Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

A Pytorch implementation of Sparsely-Gated Mixture of Experts, for massively increasing the parameter count of language models

[CVPR 2022] CLIMS: Cross Language Image Matching for Weakly Supervised Semantic Segmentation

Official repository of "Event-guided Deblurring of Unknown Exposure Time Videos" ECCV 2022 paper(Oral).

Adversarial Erasing Framework via Triplet with Gated Pyramid Pooling Layer for Weakly Supervised Semantic Segmentation, ECCV2022

Official repository for CVPR 2023 paper: WSSS via Adversarial Learning of Classifier and Reconstructor

some mixture of experts architecture implementations

Official code for Class Tokens Infusion for Weakly Supervised Semantic Segmentation, CVPR2024

Official respository for ECCV24 paper "Diffusion-Guided Weakly Supervised Semantic Segmentation"

[ICCV 2025] FiVE-Bench: A Fine-grained Video Editing Benchmark for Evaluating Emerging Diffusion and Rectified Flow Models

[arXiv 2025] Delta Velocity Rectified Flow for Text-to-Image Editing

Official implementation of "SplitFlow: Flow Decomposition for Inversion-Free Text-to-Image Editing (NeurIPS 2025)"

Official code for Phase Concentration and Shortcut Suppression for Weakly Supervised Semantic Segmentation, ECCV2024