Siyuan Yan

OmniSleep. Python

MOOZY. [ECCV 2026] A Patient-First Foundation Model for Computational Pathology

ICML2026_paper_filter. Python

FairSSL. Official implementation of the paper "FairSSL: Fair Multimodal Self-Supervised Learning", published at ICML 2026.

acnedetection. Python

Clin-JEPA. Python

DeepSpotM. Multimodal foundation model predicting transcriptome-wide virtual spatial transcriptomics from histology.

HealthAgentBench. Python

DeepSpot. DeepSpot: Deep learning model for predicting spatial transcriptomics from H&E histopathology images. Supports spot-level (Visium) and single-cell (Xenium) resolution.

Histopathology-Datasets. Ressources of histopathology datasets

he2st. Code of the paper "DeepSpot: Leveraging Spatial Context for Enhanced Spatial Transcriptomics Prediction from H&E Images"

HEST. Integrating histology and spatial transcriptomics - NeurIPS 2024

ai-berkshire. AI 时代的伯克希尔：基于 Claude Code / Codex 的价值投资研究框架。巴菲特·芒格·段永平·李录四大师方法论 + 多Agent并行研究。| AI-era Berkshire: a value investing research framework built for Claude Code / Codex. 4 masters' methodologies + multi-agent adversarial analysis.

PatientSim. PatientSim: A Persona-Driven Simulator for Realistic Doctor-Patient Interactions (NeurIPS 2025 D&B track, Spotlight)

RT-Super. [MICCAI 2026] A longitudinal, multimodal algorithm for multi-tumor segmentation (learning from reports).

ECG-SCD. Python

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

SoccerMaster. [CVPR 2026 Oral] SoccerMaster: A Vision Foundation Model for Soccer Understanding

Light-WAM. Codebase for Light-WAM: Efficient World Action Models with State-Fusion Action Decoding.

science-superpowers. Composable computational-science methodology skills for AI research agents — pre-registration over TDD. A science-domain reimplementation of Superpowers.

superpowers-zh. 🦸 AI 编程超能力 · 中文增强版 — superpowers（116k+ ⭐）完整汉化 + 6 个中国原创 skills，让 Claude Code / Copilot CLI / Hermes Agent / Cursor / Windsurf / Kiro / Gemini CLI 等 16 款 AI 编程工具真正会干活

discover. Python

openmed. Local-first healthcare AI: clinical NER & HIPAA PII de-identification that runs 100% on-device. 1,000+ medical models, 12 languages, Apple MLX + Python, no cloud, no patient data leaving your network. Apache-2.0

MedCBR. [CVPR'26 Findings] Vision-Language Models Encode Clinical Guidelines for Concept-Based Medical Reasoning

thymus_health_deeplearning_system. This repo contains the source code for the thymus health projects.

DermFM-Zero. Vision-language foundation model for zero-shot dermatology

Doctor-R1. This is the official repository for our paper "Doctor-R1: Mastering Clinical Inquiry with Experiential Agentic Reinforcement Learning" published in ICRL 2026.

EviScreen. Official Code for Evidential Reasoning Advances Interpretable Real-World Disease Screening (ICML 2026)

Deep-Spurious-Regression. Shortcut to Nowhere: Demystifying Deep Spurious Regression

MedSP1000. Python

DermoGPT. Python

procedural-warmup-vit. Python

sparse_autoencoder. Sparse Autoencoder for Mechanistic Interpretability

m4oe. Python

NeurIPS. [ICML 2026] Official Code of "NeurIPS: Neuro-anatomical Inductive Priors for Sphere-based Brain Decoding"

Nature-Paper-Skills. Agent skills for drafting, revising, auditing, and resubmitting Nature-style journal manuscripts.

Awesome-AI4DigitalPathology. A Curated List of Awesome Works in Computational Pathology, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in Digital Pathology.

ConceptSeg-R1. Segment Any Concept via Meta-Reinforcement Learning

CaRE. [ICML 2026] Scaling Continual Learning to 300+ Tasks with Bi-Level Routing Mixture-of-Experts

ECG-R1. [ICML 2026] ECG-R1: Protocol-Guided and Modality-Agnostic MLLM for Reliable ECG Interpretation

OphthaReason. Python

nature-skills. 符合nature论文学术表达和科研绘图的Skill

paper-plot-skills. Top-Conference Paper Figure Reproduction & Plotting Skills | 顶会论文图表复现绘制Skills

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

DermAgent. DermAgent: A Self-Reflective Agentic System for Dermatological Image Analysis with Multi-Tool Reasoning and Traceable Decision-Making

MeWM. [ICCV 2025] Medical World Model

PhysicianBench. The benchmark tasks and evaluation harness for "PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments".

figures4papers. My Python scripts to make high-quality figures for publications in top AI conferences and journals.

onco-agent. Python

allofus_NIH_wear. Jupyter Notebooks for use on the AllOfUs Researcher Workbench for wearables data analysis related to the NIH WEAR Program.

