Enabling Preference-driven Unlearning in Few-step Distilled Text-to-Image Diffusion Models
cs.CV, cs.LG
Submitted: 2026-10-07
Updated: 2026-10-07
Code: https://github.com/CompVis/latent-diffusion
Terminology
Sources
- GPT-4 Technical Report
- eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers
- Locality-Aware Continual Unlearning for Diffusion Models
- SafetyPairs: Isolating Safety Critical Image Features with Counterfactual Image Generation
- Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
- Wuerstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models
- Red-Teaming the Stable Diffusion Safety Filter
- ContinualFlow: Learning and Unlearning with Neural Flow Matching
- Score-Based Generative Modeling through Stochastic Differential Equations
- Continual Unlearning for Foundational Text-to-Image Models without Generalization Erosion
- Concept Unlearning by Modeling Key Steps of Diffusion Process
- Text-to-image Diffusion Models in Generative AI: A Survey
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models