence Representations with Cross-lingual Consistency Regularization"

wikdict-gen. Generation of bilingual dictionaries from Wiktionary/dbnary data for the WikDict project

Awesome-LLM-MT.

LLM-MT-Eval. {DeepL, Google, WMT-Best, davinci-003, turbo, gpt-4} × {En-De, En-Cs, En-Ru, En-Zh, De-Fr, En-Ja, Uk-En, Uk-Cs, En-Hr, En-Ha, En-Is}

ContraDecode. The implementation of "Mitigating Hallucinations and Off-target Machine Translation with Source-Contrastive and Language-Contrastive Decoding"

skip-thoughts. Sent2Vec encoder and training code from the paper "Skip-Thought Vectors"

TART. TART: A plug-and-play Transformer module for task-agnostic reasoning

awesome-instruction-dataset. A collection of open-source dataset to train instruction-following LLMs (ChatGPT,LLaMA,Alpaca)

Awesome-Knowledge-Distillation-of-LLMs. This repository collects papers for "A Survey on Knowledge Distillation of Large Language Models". We break down KD into Knowledge Elicitation and Distillation Algorithms, and explore the Skill & Vertical Distillation of LLMs.

LookaheadDecoding. [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding

self-translate. Do Multilingual Language Models Think Better in English?

lm-evaluation-harness. A framework for few-shot evaluation of language models.

promptbench. A unified evaluation framework for large language models

MultilingualSIFT. MultilingualSIFT: Multilingual Supervised Instruction Fine-tuning

instruction-datasets. Datasets for Instruction Tuning of Large Language Models

awesome-instruction-datasets. A collection of awesome-prompt-datasets, awesome-instruction-dataset, to train ChatLLM such as chatgpt 收录各种各样的指令数据集, 用于训练 ChatLLM 模型。

BigTranslate. BigTranslate: Augmenting Large Language Models with Multilingual Translation Capability over 100 Languages

parallel-corpora-tools. Tools for filtering and cleaning parallel and monolingual corpora for machine translation and other natural language processing tasks.

Evaluation-of-ChatGPT. A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets.

OpenRLHF. An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

Awesome-LLMs-Evaluation-Papers. The papers are organized according to our survey: Evaluating Large Language Models: A Comprehensive Survey.

LLMTuner. 大语言模型指令调优工具（支持 FlashAttention）

Bi-ACL. Mitigating Data Imbalance and Representation Degeneration in Multilingual Machine Translation (EMNLP 2023)

LLM-Adapters. Code for our EMNLP 2023 Paper: "LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models"

llama. Inference code for Llama models

self-correction-llm-papers. This is a collection of research papers for Self-Correcting Large Language Models with Automated Feedback.

SwiftSage. SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks

imitation_learning_from_language_feedback. This repository contains some of the code used in the paper "Training Language Models with Langauge Feedback at Scale"

awesome-test-time-adaptation. Collection of awesome test-time (domain/batch/instance) adaptation methods

easy-rl. 强化学习中文教程（蘑菇书🍄），在线阅读地址：https://datawhalechina.github.io/easy-rl/

Thought-Cloning. [NeurIPS '23 Spotlight] Thought Cloning: Learning to Think while Acting by Imitating Human Thinking

seamless_communication. Foundational Models for State-of-the-Art Speech and Text Translation