PS3. Scaling Vision Pre-Training to 4K Resolution

ppt-master. AI generates a real, editable PowerPoint from any document — native shapes & animations, editable charts & tables you can change the data on, speaker notes voiced as audio narration, and the option to follow your own .pptx template, not slide images · by Hugo He

medgemma. Jupyter Notebook

andrej-karpathy-skills. A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

MAKE. [MICCAI‘25 Early Accept] MAKE: Multi-Aspect Knowledge-Enhanced Vision-Language Pretraining for Zero-shot Dermatological Assessment

Derm1M. [ICCV'25 Highlight] Derm1M: A Million‑Scale Vision‑Language Dataset Aligned with Clinical Ontology Knowledge for Dermatology

PanDerm. [Nature Medicine'25] A Multimodal Vision Foundation Model for Clinical Dermatology

DemMA. The official implementation for ACL26 (findings) paper DemMA: Dementia Multi-Turn Dialogue Agent with Expert-Guided Reasoning and Action Simulation

MAP. Python

mtbbench. MTBBench is a benchmark designed to evaluate the reasoning capabilities of multimodal large language models (LLMs) in complex clinical decision-making scenarios. It focuses on two core challenges in oncology: multimodal integration (e.g., pathology, genomics, radiology) and longitudinal reasoning across patient timelines.

eSkinHealth. [ACM Multimedia'25 Dataset Track] A Multimodal Dataset for Neglected Tropical Skin Diseases

le-wm. Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

MedMASLab. Python

Cerebra. Official implementation of Cererba

sleepfm-clinical. Python

Meissa. Meissa is a multi-modal medical agent, built on trajectory-based agentic behavior distillation framework.

OSF-Open-Sleep-FM. [ICML 2026] OSF: On Pre-training and Scaling of Sleep Foundation Models

HEARTS. [ICML 2026] HEARTS: Benchmarking LLM Reasoning on Health Time Series

pua. 你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.

DERM-3R. The world's first multimodal intelligent agent for traditional chinese medicine dermatology

MAGEN-O-MAKE. Multi-Aspect Knowledge-Enhanced Medical Vision-Language Pretraining with Multi-Agent Data Generation

PathReasoner-R1. Official implementation of "PathReasoner-R1: Instilling Structured Reasoning into Pathology Vision-Language Model via Knowledge-Guided Policy Optimization"

SleepLM. [ICML 2026, Spotlight] SleepLM: Natural-Language Intelligence for Human Sleep

OphAgent. Python

MediX-R1. Open Ended Medical Reinforcement Learning

AgentFlow. AgentFlow: In-the-Flow Agentic System Optimization

Eubiota. Python

ConceptCLIP. Python

Awesome-Agentic-Reasoning. A curated list of papers and resources based on the survey "Agentic Reasoning for Large Language Models"

RetSAM. Official Implementation of "A General Model for Retinal Segmentation and Quantification"

AI-Research-SKILLs. Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepower. Maintained by Orchestra Research.

data-formulator. 🪄 Data Formulator is an interactive AI-powered data analysis system makes it easy to connect, explore and visualize data.

AlitaOpen. Alita invents weapons for herself, to minimize control & maximize intelligence

Biomni. Biomni: a general-purpose biomedical AI agent

GazeCapture. Eye Tracking for Everyone

LungNoduleAgent. [AAAI 2026] LungNoduleAgent: A Collaborative Multi-Agent System for Precision Diagnosis of Lung Nodules

EvoClinician. EvoClinician: A Self-Evolving Agent for Multi-Turn Medical Diagnosis via Test-Time Evolutionary Learning

synthea. Synthetic Patient Population Simulator

BioDSA. BioDSA: Framework for Vibe Prototyping of AI Agents for Biomedicine

AutoFigure-Edit. Python

MedRAX. MedRAX: Medical Reasoning Agent for Chest X-ray - ICML 2025

DeepRare. Code implementation of DeepRare (Nature 2026)

awesome-ai-research-writing. Elevate your AI research writing, no more tedious polishing ✨

