Yangyi Chen

ProgramBench. Can Language Models Rebuild Programs From Scratch?

SWE-bench-Live. [NeurIPS 2025 D&B] 🚀 SWE-bench Goes Live!

AMAI. Advanced Melee Artificial Intelligence Mod For Warcraft 3

skills. Public repository for Agent Skills

awesome-yangjingyuan. 杨景媛（武汉大学）事件记录。更新：杨景媛论文下载突破31万次。

PAPO. Official repo for "PAPO: Perception-Aware Policy Optimization for Multimodal Reasoning"

Agentless. Agentless🐱: an agentless approach to automatically solve software development problems

swe-rl. [NeurIPS'25] Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"

litellm. Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]

SWE-agent. SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

OpenHands. 🙌 OpenHands: AI-Driven Development

PRIOR. Public code repo for paper "Prioritizing Image-Related Tokens Enhances Vision-Language Pre-Training"

Alice. Public code repo for paper "Alice: Proactive Learning with Teacher's Demonstrations for Weak-to-Strong Generalization"

leetcode-master. 《代码随想录》LeetCode 刷题攻略：200道经典题目刷题顺序，共60w字的详细图解，视频难点剖析，50余张思维导图，支持C++，Java，Python，Go，JavaScript等多语言版本，从此算法学习不再迷茫！🔥🔥 来看看，你会发现相见恨晚！🚀

HowToCook. Programmer's guide about how to cook at home.

maze-dataset. maze datasets for investigating OOD behavior of ML systems

ray. Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

open-r1. Fully open reproduction of DeepSeek-R1

Math-Verify. Python

VLM-R1. Solve Visual Understanding with Reinforced VLMs

lmm-r1. Extend OpenRLHF to support LMM RL training for reproduction of DeepSeek-R1 on multimodal tasks.

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

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

olmocr. Toolkit for linearizing PDFs for LLM datasets/training

Awesome-RL-based-Reasoning-MLLMs. This repository provides valuable reference for researchers in the field of multimodality, please start your exploratory travel in RL-based Reasoning MLLMs!

VLMEvalKit. Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

torchtitan. A PyTorch native platform for training generative AI models

SyncMind. SyncMind for Agent Out-of-Sync

OpenOmni. (NIPS 2025) OpenOmni: Official implementation of Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-Time Self-Aware Emotional Speech Synthesis

verl. verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

ALOE. Public code repo for COLING 2025 paper "Aligning LLMs with Individual Preferences via Interaction"

img2dataset. Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

Autoregressive-Models-in-Vision-Survey. [TMLR 2025🔥] A survey for the autoregressive models in vision.

python-fire. Python Fire is a library for automatically generating command line interfaces (CLIs) from absolutely any Python object.

llm-reasoners. A library for advanced large language model reasoning

Awesome-LLM-Strawberry. A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.

datacomp. DataComp: In search of the next generation of multimodal datasets

LLM-Honesty-Survey. [2025-TMLR] A Survey on the Honesty of Large Language Models

cosmopedia. Python

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

SOLO. [TMLR] Public code repo for paper "A Single Transformer for Scalable Vision-Language Modeling"

BMPrinciples. A collection of phenomenons observed during the scaling of big foundation models, which may be developed into consensus, principles, or laws in the future

MACAROON. Public code repo for EMNLP 2024 Findings paper "MACAROON: Training Vision-Language Models To Be Your Engaged Partners"

SaySelf. Public code repo for paper "SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales"

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

s5cmd. Parallel S3 and local filesystem execution tool.

PaddleOCR. Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

conference-deadlines. :alarm_clock: AI conference deadline countdowns + Calendar overview with deadlines and conference dates.

torchtune. PyTorch native post-training library

llama3. The official Meta Llama 3 GitHub site

Speech. A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

opencompass. OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

cld3. C++

toma. Helps you write algorithms in PyTorch that adapt to the available (CUDA) memory

accelerate. 🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

Megatron-LLM. distributed trainer for LLMs

llm_debate. Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"

OpenMoE. A family of open-sourced Mixture-of-Experts (MoE) Large Language Models

code-act. Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, Heng Ji.

Awesome-LLMs-for-Video-Understanding. 🔥🔥🔥 [IEEE TCSVT] Latest Papers, Codes and Datasets on Vid-LLMs.

LM-TOAST. Source code for ACL 2023 Findings paper "Making Pre-trained Language Models both Task-solvers and Self-calibrators"

Awesome-Generalist-Robots-via-Foundation-Models. Paper list in the survey paper: Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis

Multimodal-AND-Large-Language-Models. Paper list about multimodal and large language models, only used to record papers I read in the daily arxiv for personal needs.

webarena. Code repo for "WebArena: A Realistic Web Environment for Building Autonomous Agents"

lm-polygraph. Python

R-Tuning. [NAACL 2024 Outstanding Paper] Source code for the NAACL 2024 paper entitled "R-Tuning: Instructing Large Language Models to Say 'I Don't Know'"

UnknownBench. Repo for paper: Examining LLMs' Uncertainty Expression Towards Questions Outside Parametric Knowledge

LLM-generated-text-detection. Python

trl. Train transformer language models with reinforcement learning.

alfred. ALFRED - A Benchmark for Interpreting Grounded Instructions for Everyday Tasks

CRAFT. Code for ICLR 2024 paper "CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets"

mint-bench. Official Repo for ICLR 2024 paper MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback by Xingyao Wang*, Zihan Wang*, Jiateng Liu, Yangyi Chen, Lifan Yuan, Hao Peng and Heng Ji.

llm-hallucination-survey. Reading list of hallucination in LLMs. Check out our new survey paper: "Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models"

CoTConsistency. The released data for paper "Measuring and Improving Chain-of-Thought Reasoning in Vision-Language Models".

