Yuchen Zhuang

openclaw. Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

AceSearcher. This is the code repo for the paper AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play (NeurIPS 2025 Spotlight).

BIRD-CRITIC-1. [NeurIPS 2025 Main] SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications

game_arena. Python

Awesome-LLM-RLVR. Collection of latest papers and materials in the area of RLVR!

MedAgentGym. [ICLR'26] MedAgentGYM: Training LLM Agents for Code-Based Medical Reasoning at Scale

MLE-Dojo. Python

verifiers. Our library for RL environments + evals

verl-tool. A version of verl to support diverse tool use [TMLR 2026]

rllm. Democratizing Reinforcement Learning for LLMs

Collab-RAG. Python

Awesome-RL-for-LRMs. A Survey of Reinforcement Learning for Large Reasoning Models

awesome-mcp-servers. A collection of MCP servers.

Agent-R1. Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning

GamingAgent. [ICLR 2026] LLM/VLM gaming agents and model evaluation through games.

TinyZero. Minimal reproduction of DeepSeek R1-Zero

BrowserGym. 🌎💪 BrowserGym, a Gym environment for web task automation

AgentLab. AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and reproducibility.

TheAgentCompany. An agent benchmark with tasks in a simulated software company.

TinyLlama. The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

awesome-diffusion-model-in-rl. A curated list of Diffusion Model in RL resources (continually updated)

Awesome-Code-LLM. [TMLR] A curated list of language modeling researches for code (and other software engineering activities), plus related datasets.

O1-Journey. O1 Replication Journey

gorilla. Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

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

kat. [ICLR2025] Kolmogorov-Arnold Transformer

transformers-icl-second-order. Official repository for our paper, Transformers Learn Higher-Order Optimization Methods for In-Context Learning: A Study with Linear Models.

OpenHands. 🙌 OpenHands: AI-Driven Development

GuardAgent-code. Python

code. Python

NeuScraper. [ACL 2024] This is the code repo for our ACL’24 paper "Cleaner Pretraining Corpus Curation with Neural Web Scraping".

RE-Control. Code for paper: Aligning Large Language Models with Representation Editing: A Control Perspective

RAM-EHR. [ACL 2024] This is the code for our paper ”RAM-EHR: Retrieval Augmentation Meets Clinical Predictions on Electronic Health Records“.

MOLLEO. Source code of MOLLEO

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)

TaskMeAnything. [NeurIPS 2024] A task generation and model evaluation system for multimodal language models.

JARVIS. JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

LLM-Agents-Papers. A repo lists papers related to LLM based agent

BMRetriever. [EMNLP 2024] This is the code for our paper "BMRetriever: Tuning Large Language Models as Better Biomedical Text Retrievers".

proxy-tuning. Code associated with Tuning Language Models by Proxy (Liu et al., 2024)

ToolQA. ToolQA, a new dataset to evaluate the capabilities of LLMs in answering challenging questions with external tools. It offers two levels (easy/hard) across eight real-life scenarios.

GraphFNP. Python

Prompt4ReasoningPapers. [ACL 2023] Reasoning with Language Model Prompting: A Survey

MoraBench. MoraBench (Model Ranking Benchmark)

gemma_pytorch. The official PyTorch implementation of Google's Gemma models

awesome-llm-powered-agent. Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...

BBox-Adapter. Lightweight Adapting for Black-Box Large Language Models

indigo. Minimalist Jekyll Template, dark and light themes

GL-SMART. Shriners GL-SMART Demo

Heart-Transplant-Rejection-WSI. [NeurIPS DGM4H'23] Code repo for "Mapping and Diagnosing Augmented Whole Slide Image Datasets with Training Dynamics".

EhrAgent. [EMNLP'24] EHRAgent: Code Empowers Large Language Models for Complex Tabular Reasoning on Electronic Health Records

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

PolyIE. Python

awesome-language-agents. List of language agents based on paper "Cognitive Architectures for Language Agents"

ClinGen. [ACL 2024 Findings] This is the code for our paper "Knowledge-Infused Prompting: Assessing and Advancing Clinical Text Data Generation with Large Language Models".

Awesome-Multimodal-Prompts. Prompts of GPT-4V & DALL-E3 to full utilize the multi-modal ability. GPT4V Prompts, DALL-E3 Prompts.

EcoAssistant. EcoAssistant: using LLM assistant more affordably and accurately

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

Awesome-Efficient-LLM. A curated list for Efficient Large Language Models

autogen. A programming framework for agentic AI

medalign. MedAlign is a clinician-generated dataset for instruction following with electronic medical records.

