Bowen Jin

PhD_Thesis.

OpenDecoder. A repository of OpenDecoder framework: Open Large Language Model Decoding to Incorporate Document Quality in RAG (WWW 2026)

tolerator. Code Repo for FIRE decoding of dLLMs

tinker-cookbook. Post-training with Tinker

DRL. Deep Reinforcement Learning

AReaL. The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.

gpt-oss. gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

harmony. Renderer for the harmony response format to be used with gpt-oss

Megatron-LM. Ongoing research training transformer models at scale

firejail. Linux namespaces and seccomp-bpf sandbox

rllm. Democratizing Reinforcement Learning for LLMs

code-r1. Reproducing R1 for Code with Reliable Rewards

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!

Awesome_Think_With_Images. Resources and paper list for "Thinking with Images for LVLMs". This repository accompanies our survey on how LVLMs can leverage visual information for complex reasoning, planning, and generation.

MIRIX. Mirix is a multi-agent personal assistant designed to track on-screen activities and answer user questions intelligently. By capturing real-time visual data and consolidating it into structured memories, Mirix transforms raw inputs into a rich knowledge base that adapts to your digital experiences.

crawl4ai. 🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN

VTool-R1. [ICLR 2026] "VTool-R1: VLMs Learn to Think with Images via Reinforcement Learning on Multimodal Tool Use"

mllm_interview_note. 主要记录大语言大模型（LLMs） 算法（应用）工程师多模态相关知识

quant-wiki. We are committed to the open-sourcing quantitative knowledge, aiming to bridge the information gap between the domestic and international quantitative finance industries. 我们致力于量化知识的开源与汉化，打破国内外量化金融行业信息差。

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

RAST. Reasoning Activation in LLMs via Small Model Transfer (NeurIPS 2025)

HRPO. [NeurIPS 2025] Hybrid Latent Reasoning via Reinforcement Learning

SearchAgent-X. A High-Efficiency System of Large Language Model Based Search Agents

acad-homepage.github.io. AcadHomepage: A Modern and Responsive Academic Personal Homepage

knowledge-r1. IKEA: Reinforced Internal-External Knowledge Synergistic Reasoning for Efficient Adaptive Search Agent

ZeroSearch. ZeroSearch: Incentivize the Search Capability of LLMs without Searching

SkyRL. SkyRL: A Modular Full-stack RL Library for LLMs

Multiturn-RL-SWE. Multiturn RL experiments

RM-R1. [ICLR'26] RM-R1: Unleashing the Reasoning Potential of Reward Models

Chem-R1. Python

OpenHands. 🙌 OpenHands: AI-Driven Development

Rec-R1. [TMLR 2025] A general framework for bridging LLMs and recommendation systems via reinforcement learning. https://arxiv.org/pdf/2503.24289

Rubric-RM. Jupyter Notebook

openvla. OpenVLA: An open-source vision-language-action model for robotic manipulation.

GUI-Agents-Paper-List. Awesome GUI Agent Paper List

scaling-retriever. [SIGIR 2025] The official repo for "Scaling Sparse and Dense Retrieval in Decoder-Only LLMs"

Search-R1. Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL

Awesome-ML-SYS-Tutorial. My learning notes for ML SYS.

Embodied-AI-Guide. [Lumina具身智能社区] 具身智能技术指南 Embodied-AI-Guide

open-infra-index. Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

OmniParser. A simple screen parsing tool towards pure vision based GUI agent

code-interpreter. Python & JS/TS SDK for running AI-generated code/code interpreting in your AI app

smolagents. 🤗 smolagents: a barebones library for agents that think in code.

ScienceWorld. ScienceWorld is a text-based virtual environment centered around accomplishing tasks from the standardized elementary science curriculum.

Online-DPO-R1. Codebase for Iterative DPO Using Rule-based Rewards

MobileAgent. Mobile-Agent: The Powerful GUI Agent Family

R1-V. Witness the aha moment of VLM with less than $3.

Gymnasium. A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

CoF. Chain-of-Factors Paper-Reviewer Matching (WWW'25)

TinyZero. Minimal reproduction of DeepSeek R1-Zero

RAGEN. RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.

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

open-r1. Fully open reproduction of DeepSeek-R1

ollama. Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

GPT-4V-Act. AI agent using GPT-4V(ision) capable of using a mouse/keyboard to interact with web UI

DeepSeek-R1.

TEG-Benchmark. [NeurIPS 2024 🔥] TEG-DB: A Comprehensive Dataset and Benchmark of Textual-Edge Graphs

RAGTruth. Github repository for "RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models"

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

tevatron. Tevatron - Unified Document Retrieval Toolkit across Scale, Language, and Modality. Demo in SIGIR 2023, SIGIR 2025.