MedAgent-Pro. [2026 ICLR] The official code for MedAgent_Pro

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

Deep-DxSearch. An agentic RL framework to enhance retreival-augmented reasoning in Diagnostic Policy

Qwen3.6. Qwen3.6 is the large language model series developed by Qwen team, Alibaba Group.

mixture-of-visual-thoughts. Python

CoT-Evo. [ICLR 2026] CoT-Evo: Evolutionary Distillation of Chain-of-Thought for Scientific Reasoning

PyGaze. an open-source, cross-platform toolbox for minimal-effort programming of eye tracking experiments

EchoJEPA. EchoJEPA: A Latent Predictive Foundation Model for Echocardiography

agentskills. Specification and documentation for Agent Skills

OpenScholar. This repository includes the official implementation of OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs.

SciToolAgent. SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integration

DentalGPT. Incentivizing Multimodal Complex Reasoning in Dentistry

TeamPath. Python

OmniScientist.

langgraph. Build resilient agents.

MIRA. MIRA: Medical Time Series Foundation Model for Real-World Health Data

TMLR_FedDRA. official implementation of tmlr submission Distributionally Robust Alignment for Medical Federated Vision-Language Pre-training Under Data Heterogeneity

DeepEyesV2. Python

DSGym. A holistic framework for advancing LLMs as data science agents

AMIE-pytorch. Implementation of the general framework for AMIE, from the paper "Towards Conversational Diagnostic AI", out of Google Deepmind

heartlib. HeartMuLa Official Repo: The Most Powerful Open-Source Music Generation Model of 2026

pcdf. Implementation of our AAAI 2026 Paper

GenEnv. GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators

PulseMind. Python

OmicsNavigator. Python

MinerU. Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

Baichuan-M3-235B. Baichuan-M3 Modeling Clinical Inquiry for Reliable Medical Decision-Making

Tissuelab-Model-Zoo. Tissuelab Model Zoo

semanticlens. Mechanistic understanding and validation of large AI models with SemanticLens

Multi-Agent-Medical-Assistant. ⚕️GenAI powered multi-agentic medical diagnostics and healthcare research assistance chatbot. 🏥 Designed for healthcare professionals, researchers and patients.

IntroECG. Resource library for getting started with deep learning work using electrocardiograms

KnoBo. NeurIPS 2024 (spotlight): A Textbook Remedy for Domain Shifts Knowledge Priors for Medical Image Analysis

skin-disease-recognition. Acne and Dark Circles Detection

Awesome-AI-Agents-for-Healthcare. Latest Advances on Agentic AI & AI Agents for Healthcare

MiroThinker. MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.

Awesome-Pathology-Agents. Awesome papers & datasets specifically focused on pathology.

IMAplusplus. Python

EHRFormer. Python

PathGen-1.6M. Python

Qwen-Agent. Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

LLaVA-OneVision-1.5-RL. Fully Open Framework for Democratized Multimodal Reinforcement Learning.

GigaTIME. GigaTIME: Multimodal AI generates virtual population for tumor microenvironment modeling (Cell)

MindJourney. [NeurIPS 2025] Source codes for the paper "MindJourney: Test-Time Scaling with World Models for Spatial Reasoning"

Dr.V. Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Grounding

FedMLLM. Python

CLOVER. Cost-efficient and Instruction-driven AI Conversation in Digital Pathology

awesome-nano-banana-pro-prompts. 🍌 World's largest Nano Banana Pro prompt library — 10,000+ curated prompts with preview images, 16 languages. Google Gemini AI image generation. Free & open source.

HistoGPT. A vision language model for gigapixel whole slide images in histopathology

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

Qwen3-VL. Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

MIRIAD. MIRIAD is a million-scale Medical Instruction and Retrieval Datatset

Med-PRM. [EMNLP 2025] Med-PRM: Medical Reasoning Models with Stepwise, Guideline-verified Process Rewards

fastsae. FastSAE: Adopt seamlessly, train fast

WSI-LLaVA. Python

SpLiCE. Sparse Linear Concept Embeddings

CFN. [IPMI'25] Concepts from Neurons: Building Interpretable Medical Image Diagnostic Models by Dissecting Opaque Neural Networks

