{"total":54,"rows":[{"id":"2403.06135","title":"MACE: Mass Concept Erasure in Diffusion Models","created":"2024-03-10","cited_by_count":307,"area":"diffusion"},{"id":"2405.15234","title":"Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models","created":"2024-05-24","cited_by_count":168,"area":"diffusion"},{"id":"2501.18052","title":"SAeUron: Interpretable Concept Unlearning in Diffusion Models with Sparse Autoencoders","created":"2025-01-29","cited_by_count":80,"area":"diffusion"},{"id":"2502.17516","title":"A Survey on Mechanistic Interpretability for Multi-Modal Foundation Models","created":"2025-02-22","cited_by_count":34,"area":"mllm"},{"id":"2405.07288","title":"Erasing Concepts from Text-to-Image Diffusion Models with Few-shot Unlearning","created":"2024-05-12","cited_by_count":29,"area":"diffusion"},{"id":"2405.01008","title":"On Mechanistic Knowledge Localization in Text-to-Image Generative Models","created":"2024-05-02","cited_by_count":28,"area":null},{"id":"2404.11534","title":"Decomposing and Editing Predictions by Modeling Model Computation","created":"2024-04-17","cited_by_count":19,"area":null},{"id":"2407.11867","title":"Targeted Unlearning with Single Layer Unlearning Gradient","created":"2024-07-16","cited_by_count":18,"area":"safety"},{"id":"2503.07050","title":"TIDE : Temporal-Aware Sparse Autoencoders for Interpretable Diffusion Transformers in Image Generation","created":"2025-03-10","cited_by_count":16,"area":"diffusion"},{"id":"2503.07389","title":"TRCE: Towards Reliable Malicious Concept Erasure in Text-to-Image Diffusion Models","created":"2025-03-10","cited_by_count":15,"area":"diffusion"},{"id":"2404.19227","title":"Espresso: Robust Concept Filtering in Text-to-Image Models","created":"2024-04-30","cited_by_count":14,"area":"diffusion"},{"id":"2501.06751","title":"Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models","created":"2025-01-12","cited_by_count":13,"area":"diffusion"},{"id":"2503.15197","title":"Detect-and-Guide: Self-regulation of Diffusion Models for Safe Text-to-Image Generation via Guideline Token Optimization","created":"2025-03-19","cited_by_count":13,"area":"diffusion"},{"id":"2412.02542","title":"Unveiling Concept Attribution in Diffusion Models","created":"2024-12-03","cited_by_count":11,"area":"diffusion"},{"id":"2509.21379","title":"SAEmnesia: Erasing Concepts in Diffusion Models with Supervised Sparse Autoencoders","created":"2025-09-23","cited_by_count":10,"area":"diffusion"},{"id":"2404.08030","title":"Rethinking Artistic Copyright Infringements in the Era of Text-to-Image Generative Models","created":"2024-04-11","cited_by_count":9,"area":"diffusion"},{"id":"2501.18877","title":"Mitigating Sexual Content Generation via Embedding Distortion in Text-conditioned Diffusion Models","created":"2025-01-31","cited_by_count":7,"area":"diffusion"},{"id":"2503.16835","title":"Safe and Reliable Diffusion Models via Subspace Projection","created":"2025-03-21","cited_by_count":7,"area":"diffusion"},{"id":"2505.18832","title":"Localizing Knowledge in Diffusion Transformers","created":"2025-05-24","cited_by_count":7,"area":"diffusion"},{"id":"2602.05859","title":"DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders","created":"2026-02-05","cited_by_count":7,"area":"diffusion"},{"id":"2411.08224","title":"Joint Diffusion models in Continual Learning","created":"2024-11-12","cited_by_count":6,"area":"diffusion"},{"id":"2404.09172","title":"LoopAnimate: Loopable Salient Object Animation","created":"2024-04-14","cited_by_count":5,"area":"diffusion"},{"id":"2502.09935","title":"Precise Parameter Localization for Textual Generation in Diffusion Models","created":"2025-02-14","cited_by_count":5,"area":"diffusion"},{"id":"2410.22370","title":"Survey of User Interface Design and Interaction Techniques in Generative AI Applications","created":"2024-10-28","cited_by_count":4,"area":null},{"id":"2507.19894","title":"Generative Model Unlearning: A Survey through Target Events, Unlearning Operators, and Evaluation Protocols","created":"2025-07-26","cited_by_count":4,"area":"safety"},{"id":"2602.11910","title":"TADA! Tuning Audio Diffusion Models through Activation Steering","created":"2026-02-12","cited_by_count":4,"area":"diffusion"},{"id":"2410.04891","title":"Low-Rank Continual Personalization of Diffusion Models","created":"2024-10-07","cited_by_count":3,"area":"diffusion"},{"id":"2601.08623","title":"SafeRedir: Prompt Embedding Redirection for Robust Unlearning in Image Generation Models","created":"2026-01-13","cited_by_count":3,"area":"safety"},{"id":"2602.19631","title":"Localized