RLHF-Reward-Modeling. Recipes to train reward model for RLHF.

simple-evals. Python

Online-RLHF. A recipe for online RLHF and online iterative DPO.

lingua. Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

evalplus. Rigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024

alpaca_farm. A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.

awesome-o1. A bibliography and survey of the papers surrounding o1

InstructG2I. InstructG2I: Synthesizing Images from Multimodal Attributed Graphs (NeurIPs 2024)

nerfies.github.io. JavaScript

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

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

Awesome-LLM. Awesome-LLM: a curated list of Large Language Model

Awesome-LLM-Preference-Learning. The official repository of our survey paper: "Towards a Unified View of Preference Learning for Large Language Models: A Survey"

graph-instruction-tuning. [COLM'24] Investigating Instruction Tuning Large Language Models on Graphs

CitationMap. A simple pip-installable Python tool to generate your HTML citation world map from your Google Scholar ID.

corenet. CoreNet: A library for training deep neural networks

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

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

chameleon. Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.

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

axolotl. Go ahead and axolotl questions

llm.c. LLM training in simple, raw C/CUDA

DocGenome. DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Models

RAG-Survey. Collecting awesome papers of RAG for AIGC. We propose a taxonomy of RAG foundations, enhancements, and applications in paper "Retrieval-Augmented Generation for AI-Generated Content: A Survey".

VideoNIAH. VideoNIAH: A Flexible Synthetic Method for Benchmarking Video MLLMs

torchtitan. A PyTorch native platform for training generative AI models

LLMLingua. [EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

llama.cpp. LLM inference in C/C++

FlashRAG. ⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)

Awesome-Video-Datasets. Video datasets

Open-Sora. Open-Sora: Democratizing Efficient Video Production for All

Awesome-Multimodal-on-Graphs. A curated list of papers and resources about multimodal learning on graphs.

FlagEmbedding. Retrieval and Retrieval-augmented LLMs

ToTER_WWW24. Improving Retrieval in Theme-specific Applications using a Corpus Topical Taxonomy (WWW'24)

UniMP. [ICLR 2024] Towards Unified Multi-Modal Personalization: Large Vision-Language Models for Generative Recommendation and Beyond

lost-in-the-middle. Code and data for "Lost in the Middle: How Language Models Use Long Contexts"

alignment-handbook. Robust recipes to align language models with human and AI preferences

RAG-Survey.

Machine-learning-for-proteins. Listing of papers about machine learning for proteins.

d3po. [CVPR 2024] Code for the paper "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"

audiocraft. Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

Mol-Instructions. [ICLR 2024] Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models

Awesome-Biomolecule-Language-Cross-Modeling. Awesome-Biomolecule-Language-Cross-Modeling: a curated list of resources for paper "Leveraging Biomolecule and Natural Language through Multi-Modal Learning: A Survey"

MGM. Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

IP-Adapter. The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.

Auto3D_pkg. Auto3D generates low-energy conformers from SMILES/SDF

transformer-debugger. Python

songcomposer. [ACL 2025 Main] SongComposer: A Large Language Model for Lyric and Melody Generation in Song Composition

Awesome-Mamba-Papers. Awesome Papers related to Mamba.

Open-Sora-Plan. This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

needle-in-a-haystack. Doing simple retrieval from LLM models at various context lengths to measure accuracy

deepchem. Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology

AIRS. Artificial Intelligence Research for Science (AIRS)

KG-MM-Survey. Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey

GenAI4Drug. [Briefings in Bioinformatics] A Survey of Generative AI for de novo Drug Design

Generative-Diffusion-Models-on-Graphs.

METAG. Learning Multiplex Representations on Text-Attributed Graphs with One Language Model Encoder

LMIndexer. Language Models as Semantic Indexers (ICML 2024)

LWM. Large World Model -- Modeling Text and Video with Millions Context

Graph-CoT. Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs (ACL 2024)

InstructDoc. InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions (AAAI2024)

llm-course. Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Awesome-Scientific-Language-Models. A Comprehensive Survey of Scientific Large Language Models and Their Applications in Scientific Discovery (EMNLP'24)

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

Awesome-LLM-Survey. An Awesome Collection for LLM Survey

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

llm-paper-daily. Daily updated LLM papers. 每日更新 LLM 相关的论文，欢迎订阅 👏 喜欢的话动动你的小手 🌟 一个

Awesome-LLM-hallucination. LLM hallucination paper list

DreamLLM. [ICLR 2024 Spotlight] DreamLLM: Synergistic Multimodal Comprehension and Creation

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

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.