DISC. (ICML 2023) Discover and Cure: Concept-aware Mitigation of Spurious Correlation

DIM. Discover and mitigate multiple unknown bias (CVPR'24)

viconex-med. Code for the paper "ViConEx-Med: Visual Concept Explainability via Multi-Concept Token Transformer for Medical Image Analysis", 2025.

turtle. [ICML 2024] Let Go of Your Labels with Unsupervised Transfer

Discover-then-Name. Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.

cgbench. CGBench: Benchmarking Scientific Understanding of LLMs via Clinical Genetics Annotations

ReasonMed. ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning

BenchX. BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays

ConceptScope. Official implementation of paper: Characterizing Dataset Bias via Disentangled Visual Concepts

OmniShopAgent. An autonomous multi-modal fashion shopping agent powered by LangGraph and ReAct pattern.

CHA. Conversational Health Agents: A Personalized LLM-powered Agent Framework

TAM. [ICCV25 Oral] Token Activation Map to Visually Explain Multimodal LLMs

MAM. MAM: ModularMulti-Agent Framework for Multi-Modal Medical Diagnosis via Role-Specialized Collaboration

HealthcareAgent. List of Awesome AI Agent for Healthcare and Common Agentic AI API Interface

ALIP. [ICCV 2023] ALIP: Adaptive Language-Image Pre-training with Synthetic Caption

RAE. Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"

VAPO. Official repo for "More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Models" (ICLR 2026)

MedVLThinker. [ML4H'25] MedVLThinker: Simple Baselines for Multimodal Medical Reasoning

DermaSynth-VQA. DermaSynth-VQA: A large-scale synthetic Visual Question-Answering dataset generation tool using Gemini API.

MedAgentSim. MedAgentSim: Self-Evolving Multi-Agent Simulations for Realistic Clinical Interactions, MICCAI 2025 (oral and early accepted)

Hulu-Med. A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding

UniMed-CLIP. Official repository of paper titled "UniMed-CLIP: Towards a Unified Image-Text Pretraining Paradigm for Diverse Medical Imaging Modalities".

Toucan. Official repo of Toucan: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments

Self-Evolving-Agents.

Longitudinal_skin_images. Python

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

TissueLab. A Co-evolving Agentic AI System for Medical Imaging Analysis

Baichuan-M2-32B. Beyond the Model: Scaling Medical Capability with a Large Verifier System

LLaVA-OneVision-2. Fully Open Framework for Democratized Multimodal Training

OralGPT. [NeurIPS'25 | CVPR'26] The official repo of OralGPT & MMOral Bench.

SPEC. [CVPR 2024] The official implementation of paper "synthesize, diagnose, and optimize: towards fine-grained vision-language understanding"

biomlbench. Benchmark agents on BioML tasks

DiDE. Code for EMNLP 2022 paper “Distilled Dual-Encoder Model for Vision-Language Understanding”

GPFM. The official implementation of GPFM

embedding-atlas. Embedding Atlas is a tool that provides interactive visualizations for large embeddings. It allows you to visualize, cross-filter, and search embeddings and metadata.

Patho-AgenticRAG. [AAAI-2026] Patho-AgenticRAG: Towards Multimodal Agentic Retrieval-Augmented Generation for Pathology VLMs via Reinforcement Learning

Paper2Video. [ICCV 2025] Preacher: Paper-to-Video Agentic System

protected-attrib-prediction. Code for the paper "Towards a framework for discovering mechanisms underlying AI prediction of protected attributes"

Awesome-Scientific-Datasets-and-LLMs. A curated collection of papers, datasets, and resources on Scientific Datasets and Large Language Models (LLMs)

DiagGym. A virtual clinical environment for self‑evolving LLM diagnostic agents.

superclass. [NeurIPS 2024] Classification Done Right for Vision-Language Pre-Training

EyeFM. Python

ELF. Ensemble Learning of Foundation Models

LIFT. The official repo for LIFT: Language-Image Alignment with Fixed Text Encoders

gigaheart. The official repo for GigaHeart model

icd-10-cm-embedding. LLM Embeddings for ICD 10 Data

isic-algorithm-example. A template for submitting algorithms to the ISIC Challenge

FairCLIP. [CVPR 2024] FairCLIP: Harnessing Fairness in Vision-Language Learning

LLM_RAG_Agent. Python

openevolve. Open-source implementation of AlphaEvolve

dinov3. Reference PyTorch implementation and models for DINOv3