"Paper2Slides: From Paper to Presentation in One Click"

VeloxSeg is a lightweight multimodal medical image segmentation framework that addresses the fundamental "efficiency / robustness conflict" in 3D medical image segmentation.

Official repository of ICCV 2025 CVAMD Oral paper: MK-UNet: Multi-kernel Lightweight CNN for Medical Image Segmentation

[MICCAI2024] Rethinking Abdominal Organ Segmentation (RAOS) in the clinical scenario: A robustness evaluation benchmark with challenging cases

MedDINOv3: How to adapt vision foundation models for medical image segmentation?

[Patterns (Cell subsidiary journal)] The official code for "UltraLight VM-UNet: Parallel Vision Mamba Significantly Reduces Parameters for Skin Lesion Segmentation".

[ICML 2025] Implementation of "GNN+ (ModernGNN): Can Classic GNNs Be Strong Baselines for Graph-level Tasks?"

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…

A topic-centric list of HQ open datasets.

DomainBed is a suite to test domain generalization algorithms

Project Imaging-X: A Survey of 1000+ Open-Access Medical Imaging Datasets for Foundation Model Development