Concept Erasure in Text-to-Image Diffusion Models via High-Level Representation Misdirection","created":"2026-02-23","cited_by_count":3,"area":"diffusion"},{"id":"2504.14554","title":"REDEditing: Relationship-Driven Precise Backdoor Poisoning on Text-to-Image Diffusion Models","created":"2025-04-20","cited_by_count":2,"area":"diffusion"},{"id":"2505.02824","title":"Towards Dataset Copyright Evasion Attack against Personalized Text-to-Image Diffusion Models","created":"2025-05-05","cited_by_count":2,"area":"diffusion"},{"id":"2512.22877","title":"M-ErasureBench: A Comprehensive Multimodal Evaluation Benchmark for Concept Erasure in Diffusion Models","created":"2025-12-28","cited_by_count":2,"area":"diffusion"},{"id":"2604.06052","title":"Attention, May I Have Your Decision? Localizing Generative Choices in Diffusion Models","created":"2026-03-29","cited_by_count":2,"area":"diffusion"},{"id":"2609.23658","title":"Why Do Video Diffusion Models Violate Physics? Unveiling the Flaws in Attention Mechanisms","created":"2026-09-20","cited_by_count":2,"area":"diffusion"},{"id":"2412.03400","title":"Implicit Priors Editing in Stable Diffusion via Targeted Token Adjustment","created":"2024-12-04","cited_by_count":1,"area":"diffusion"},{"id":"2506.08991","title":"Do Concept Replacement Techniques Really Erase Unacceptable Concepts?","created":"2025-06-10","cited_by_count":1,"area":"diffusion"},{"id":"2507.03636","title":"SecureT2I: No More Unauthorized Manipulation on AI Generated Images from Prompts","created":"2025-07-04","cited_by_count":1,"area":"diffusion"},{"id":"2510.27285","title":"Rethinking Robust Adversarial Concept Erasure in Diffusion Models","created":"2025-10-31","cited_by_count":1,"area":"diffusion"},{"id":"2605.24624","title":"Vision-Language Binding in In-Context Image Generation","created":"2026-05-23","cited_by_count":1,"area":null},{"id":"2606.00477","title":"Do Text Edits Generalize to Visual Generation? Benchmarking Cross-Modal Knowledge Editing in UMMs","created":"2026-05-30","cited_by_count":1,"area":null},{"id":"2608.10985","title":"PEAK: Precise and Persistent Concept Erasure via k-Sparse Autoencoders","created":"2026-08-11","cited_by_count":1,"area":"diffusion"},{"id":"2610.05601","title":"Your Unlearning Gives You Away: Identifying Erased Concepts in Diffusion Models","created":"2026-10-04","cited_by_count":1,"area":"diffusion"},{"id":"2508.03221","title":"BadBlocks: Low-Cost and Stealthy Backdoor Attacks Tailored for Text-to-Image Diffusion Models","created":"2025-08-05","cited_by_count":0,"area":"diffusion"},{"id":"2509.26235","title":"Interpret, prune and distill Donut : towards lightweight VLMs for VQA on document","created":"2025-09-30","cited_by_count":0,"area":"mllm"},{"id":"2602.08059","title":"DICE: Disentangling Artist Style from Content via Contrastive Subspace Decomposition in Diffusion Models","created":"2026-02-08","cited_by_count":0,"area":"diffusion"},{"id":"2605.01480","title":"AttnRouter: Per-Category Attention Routing for Training-Free Image Editing on MMDiT","created":"2026-05-02","cited_by_count":0,"area":"diffusion"},{"id":"2606.25548","title":"Concept Removal for Frontier Image Generative Models","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2607.03180","title":"FairFlow: Demystifying and Mitigating Stereotype Bias in Text-to-Image Diffusion Transformers","created":"2026-07-03","cited_by_count":0,"area":"diffusion"},{"id":"2607.06120","title":"AEGIS: A Mechanism-Guided Defense against Visual Synonym Jailbreaks in Text-to-Image Models","created":"2026-07-07","cited_by_count":0,"area":"diffusion"},{"id":"2607.17138","title":"Denoising Models Develop Human-Like Perceptual Illusion Representations Across Architectures","created":"2026-07-19","cited_by_count":0,"area":null},{"id":"2608.14172","title":"Concept Guidance: Precise, Training-Free Latent Control for Text-to-Image Generation","created":"2026-08-14","cited_by_count":0,"area":"diffusion"},{"id":"2608.15341","title":"TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models","created":"2026-08-15","cited_by_count":0,"area":"diffusion"},{"id":"2609.20139","title":"Cross-Modal Attention Acts as a Frequency Filter: Why Verbose Prompts Improve Robustness in Vision-Language Models","created":"2026-09-17","cited_by_count":0,"area":"mllm"},{"id":"2610.06945","title":"Beyond the Linear Representation Hypothesis: Non-Linear Activation Steering in Text-to-Image Models","created":"2026-10-03","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}