{"total":69,"rows":[{"id":"2410.12761","title":"SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation","created":"2024-10-16","cited_by_count":133,"area":"diffusion"},{"id":"2404.08031","title":"Latent Guard: a Safety Framework for Text-to-image Generation","created":"2024-04-11","cited_by_count":71,"area":null},{"id":"2405.03486","title":"UnsafeBench: Benchmarking Image Safety Classifiers on Real-World and AI-Generated Images","created":"2024-05-06","cited_by_count":53,"area":null},{"id":"2403.17064","title":"Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions","created":"2024-03-25","cited_by_count":41,"area":"diffusion"},{"id":"2411.09259","title":"Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey","created":"2024-11-14","cited_by_count":32,"area":"safety"},{"id":"2409.19365","title":"Conditional Image Synthesis with Diffusion Models: A Survey","created":"2024-09-28","cited_by_count":29,"area":"diffusion"},{"id":"2402.05947","title":"Separable Multi-Concept Erasure from Diffusion Models","created":"2024-02-03","cited_by_count":28,"area":"diffusion"},{"id":"2504.01081","title":"ShieldGemma 2: Robust and Tractable Image Content Moderation","created":"2025-04-01","cited_by_count":28,"area":null},{"id":"2505.12677","title":"CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Models","created":"2025-05-19","cited_by_count":27,"area":"diffusion"},{"id":"2405.13360","title":"How to Trace Latent Generative Model Generated Images without Artificial Watermark?","created":"2024-05-22","cited_by_count":26,"area":"diffusion"},{"id":"2412.07658","title":"TraSCE: Trajectory Steering for Concept Erasure","created":"2024-12-10","cited_by_count":26,"area":"diffusion"},{"id":"2408.12692","title":"Rethinking Training for De-biasing Text-to-Image Generation: Unlocking the Potential of Stable Diffusion","created":"2024-08-22","cited_by_count":22,"area":"diffusion"},{"id":"2412.10493","title":"AlignGuard: Scalable Safety Alignment for Text-to-Image Generation","created":"2024-12-13","cited_by_count":20,"area":"alignment"},{"id":"2404.02697","title":"Which Model Generated This Image? A Model-Agnostic Approach for Origin Attribution","created":"2024-04-03","cited_by_count":16,"area":null},{"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":"2411.18289","title":"Don't Let Your Robot be Harmful: Responsible Robotic Manipulation via Safety-as-Policy","created":"2024-11-27","cited_by_count":9,"area":null},{"id":"2506.10632","title":"Hessian Geometry of Latent Space in Generative Models","created":"2025-06-12","cited_by_count":9,"area":"diffusion"},{"id":"2506.13298","title":"Fair Generation without Unfair Distortions: Debiasing Text-to-Image Generation with Entanglement-Free Attention","created":"2025-06-16","cited_by_count":9,"area":"diffusion"},{"id":"2404.05783","title":"A Survey on Responsible Generative AI: What to Generate and What Not","created":"2024-04-08","cited_by_count":8,"area":null},{"id":"2412.18810","title":"FairGen: Enhancing Fairness in Text-to-Image Diffusion Models via Self-Discovering Latent Directions","created":"2024-12-25","cited_by_count":8,"area":"diffusion"},{"id":"2501.15562","title":"CE-SDWV: Effective and Efficient Concept Erasure for Text-to-Image Diffusion Models via a Semantic-Driven Word Vocabulary","created":"2025-01-26","cited_by_count":8,"area":"diffusion"},{"id":"2512.12196","title":"AutoMV: An Automatic Multi-Agent System for Music Video Generation","created":"2025-12-13","cited_by_count":8,"area":null},{"id":"2412.05538","title":"Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models","created":"2024-12-07","cited_by_count":7,"area":null},{"id":"2412.18123","title":"AEIOU: A Unified Defense Framework against NSFW Prompts in Text-to-Image Models","created":"2024-12-24","cited_by_count":7,"area":null},{"id":"2503.13994","title":"TarPro: Targeted Protection against Malicious Image Editing","created":"2025-03-18","cited_by_count":7,"area":null},{"id":"2510.21363","title":"FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models","created":"2025-10-24","cited_by_count":7,"area":"diffusion"},{"id":"2409.18214","title":"Trustworthy Text-to-Image Diffusion Models: A Timely and Focused Survey","created":"2024-09-26","cited_by_count":6,"area":"diffusion"},{"id":"2503.18324","title":"Plug-and-Play Interpretable Responsible Text-to-Image Generation via Dual-Space Multi-facet Concept Control","created":"2025-03-24","cited_by_count":5,"area":null},{"id":"2504.02828","title":"Concept Lancet: Image Editing with Compositional Representation Transplant","created":"2025-04-03","cited_by_count":4,"area":"diffusion"},{"id":"2511.18684","title":"Now You See It, Now You Don't - Instant Concept Erasure for Safe Text-to-Image and Video Generation","created":"2025-11-24","cited_by_count":4,"area":"safety"},{"id":"2512.04267","title":"UniLight: A Unified Representation for Lighting","created":"2025-12-03","cited_by_count":4,"area":null},{"id":"2603.25994","title":"Neighbor-Aware Localized Concept Erasure in Text-to-Image Diffusion Models","created":"2026-03-27","cited_by_count":4,"area":"diffusion"},{"id":"2407.11104","title":"Exploring the Potentials and Challenges of Deep Generative Models in Product Design Conception","created":"2024-07-15","cited_by_count":3,"area":null},{"id":"2502.02225","title":"Exploring the latent space of diffusion models directly through singular value decomposition","created":"2025-02-04","cited_by_count":3,"area":"diffusion"},{"id":"2503.02078","title":"Superscopes: Amplifying Internal Feature Representations for Language Model Interpretation","created":"2025-03-03","cited_by_count":3,"area":"mechinterp"},{"id":"2509.15257","title":"RespoDiff: Dual-Module Bottleneck Transformation for Responsible & Faithful T2I Generation","created":"2025-09-18","cited_by_count":3,"area":"diffusion"},{"id":"2512.03749","title":"Fully Unsupervised Self-debiasing of Text-to-Image Diffusion Models","created":"2025-12-03","cited_by_count":3,"area":"diffusion"},{"id":"2502.17537","title":"Rethinking the Vulnerability of Concept Erasure and a New Method","created":"2025-02-24","cited_by_count":2,"area":"diffusion"},{"id":"2504.05838","title":"Mind the Trojan Horse: Image Prompt Adapter Enabling Scalable and Deceptive Jailbreaking","created":"2025-04-08","cited_by_count":2,"area":"safety"},{"id":"2507.17554","title":"An h-space Based Adversarial Attack for Protection Against Few-shot Personalization","created":"2025-07-23","cited_by_count":2,"area":"diffusion"},{"id":"2508.21099","title":"Beyond the Safety Tax: Mitigating Unsafe Text-to-Image Generation via External Safety Rectification","created":"2025-08-28","cited_by_count":2,"area":null},{"id":"2511.13750","title":"SCALEX: Scalable Concept and Latent Exploration for Diffusion Models","created":"2025-11-13","cited_by_count":2,"area":"diffusion"},{"id":"2602.07919","title":"Selective Fine-Tuning for Targeted and Robust Concept Unlearning","created":"2026-02-08","cited_by_count":2,"area":"diffusion"},{"id":"2603.11793","title":"Locating Demographic Bias at the Attention-Head Level in CLIP's Vision Encoder","created":"2026-03-12","cited_by_count":2,"area":null},{"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":"2607.14962","title":"Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation","created":"2026-07-16","cited_by_count":2,"area":"deeprl"},{"id":"2411.13982","title":"Safety Without Semantic Disruptions: Editing-free Safe Image Generation via Context-preserving Dual Latent Reconstruction","created":"2024-11-21","cited_by_count":1,"area":null},{"id":"2601.20791","title":"FAIRT2V: Training-Free Debiasing for Text-to-Video Diffusion Models","created":"2026-01-28","cited_by_count":1,"area":"diffusion"},{"id":"2603.16368","title":"Encoding Predictability and Legibility for Style-Conditioned Diffusion Policy","created":"2026-03-17","cited_by_count":1,"area":"diffusion"},{"id":"2604.09405","title":"EGLOCE: Training-Free Energy-Guided Latent Optimization for Concept Erasure","created":"2026-04-10","cited_by_count":1,"area":"diffusion"},{"id":"2605.24687","title":"HoloFair: Unified T2I Fairness Evaluation and Fair-GRPO Debiasing","created":"2026-05-23","cited_by_count":1,"area":"lr"},{"id":"2606.17257","title":"Pulling The REINS: Training-Free Safety Alignment of Video Diffusion Models via Representation Steering","created":"2026-06-15","cited_by_count":1,"area":"diffusion"},{"id":"2606.27147","title":"Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2410.04421","title":"Disentangling Regional Primitives for Image Generation","created":"2024-10-06","cited_by_count":0,"area":null},{"id":"2505.08817","title":"Towards SFW sampling for diffusion models via external conditioning","created":"2025-05-12","cited_by_count":0,"area":"diffusion"},{"id":"2505.19313","title":"Concept Reachability in Diffusion Models: Beyond Dataset Constraints","created":"2025-05-25","cited_by_count":0,"area":"diffusion"},{"id":"2507.03846","title":"Interpretable Diffusion Models with B-cos Networks","created":"2025-07-05","cited_by_count":0,"area":"diffusion"},{"id":"2508.00445","title":"AutoDebias: Automated Framework for Debiasing Text-to-Image Models","created":"2025-08-01","cited_by_count":0,"area":"safety"},{"id":"2510.22650","title":"Self-Attention Decomposition For Training Free Diffusion Editing","created":"2025-10-26","cited_by_count":0,"area":"diffusion"},{"id":"2510.26105","title":"Security Risk of Misalignment between Text and Image in Multi-modal Model","created":"2025-10-30","cited_by_count":0,"area":"diffusion"},{"id":"2512.17873","title":"Preserving Spectral Structure and Statistics in Diffusion Models","created":"2025-12-19","cited_by_count":0,"area":"diffusion"},{"id":"2602.06806","title":"RAIGen: Rare Attribute Identification in Text-to-Image Generative Models","created":"2026-02-06","cited_by_count":0,"area":"diffusion"},{"id":"2603.07066","title":"PolypSteer: Counterfactual Endoscopic Synthesis via Training-Free Activation Steering","created":"2026-03-07","cited_by_count":0,"area":"diffusion"},{"id":"2604.18167","title":"Embedding Arithmetic: A Lightweight, Tuning-Free Framework for Post-hoc Bias Mitigation in Text-to-Image Models","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2607.03397","title":"Efficient bias mitigation in T2I diffusion models using Concept Graphs","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":"2607.14945","title":"Introspective Attention Modulation for Safe Text-to-Image Generation","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2609.39688","title":"ShieldCLIP: Selective Safety Alignment for Harmful Content Mitigation in Multimodal Foundation Models","created":"2026-09-30","cited_by_count":0,"area":"alignment"},{"id":"2610.01815","title":"Debias Anything: Fairness with Diversity without Supervision in Diffusion Models","created":"2026-10-01","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}