Concept Bottleneck Models, ICML 2020

PyTorch Explain: Interpretable Deep Learning in Python.

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

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

[pip install medmnist] 18x Standardized Datasets for 2D and 3D Biomedical Image Classification

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

Tool for robust segmentation of >100 important anatomical structures in CT and MR images

[ICLR 23] A new framework to transform any neural networks into an interpretable concept-bottleneck-model (CBM) without needing labeled concept data

Code for Stochastic Concept Bottleneck Models

CVPR 2023: Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification

Official code for "Probabilistic Concept Bottleneck Models (ICML 2023)"

Easy and Efficient dLLM Fine-Tuning

An Open-access Dataset for Liver Lesion Diagnosis on Multi-phase MRI

This is the official repository for the IEEE TMI paper titled "Large Language Model with Region-Guided Referring and Grounding for CT Report Generation".

Transition Models

Unofficial implementation of "Simplifying, Stabilizing & Scaling Continuous-Time Consistency Models" for MNIST

Jodi: Unification of Visual Generation and Understanding via Joint Modeling

[nature biomedical engineering 2025] Official code for paper: A generalist foundation model and database for open-world medical image segmentation (MedSegX)

Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"

[CVPR'25 Highlight] Multi-modal Vision Pre-training for Medical Image Analysis

Pytorch implementation for MeanFlow

Code for the paper "Evaluating Large Language Models Trained on Code"

The official github repo for "Diffusion Language Models are Super Data Learners".

Diffusion-LM

Pytorch Implementation (unofficial) of the paper "Mean Flows for One-step Generative Modeling" by Geng et al.

JAX implementation of MeanFlow

Papers of Medical Image Analysis on CVPR

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