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

papermage. library supporting NLP and CV research on scientific papers

RIPOR. [WWW 2024] The official repo for paper "Scalable and Effective Generative Information Retrieval".

MMGL. Multimodal Graph Learning: how to encode multiple multimodal neighbors with their relations into LLMs

hetionet. Hetionet: an integrative network of disease

Awesome-HealthCare-KnowledgeBase. A curated list of awesome healthcare taxonomies and knowledge graphs.

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

chroma. Search infrastructure for AI

LLM-Agent-Survey.

courtlistener. A fully-searchable and accessible archive of court data including growing repositories of opinions, oral arguments, judges, judicial financial records, and federal filings.

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

ChatBridge. ChatBridge, an approach to learning a unified multimodal model to interpret, correlate, and reason about various modalities without relying on all combinations of paired data.

KG-LLM-Papers. [Paper List] Papers integrating knowledge graphs (KGs) and large language models (LLMs)

AgentVerse. 🤖 AgentVerse 🪐 is designed to facilitate the deployment of multiple LLM-based agents in various applications, which primarily provides two frameworks: task-solving and simulation

LLM-Agent-Paper-List. The paper list of the 86-page SCIS cover paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.

law-net. code to analyze the legal citation network

LMFlow. An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

Awesome-LLM-Reasoning. From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓

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

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.

legalbench. An open science effort to benchmark legal reasoning in foundation models

rank_bm25. A Collection of BM25 Algorithms in Python

open-instruct. AllenAI's post-training codebase

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.

StructGPT. The code and data for "StructGPT: A general framework for Large Language Model to Reason on Structured Data"

denoising-diffusion-pytorch. Implementation of Denoising Diffusion Probabilistic Model in Pytorch

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

higgsfield. Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters

torchdrug. A powerful and flexible machine learning platform for drug discovery

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

Awesome-Language-Model-on-Graphs. A curated list of papers and resources based on "Large Language Models on Graphs: A Comprehensive Survey" (TKDE)

Heterformer. Heterformer: Transformer-based Deep Node Representation Learning on Heterogeneous Text-Rich Networks (KDD 2023)

daam. Diffusion attentive attribution maps for interpreting Stable Diffusion.

Awesome-Diffusion-Models. A collection of resources and papers on Diffusion Models

Awesome-Graph-LLM. A collection of AWESOME things about Graph-Related LLMs.

nanoT5. Fast & Simple repository for pre-training and fine-tuning T5-style models

simple_rqvae. Jupyter Notebook

awesome-generative-information-retrieval.

DSI-transformers. A huggingface transformers implementation of "Transformer Memory as a Differentiable Search Index"

vector-quantize-pytorch. Vector (and Scalar) Quantization, in Pytorch

FUTEX. Weakly Supervised Multi-Label Classification of Full-Text Scientific Papers (KDD'23)

hh-rlhf. Human preference data for "Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback"

StarSpace. Learning embeddings for classification, retrieval and ranking.

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

awesome-instruction-learning. Papers and Datasets on Instruction Tuning and Following. ✨✨✨

Patton. Patton: Language Model Pretraining on Text-rich Networks (ACL 2023 main oral)

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

LLMsPracticalGuide. A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)

OpenHGNN. This is an open-source toolkit for Heterogeneous Graph Neural Network(OpenHGNN) based on DGL.

openai-cookbook. Examples and guides for using the OpenAI API

GPTeacher. A collection of modular datasets generated by GPT-4, General-Instruct - Roleplay-Instruct - Code-Instruct - and Toolformer

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

xformers. Hackable and optimized Transformers building blocks, supporting a composable construction.

alpa. Training and serving large-scale neural networks with auto parallelization.

llama_index. LlamaIndex is the leading document agent and OCR platform

awesome-RLHF. A curated list of reinforcement learning with human feedback resources (continually updated)

LLaMA-Adapter. [ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

llama. Inference code for Llama models

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

ChatPaper. Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复

CowAgent. Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-model, multi-channel. Lightweight, extensible, one-line install. (formerly chatgpt-on-wechat)

alpaca-lora. Instruct-tune LLaMA on consumer hardware

fairseq. Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

nanoGPT. The simplest, fastest repository for training/finetuning medium-sized GPTs.

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

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

awesome-graph-transformer. Papers about graph transformers.

DiffuSeq. [ICLR'23] DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models

GP-VAE. This repository contains the data and code for the paper "Diverse Text Generation via Variational Encoder-Decoder Models with Gaussian Process Priors" (SPNLP@ACL2022)