ToolkenGPT. ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings - NeurIPS 2023 (oral)

Awesome-LLM-Watermark. UP-TO-DATE LLM Watermark paper. 🔥🔥🔥

lit-llama. Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

AttrPrompt. [NeurIPS 2023] This is the code for the paper `Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias`.

MUBen. MUBen: Benchmarking the Uncertainty of Molecular Representation Models

GITM. Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory

Awesome-LLM-Uncertainty-Reliability-Robustness. Awesome-LLM-Robustness: a curated list of Uncertainty, Reliability and Robustness in Large Language Models

open_llama. OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset

reflexion. [NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning

chameleon-llm. Codes for "Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models".

prm800k. 800,000 step-level correctness labels on LLM solutions to MATH problems

chatgpt-retrieval-plugin. The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.

guidance. A guidance language for controlling large language models.

ReGen. [ACL'23 Findings] This is the code repo for our ACL'23 Findings paper "ReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense Retrieval".

qlora. QLoRA: Efficient Finetuning of Quantized LLMs

SMAA. Source code for ICML 2023 paper "Competing for Shareable Arms in Multi-Player Multi-Armed Bandits"

ToolBench. [ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.

AdaPlanner. AdaPlanner: Language Models for Decision Making via Adaptive Planning from Feedback

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

pylatexenc. Simple LaTeX parser providing latex-to-unicode and unicode-to-latex conversion

arxiv.py. Python wrapper for the arXiv API

chat-langchain. TypeScript

langchain. The agent engineering platform.

ReAct. [ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models

ircot. Repository for Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions, ACL23

evals. Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

Chain-of-ThoughtsPapers. A trend starts from "Chain of Thought Prompting Elicits Reasoning in Large Language Models".

ICL_PaperList. Paper List for In-context Learning 🌷

prompts.chat. f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

lion-pytorch. 🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch

Awesome-Learning-with-Label-Noise. A curated list of resources for Learning with Noisy Labels

awesome-uncertainty-deeplearning. This repository contains a collection of surveys, datasets, papers, and codes, for predictive uncertainty estimation in deep learning models.

so-ebm. Code for paper: End-to-end Stochastic Optimization with Energy-based Model

Advances-in-Label-Noise-Learning. A curated (most recent) list of resources for Learning with Noisy Labels

NPC. Python

MPB-UCB. Source code for NeurIPS 2022 paper "Product Ranking for Revenue Maximization with Multiple Purchases".

independence-driven-IW. Source code for ICML 2022 paper "A Theoretical Analysis on Independence-driven Importance Weighting for Covariate-shift Generalization".

NLL-IE. Source code for paper "Learning from Noisy Labels for Entity-Centric Information Extraction", EMNLP 2021

uncertainty-toolbox. Uncertainty Toolbox: a Python toolbox for predictive uncertainty quantification, calibration, metrics, and visualization

Out-of-Distribution-Generalization.github.io. HTML

PRBoost. The codes for our ACL'22 paper: PRBOOST: Prompt-Based Rule Discovery and Boosting for Interactive Weakly-Supervised Learning.

Awesome-Graph-Neural-Networks. Paper Lists for Graph Neural Networks

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

dgl. Python package built to ease deep learning on graph, on top of existing DL frameworks.

BoT. Implementation of "Bag of Tricks for Node Classification with Graph Neural Networks" based on DGL

annotated_latex_equations. Examples of how to create colorful, annotated equations in Latex using Tikz.

Prompt-BERT. PromptBERT: Improving BERT Sentence Embeddings with Prompts

AlphaZero_Gomoku. An implementation of the AlphaZero algorithm for Gomoku (also called Gobang or Five in a Row)

DL4MolecularGraph. Literature of deep learning for graphs in Chemistry and Biology

GNN4NLP-Papers. A list of recent papers about Graph Neural Network methods applied in NLP areas.

SupContrast. PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)

CHMM-ALT. Code for "BERTifying the Hidden Markov Model for Multi-Source Weakly Supervised Named Entity Recognition"

COSINE. [NAACL 2021] This is the code for our paper `Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach'.

awesome-knowledge-graph. 整理知识图谱相关学习资料

Denoise-multi-weak-sources. Python

Megatron-LM. Ongoing research training transformer models at scale

Bayesian_neural_network_papers. Papers for Bayesian-NN

rebiber. A simple tool to update bib entries with their official information (e.g., DBLP or the ACL anthology).

uncertainty-baselines. High-quality implementations of standard and SOTA methods on a variety of tasks.

Calibrated-BERT-Fine-Tuning. Code for Paper: Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution Data

SDE-Net. Code for paper: SDE-Net: Equipping Deep Neural network with Uncertainty Estimates

tokenizations. Robust and Fast tokenizations alignment library for Rust and Python https://tamuhey.github.io/tokenizations/