SafeEditor: Unified MLLM for Efficient Post-hoc T2I Safety Editing
"文本到图像模型" 相关文章
Semantic Surgery: Zero-Shot Concept Erasure in Diffusion Models
Beyond Fixed Anchors: Precisely Erasing Concepts with Sibling Exclusive Counterparts
DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models
SafeGuider: Robust and Practical Content Safety Control for Text-to-Image Models
SafeGuider: Robust and Practical Content Safety Control for Text-to-Image Models
Memory Self-Regeneration: Uncovering Hidden Knowledge in Unlearned Models
MetaLogic: Robustness Evaluation of Text-to-Image Models via Logically Equivalent Prompts
Beyond the Prompt: Gender Bias in Text-to-Image Models, with a Case Study on Hospital Professions
Free Lunch Alignment of Text-to-Image Diffusion Models without Preference Image Pairs
DyME: Dynamic Multi-Concept Erasure in Diffusion Models with Bi-Level Orthogonal LoRA Adaptation
Moment- and Power-Spectrum-Based Gaussianity Regularization for Text-to-Image Models
Exploring Diffusion Models for Generative Forecasting of Financial Charts
SafeFix: Targeted Model Repair via Controlled Image Generation
UnGuide: Learning to Forget with LoRA-Guided Diffusion Models
Zero-Residual Concept Erasure via Progressive Alignment in Text-to-Image Model
Finding Dori: Memorization in Text-to-Image Diffusion Models Is Less Local Than Assumed
Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning
Towards Evaluating Robustness of Prompt Adherence in Text to Image Models
How BRIA AI used distributed training in Amazon SageMaker to train latent diffusion foundation models for commercial use
