Code repo for Squeezed Diffusion Models

Official Implementation of Diffusion Step Annealing (DiSA) in Autoregressive Image Generation

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

[npj Digital Medicine] The official repository for "Large-Vocabulary Segmentation for Medical Images with Text Prompts"

Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabilities.

[CVPR 2025] The First Investigation of CoT Reasoning (RL, TTS, Reflection) in Image Generation

[CVPR 2025] Learning Flow Fields in Attention for Controllable Person Image Generation

More relighting!

[MICCAI 2024 Early Accept, Oral] Aligning Medical Images with General Knowledge from Large Language Models

PyTorch implementation for "WDM: 3D Wavelet Diffusion Models for High-Resolution Medical Image Synthesis" (DGM4MICCAI 2024)

TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones

A PyTorch implementation of the paper "ZigMa: A DiT-Style Mamba-based Diffusion Model" (ECCV 2024)

Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors

[ICLR'23 Spotlight🔥] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling"

Large Kernel Vision Mamba UNet for Medical Image Segmentation

Multi-Aspect Vision Language Pretraining - CVPR2024

[MICCAI 2022 Best Paper Finalist] Bayesian Pseudo Labels: Expectation Maximization for Robust and Efficient Semi Supervised Segmentation

MEDPSeg: Official implementation of Modified EfficientDet for Pulmonary Polymorphic Segmentation

Medical image processing in Python

Unsupervised Instance Segmentation in Microscopy

[ECCVW 2022] The codes for the work "Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation"

Repository for "Deformable 3D Convolution for Video Super-Resolution", SPL, 2020

Medical Diffusion: This repository contains the code to our paper Medical Diffusion: Denoising Diffusion Probabilistic Models for 3D Medical Image Synthesis

Medical Image Vision Operators, such as RoIAlign, DCNv1, DCNv2 and NMS for both 2/3D images.

[ICCV 2023] CLIP-Driven Universal Model; Rank first in MSD Competition.

[IEEE TMI] Official Implementation for UNet++

Code for CRATE (Coding RAte reduction TransformEr).

Mask Transfiner for High-Quality Instance Segmentation, CVPR 2022