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

maskrcnn-benchmark. Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

gdown. Google Drive public file downloader when curl/wget fails.

Long-Context. This repository contains code and tooling for the Abacus.AI LLM Context Expansion project. Also included are evaluation scripts and benchmark tasks that evaluate a model’s information retrieval capabilities with context expansion. We also include key experimental results and instructions for reproducing and building on them.

LLaMA2-Accessory. An Open-source Toolkit for LLM Development

FastChat. An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

AlignLLMHumanSurvey. Aligning Large Language Models with Human: A Survey

segment-anything. The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

webdataset. A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

ACL2023-Retrieval-LM.github.io. https://acl2023-retrieval-lm.github.io/

perspectiveapi. Perspective is an API that uses machine learning models to score the perceived impact a comment might have on a conversation. See https://developers.perspectiveapi.com for more information.

safe-rlhf. Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

peft. 🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

GPT-4-LLM. Instruction Tuning with GPT-4

Academic-project-page-template. A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/

PLMCalibration. Code for ACL 2023 paper "A Close Look into the Calibration of Pre-trained Language Models"

langchain. The agent engineering platform.

OOD_NLP. [NeurIPS 2023 D&B Track] Code and data for paper "Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evaluations".

RobTest. Source code for ACL 2023 Findings paper "From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework"

INDust. [NAACL' 25] INDust: Inductive Instructions for Large Language Models

Prompt-Engineering-Guide. 🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

LLMZoo. ⚡LLM Zoo is a project that provides data, models, and evaluation benchmark for large language models.⚡

BMTools. Tool Learning for Big Models, Open-Source Solutions of ChatGPT-Plugins

LongForm. Reverse Instructions to generate instruction tuning data with corpus examples

AutoGPT. AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

MM-REACT. Official repo for MM-REACT

the-algorithm. Source code for the X Recommendation Algorithm

DeepSpeed. DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

stanford_alpaca. Code and documentation to train Stanford's Alpaca models, and generate the data.

Instruction-Tuning-Papers. Reading list of Instruction-tuning. A trend starts from Natrural-Instruction (ACL 2022), FLAN (ICLR 2022) and T0 (ICLR 2022).

KnowledgeLifecycle. Paper list of "The Life Cycle of Knowledge in Big Language Models: A Survey"

TaskMatrix. Python

torchscale. Foundation Architecture for (M)LLMs

MultiModal_BigModels_Survey. [MIR-2023-Survey] A continuously updated paper list for multi-modal pre-trained big models

awesome-Vision-and-Language-Pre-training. Recent Advances in Vision and Language Pre-training (VLP)

unilm. Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

CVPR2026-Papers-with-Code. CVPR 2026 论文和开源项目合集

llama. Inference code for Llama models

frame-semantic-transformer. Frame Semantic Parser based on T5 and FrameNet

google-research. Google Research

OpenBackdoor. An open-source toolkit for textual backdoor attack and defense (NeurIPS 2022 D&B, Spotlight)

pytorch-lightning. Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

awesome-human-label-variation. A curated list of awesome datasets with human label variation (un-aggregated labels) in Natural Language Processing and Computer Vision, accompanying The 'Problem' of Human Label Variation: On Ground Truth in Data, Modeling and Evaluation (EMNLP 2022)

DeepCore. Code for coreset selection methods

tweetnlp. TweetNLP for all the NLP enthusiasts working on Twitter! The Python library tweetnlp provides a collection of useful tools to analyze/understand tweets such as sentiment analysis, emoji prediction, and named entity recognition, powered by state-of-the-art language models specialised on Twitter.

Advbench. Code and data of the EMNLP 2022 paper "Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP".

diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

NLP4SocialGood_Papers. A reading list of up-to-date papers on NLP for Social Good.

LAVIS. LAVIS - A One-stop Library for Language-Vision Intelligence

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

Conference-Accepted-Paper-List. Some Conferences' accepted paper lists (including AI, ML, Robotic)

OFA. Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

awesome-domain-adaptation-NLP. domain adaptation in NLP

SimBiber. MLNLP社区用来帮助缩短参考文献的工具。A tool for simplifying bibtex with official info

ai-deadlines. :alarm_clock: AI conference deadline countdowns

OpenDelta. A plug-and-play library for parameter-efficient-tuning (Delta Tuning)

MAYA. Code base for the EMNLP 2021 paper, "Multi-granularity Textual Adversarial Attack with Behavior Cloning".

anomaly-detection-resources. Anomaly detection related books, papers, videos, and toolboxes. Last update late 2025 for LLM and VLM works!

PLMpapers. Must-read Papers on pre-trained language models.

backdoor-learning-resources. A list of backdoor learning resources

PromptPapers. Must-read papers on prompt-based tuning for pre-trained language models.

CLIP. CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

awesome-courses. :books: List of awesome university courses for learning Computer Science!

imagenet-testbed. ImageNet Testbed, associated with the paper "Measuring Robustness to Natural Distribution Shifts in Image Classification."

pytorch-image-models. The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

TAADpapers. Must-read Papers on Textual Adversarial Attack and Defense

transformers. 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

stanza. Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages