Liuzhenghao Lv

motif. An AI-native molecular biology workbench for Claude Science: Claude opens sequence files and prepares analyses on request; you annotate, align, and review them in an interactive workspace.

OpenAI4S. 9.9 元豆包API复刻 Claude Science

bioproagent. Code for 2026 ACL Oral paper 'BioProAgent: Neuro-Symbolic Grounding for Constrained Scientific Planning'.

MoleCode. Molecode presents molecules as code and enables LLMs to operate and reason on chemistry directly.

TIDE. Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models

humanizer. Agent skill that removes signs of AI-generated writing from text

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.

STELLA. STELLA: Self-Evolving LLM Agent for Biomedical Research

FIPO. This code implements the algorithm of FIPO, a value-free RL recipe for eliciting deeper reasoning from a clean base model.

Auto-claude-code-research-in-sleep. 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 with Claude Code, Codex, OpenClaw, or any LLM agent.

verl-agent. verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

ToolRL. Python

SciEvalKit. A unified evaluation toolkit and leaderboard for rigorously assessing the scientific intelligence of large language and vision–language models across the full research workflow.

ToolUniverse. Democratizing AI scientists with ToolUniverse

agentskills. Specification and documentation for Agent Skills

Awesome-Adaptation-of-Agentic-AI. Repo for "Adaptation of Agentic AI"

ChemIQ. Jupyter Notebook

FlowER. Flow Matching for Electron Redistribution

Mechanistic_dataset. Python code for mechanistic dataset generation

MutaPLM. Python

UAE. Official repository for the UAE paper, unified-GRPO, and unified-Bench

esm. Jupyter Notebook

mood-experiments. Molecular Out-Of-Distribution

group-selfies. Jupyter Notebook

safe. A single model for all your molecular design tasks

Awesome-Continual-learning-of-Vision-Language-Models. Awsome of VLM-CL. Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting

Claude-Code-Remote. Control Claude Code remotely via email、discord、telegram. Start tasks locally, receive notifications when Claude completes them, and send new commands by simply replying to emails.

posecheck. Pose checks for 3D Structure-based Drug Design methods

Biomni. Biomni: a general-purpose biomedical AI agent

ChemCoTBench. LLM Reasoning Benchmark & Chain-of-Thoughts Dataset for Chemistry

UniWorld. UniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation

RAPM. Code for paper "Rethinking Text-based Protein Understanding: Retrieval or LLM?"

Liquid. (Accepted by IJCV) Liquid: Language Models are Scalable and Unified Multi-modal Generators

e3_diffusion_for_molecules. Python

agenticSeek. Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity.

equibind. EquiBind: geometric deep learning for fast predictions of the 3D structure in which a small molecule binds to a protein

LP-PDBBind. Jupyter Notebook

Token-Mol. Token-Mol 1.0：tokenized drug design with large language model

M-3. a Large-Scale Multi-Modal Dataset Containing 20 Million Descriptions

ByProt. Python

DrugPose. Early code. The code will be cleaned up and improved over time.

bioprobench. Code for 2026 ICML paper 'BioProBench: Comprehensive Dataset and Benchmark in Biological Protocol Understanding and Reasoning'.

HoloTime. [ACM MM 2025] HoloTime: Taming Video Diffusion Models for Panoramic 4D Scene Generation

BioMaze. Python

NeuralGS. [AAAI 2026 🔥] Official implementation of "NeuralGS: Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representation"

mmpdb. A package to identify matched molecular pairs and use them to predict property changes.

LLaDA. Official PyTorch implementation for "Large Language Diffusion Models"

Tartarus. A Benchmarking Platform for Realistic And Practical Inverse Molecular Design

ChemLactica. Fine-tuning Galactica and Gemma to operate on SMILES. Integrates into a molecular optimization algorithm.

WISE. [ICML 2026🔥] WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation

nanoGRPO. nanoGRPO is a lightweight implementation of Group Relative Policy Optimization (GRPO)

admet_ai. Training and prediction scripts for Chemprop models trained on ADMET datasets

Reasoning-Attack.

DeepBlock. This is the official implementation of the paper "A Deep Learning Approach for Rational Ligand Generation with Property Control via Reactive Building Blocks"

GPT-as-Language-Tree. GPT as a Monte Carlo Language Tree: A Probabilistic Perspective

AgentLaboratory. Agent Laboratory is an end-to-end autonomous research workflow meant to assist you as the human researcher toward implementing your research ideas

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

HME. Here is the official code for Nature Communications "Navigating Chemical-Linguistic Sharing Space with Heterogeneous Molecular Encoding".

LAB-Bench. Evaluation dataset for AI systems intended to benchmark capabilities foundational to scientific research in biology

dplm. The Family of Diffusion Protein Language Models (DPLM)

SaProt. Saprot: Protein Language Model with Structural Alphabet (AA+3Di)

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

Next-Patch-Prediction. [AAAI26] Next Patch Prediction

N-LoRA. 【COLING 2025🔥】Code for the paper "Is Parameter Collision Hindering Continual Learning in LLMs?".

ConsisID. [CVPR 2025 Highlight🔥] Identity-Preserving Text-to-Video Generation by Frequency Decomposition

WF-VAE. [CVPR 2025🔥] Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model

ml-cross-entropy. Python

LLaVA-CoT. [ICCV 2025] LLaVA-CoT, a visual language model capable of spontaneous, systematic reasoning

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

OrgMol-Design. Python

bioplanner. Data from BioPlanner: Automatic Evaluation of LLMs on Protocol Planning in Biology paper

moses. Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models

tree-of-thought-llm. [NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models

AI2BMD. AI-powered ab initio biomolecular dynamics simulation

ProtMD. Python

ChemLLMBench. Official Code for What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks (In NeurIPS 2023)

LoRA-GA. Jupyter Notebook

RectifiedFlow. Official Implementation of Rectified Flow (ICLR2023 Spotlight)

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

RADAR. Code for our NeurIPS2023 accepted paper: RADAR: Robust AI-Text Detection via Adversarial Learning. We tested RADAR on 8 LLMs including Vicuna and LLaMA. The results show that RADAR can attain good detection performance on LLM-generated AI-text while being robust against paraphrasing.

ViewCrafter. [TPAMI 2025] ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis

multiobj-rationale. Multi-Objective Molecule Generation using Interpretable Substructures (ICML 2020)

PEER_Benchmark. PEER Benchmark, appear at NeurIPS 2022 Dataset and Benchmark Track (https://arxiv.org/abs/2206.02096)

scikit-fingerprints. Scikit-learn compatible library for molecular fingerprints and chemoinformatics

OpenBioMed. Python

unsloth. Unsloth is a local UI for training and running Kimi K3, Gemma 4, Qwen3.6, DeepSeek, GLM and other models.

huggingface-llama-recipes. Jupyter Notebook

VILA. VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and cloud.

scaling-with-vocab. [NeurIPS-2024] 📈 Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies https://arxiv.org/abs/2407.13623

MolLM. A Unified Language Model to Integrate Biomedical Text with 2D and 3D Molecular Representations

LLM101n. LLM101n: Let's build a Storyteller

protein-dpo. Aligning protein generative models with experimental fitness

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

Scientific-LLM-Survey. Scientific Large Language Models: A Survey on Biological & Chemical Domains

ChronoMagic-Bench. [NeurIPS 2024 D&B Spotlight🔥] ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation

zero_nlp. 中文nlp解决方案(大模型、数据、模型、训练、推理)

MoleculeSTM. Multi-modal Molecule Structure-text Model for Text-based Editing and Retrieval, Nat Mach Intell 2023 (https://www.nature.com/articles/s42256-023-00759-6)

InstructMol. InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery (COLING 2025)

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

Visual-LLaMA. Open LLaMA Eyes to See the World

EvaGaussians.

MergeLM. Codebase for Merging Language Models (ICML 2024)

Awesome-Bio-Foundation-Models. A collection of awesome bio-foundation models, including protein, RNA, DNA, gene, single-cell, and so on.

RethinkTinyLM. [ICML'24] The official implementation of “Rethinking Optimization and Architecture for Tiny Language Models”

text2mol. Repository for Text2Mol: Cross-Modal Molecular Retrieval with Natural Language Queries

FCD. Fréchet ChemNet Distance: A quality measure for generative models for molecules

fcd_torch. Fréchet ChemNet Distance on PyTorch

awesome. 😎 Awesome lists about all kinds of interesting topics

MolT5. Associated Repository for "Translation between Molecules and Natural Language"

LAWT. Code for papers Linear Algebra with Transformers (TMLR) and What is my Math Transformer Doing? (AI for Maths Workshop, Neurips 2022)

GraphFP. Implementation of Fragment-based Pretraining and Finetuning on Molecular Graphs (NeurIPS 2023)

GaLore. GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

Uniaa. Unified Multi-modal IAA Baseline and Benchmark

PS-VAE. This repo contains the codes for our paper: Molecule Generation by Principal Subgraph Mining and Assembling.

MagicTime. [TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators

SmilesPE. SMILES Pair Encoding: A data-driven substructure representation of chemicals

VOLT. Code for paper "Vocabulary Learning via Optimal Transport for Neural Machine Translation"

MolFrag. Obtain and organize all feasible fragmentation of molecular methods

Multimodal-Roadmap-for-freshman. 本项目用于Multimodal领域新手的学习路线，包括该领域的经典论文，项目及课程。旨在希望学习者在一定的时间内达到对这个领域有较为深刻的认知，能够自己进行的独立研究。

xVal. Repository for code used in the xVal paper

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

Envision3D. Envision3D: One Image to 3D with Anchor Views Interpolation

Mole-BERT. [ICLR 2023] "Mole-BERT: Rethinking Pre-training Graph Neural Networks for Molecules"

ProteinInvBench. The official implementation of the NeurIPS'23 paper ProteinInvBench: Benchmarking Protein Design on Diverse Tasks, Models, and Metrics

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"

3D-MoLM. Python

spikformer. ICLR 2023, Spikformer: When Spiking Neural Network Meets Transformer

PoW-Simple-Simulator. SJTU IS416 区块链技术及其应用 大作业 PoW 模拟器

BPNN. 分别利用RMSProp和Momentum优化算法构造BP神经网络，实现对Iris数据集的分类

SJTU-CS433. SJTU-CS433 Parallel and Distributed Programming

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

TaxDiff. The official code for "TaxDiff: Taxonomic-Guided Diffusion Model for Protein Sequence Generation"

ProLLaMA. A Protein Large Language Model for Multi-Task Protein Language Processing

RI_framework. Here is the source code for ICASSP 2024 paper "A General Framework For Rotation Invariant Point Cloud Analysis"

ANN2SNN_GN. Here is the official code for ICASSP 2024 "Optimal ANN-SNN Conversion with Group Neurons".

ECDFormer. 【Nature Computational Science 2025🔥】Deep peak property learning for efficient chiral molecules ECD spectra prediction

PiCO. [ICLR'25] PiCO: Peer Review in LLMs based on the Consistency Optimization, https://arxiv.org/pdf/2402.01830

progen. Implementation and replication of ProGen, Language Modeling for Protein Generation, in Jax

PromptCraft-Robotics. Community for applying LLMs to robotics and a robot simulator with ChatGPT integration

rcg. PyTorch implementation of RCG https://arxiv.org/abs/2312.03701

repaint123. Official implementation of Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting (ECCV 2024)

Machine-Mindset. An MBTI Exploration of Large Language Models

Video-Bench. A Comprehensive Benchmark and Toolkit for Evaluating Video-based Large Language Models!

MMseqs2. MMseqs2: ultra fast and sensitive search and clustering suite

foldseek. Foldseek enables fast and sensitive comparisons of large structure sets.

LanguageBind. 【ICLR 2024🔥】 Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment

Hallucination-Attack. Attack to induce LLMs within hallucinations

Video-LLaVA. 【EMNLP 2024🔥】Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

ChatLaw. ChatLaw：A Powerful LLM Tailored for Chinese Legal. 中文法律大模型

Chat-UniVi. [CVPR 2024 Highlight🔥] Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding

BELLE. BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

Medusa. Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

MedicalGPT. MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training Pipeline. 训练医疗大模型，实现了包括增量预训练(PT)、有监督微调(SFT)、RLHF、DPO、ORPO、GRPO。

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

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

llama. Inference code for Llama 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

sentencepiece. Unsupervised text tokenizer for Neural Network-based text generation.

Chinese-LLaMA-Alpaca-2. 中文LLaMA-2 & Alpaca-2大模型二期项目 + 64K超长上下文模型 (Chinese LLaMA-2 & Alpaca-2 LLMs with 64K long context models)

esm. Evolutionary Scale Modeling (esm): Pretrained language models for proteins

Chinese-LLaMA-Alpaca. 中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

ChatGPT-Academic-Prompt. Use ChatGPT for academic writing

syops-counter. SyOPs counter for spiking neural networks

awesome-community-detection. A curated list of community detection research papers with implementations.

ResNet. Reproduce ResNet-v2(Identity Mappings in Deep Residual Networks) with MXNet

Parallel-Spiking-Neuron. Python

awesome-snn-conference-paper. 🔥 This repository compiles research papers (from top-tier conferences and journals) and code implementations in the field of Spiking Neural Networks (SNNs). 本仓库收集了脉冲神经网络领域的顶会顶刊论文和代码，正在持续更新中。

chatgpt-advanced. WebChatGPT: A browser extension that augments your ChatGPT prompts with web results.

BRECQ. Pytorch implementation of BRECQ, ICLR 2021

pytorch-quantization-demo. A simple network quantization demo using pytorch from scratch.

TongjiThesis. 同济大学毕业设计论文 LaTeX 模板 | TongjiThesis - LaTeX Thesis Template for Tongji University

torch-scan. Seamless analysis of your PyTorch models (RAM usage, FLOPs, MACs, receptive field, etc.)

paper-reading. 深度学习经典、新论文逐段精读

deeplearning_ai_books. deeplearning.ai（吴恩达老师的深度学习课程笔记及资源）

SNN-learning-methods-papers. 该仓库主要收录了顶会中SNN领域的一些论文，论文内容与代理梯度和ANN-SNN转换相关。

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

awesome-deep-learning. A curated list of awesome Deep Learning tutorials, projects and communities.

Awesome-Model-Quantization. A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research, we are continuously improving the project. Welcome to PR the works (papers, repositories) that are missed by the repo.

ANN2SNNConversion_SNM_NeuronNorm. Pytorch Implementation of Signed Neuron with Memory: Towards Simple, Accurate and High-Efficient ANN-SNN Conversion, IJCAI 2022

pytorch_resnet_cifar10. Proper implementation of ResNet-s for CIFAR10/100 in pytorch that matches description of the original paper.

SNN_conversion_QCFS. Python

ANN2SNN_COS. Python

ProxyLearning. Spiking neural networks trained via proxy

tuning_playbook. A playbook for systematically maximizing the performance of deep learning models.

doing_the_PhD.

HumanSystemOptimization. 健康学习到150岁 - 人体系统调优不完全指南

iBook. 收藏一些电子书

996.ICU. Repo for counting stars and contributing. Press F to pay respect to glorious developers.

DeepLearning-500-questions. 深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，50余万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系scutjy2015@163.com 版权所有，违权必究 Tan 2018.06

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

Awesome-Computer-Vision-Paper-List. This repository contains all the papers accepted in top conference of computer vision, with convenience to search related papers.

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.

SNN_Calibration. Pytorch Implementation of Spiking Neural Networks Calibration, ICML 2021

missing-semester-cn.github.io. the CS missing semester Chinese version

spikingjelly. SpikingJelly is an open-source deep learning framework for Spiking Neural Network (SNN) based on PyTorch.

pytorch-tutorial. PyTorch Tutorial for Deep Learning Researchers

pytorch-handbook. pytorch handbook是一本开源的书籍，目标是帮助那些希望和使用PyTorch进行深度学习开发和研究的朋友快速入门，其中包含的Pytorch教程全部通过测试保证可以成功运行