[JMS 2026] A Comprehensive Survey for Real-World Industrial Surface Defect Detection: Challenges, Approaches, and Prospects (Journal of Manufacturing Systems)

Official PyTorch implementation for paper: "Is Training Necessary for Anomaly Detection?"

[ICLR 2026] The implementation of the paper Foundation Visual Encoders Are Secretly Few-Shot Anomaly Detectors

[ICLR 2025] Diffusion Feedback Helps CLIP See Better

The official GitHub page for the survey paper "CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Survey". And this paper has been accepted for publication in IEEE TPAMI.

Official implementation of "MadCLIP: Few-shot Medical Anomaly Detection with CLIP" (MICCAI 2025, Early Accepted).

[ICLR 2026] This repository is the official implementation of the paper “Boosting Medial Visual Understanding From Multi-Granular Language Learning”.

Official Implementation of NAF: Zero-Shot Feature Upsampling via Neighborhood Attention Filtering

[CVPR 25] A framework named B^2-DiffuRL for RL-based diffusion model fine-tuning.

[CVPR 2026] 🔥🔥 Official Repo of USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning

🥢像老乡鸡🐔那样做饭。主要部分于2024年完工，非老乡鸡官方仓库。文字来自《老乡鸡菜品溯源报告》，并做归纳、编辑与整理。CookLikeHOC.

An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional variability in sampling steps

Easy setup for mmdetection

🚀 Cross attention map tools for huggingface/diffusers

Hackable and optimized Transformers building blocks, supporting a composable construction.

Repository for Mode-Guided Latent Diffusion for Dataset Distillation

A collection of resources on personalized image generation.

Official implementation of BLIP3o-Series

Official implementation of the paper "Attentive Eraser: Unleashing Diffusion Model’s Object Removal Potential via Self-Attention Redirection Guidance" (AAAI 2025 Oral)

[NeurIPS 2024] Official Implementation of GrounDiT

Official implemention of "Make It Count: Text-to-Image Generation with an Accurate Number of Objects" (CVPR 2025)

[CVPR 2025] Official Pytorch Code for Spatial Transport Optimization by Repositioning Attention Map for Training-Free Text-to-Image Synthesis

Code for the paper "Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models"

[ECCV 2024] Powerful and Flexible: Personalized Text-to-Image Generation via Reinforcement Learning

[ICCV 2025] Official implementation for KV-Edit: Training-Free Image Editing for Precise Background Preservation

Official code for K-LoRA (CVPR 2025)

LoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models