{"total":83,"rows":[{"id":"2412.12974","title":"Attentive Eraser: Unleashing Diffusion Model's Object Removal Potential via Self-Attention Redirection Guidance","created":"2024-12-17","cited_by_count":63,"area":"diffusion"},{"id":"2502.04320","title":"ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features","created":"2025-02-06","cited_by_count":52,"area":"diffusion"},{"id":"2412.11520","title":"EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splatting","created":"2024-12-16","cited_by_count":41,"area":"diffusion"},{"id":"2409.19365","title":"Conditional Image Synthesis with Diffusion Models: A Survey","created":"2024-09-28","cited_by_count":29,"area":"diffusion"},{"id":"2506.01949","title":"IMAGHarmony: Controllable Image Editing with Consistent Object Quantity and Layout","created":"2025-06-02","cited_by_count":28,"area":"diffusion"},{"id":"2410.00321","title":"A Cat Is A Cat (Not A Dog!): Unraveling Information Mix-ups in Text-to-Image Encoders through Causal Analysis and Embedding Optimization","created":"2024-10-01","cited_by_count":19,"area":"diffusion"},{"id":"2508.07519","title":"Exploring Multimodal Diffusion Transformers for Enhanced Prompt-based Image Editing","created":"2025-08-11","cited_by_count":17,"area":"diffusion"},{"id":"2504.10317","title":"Analysis of Attention in Video Diffusion Transformers","created":"2025-04-14","cited_by_count":15,"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":"2507.23300","title":"Training-free Geometric Image Editing on Diffusion Models","created":"2025-07-31","cited_by_count":13,"area":"diffusion"},{"id":"2405.19708","title":"Text Guided Image Editing with Automatic Concept Locating and Forgetting","created":"2024-05-30","cited_by_count":12,"area":"diffusion"},{"id":"2408.01014","title":"Growth Inhibitors for Suppressing Inappropriate Image Concepts in Diffusion Models","created":"2024-08-02","cited_by_count":12,"area":"diffusion"},{"id":"2409.09144","title":"PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage","created":"2024-09-13","cited_by_count":12,"area":"diffusion"},{"id":"2503.10081","title":"AdvPaint: Protecting Images from Inpainting Manipulation via Adversarial Attention Disruption","created":"2025-03-13","cited_by_count":11,"area":"diffusion"},{"id":"2411.16503","title":"Noise Diffusion for Enhancing Semantic Faithfulness in Text-to-Image Synthesis","created":"2024-11-25","cited_by_count":9,"area":"diffusion"},{"id":"2412.04715","title":"Addressing Text Embedding Leakage in Diffusion-based Image Editing","created":"2024-12-06","cited_by_count":7,"area":"diffusion"},{"id":"2503.07677","title":"PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity","created":"2025-03-10","cited_by_count":7,"area":"diffusion"},{"id":"2503.10350","title":"Enhancing Facial Privacy Protection via Weakening Diffusion Purification","created":"2025-03-13","cited_by_count":7,"area":"diffusion"},{"id":"2503.16406","title":"VerbDiff: Text-Only Diffusion Models with Enhanced Interaction Awareness","created":"2025-03-20","cited_by_count":7,"area":"diffusion"},{"id":"2504.12027","title":"Understanding Attention Mechanism in Video Diffusion Models","created":"2025-04-16","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":"2510.20217","title":"EditInfinity: Image Editing with Binary-Quantized Generative Models","created":"2025-10-23","cited_by_count":7,"area":"diffusion"},{"id":"2603.12749","title":"SLICE: Semantic Latent Injection via Compartmentalized Embedding for Image Watermarking","created":"2026-03-13","cited_by_count":7,"area":"diffusion"},{"id":"2409.12314","title":"Understanding Implosion in Text-to-Image Generative Models","created":"2024-09-18","cited_by_count":6,"area":"diffusion"},{"id":"2501.14524","title":"Training-Free Style and Content Transfer by Leveraging U-Net Skip Connections in Stable Diffusion","created":"2025-01-24","cited_by_count":6,"area":"diffusion"},{"id":"2411.10232","title":"ColorEdit: Training-free Image-Guided Color editing with diffusion model","created":"2024-11-15","cited_by_count":4,"area":"diffusion"},{"id":"2504.09202","title":"From Visual Explanations to Counterfactual Explanations with Latent Diffusion","created":"2025-04-12","cited_by_count":4,"area":"diffusion"},{"id":"2505.10551","title":"Does Feasibility Matter? Understanding the Impact of Feasibility on Synthetic Training Data","created":"2025-05-15","cited_by_count":4,"area":"diffusion"},{"id":"2507.17853","title":"Detail++: Training-Free Detail Enhancer for T2I Diffusion Models","created":"2025-07-23","cited_by_count":4,"area":"diffusion"},{"id":"2411.08196","title":"Latent Space Disentanglement in Diffusion Transformers Enables Precise Zero-shot Semantic Editing","created":"2024-11-12","cited_by_count":3,"area":"diffusion"},{"id":"2505.11753","title":"X-Edit: Detecting and Localizing Edits in Images Altered by Text-Guided Diffusion Models","created":"2025-05-16","cited_by_count":3,"area":"diffusion"},{"id":"2509.24773","title":"VSSFlow: Unifying Video-conditioned Sound and Speech Generation via Joint Learning","created":"2025-09-29","cited_by_count":3,"area":"diffusion"},{"id":"2510.04668","title":"ConceptSplit: Decoupled Multi-Concept Personalization of Diffusion Models via Token-wise Adaptation and Attention Disentanglement","created":"2025-10-06","cited_by_count":3,"area":"diffusion"},{"id":"2511.05219","title":"FreeControl: Efficient, Training-Free Structural Control via One-Step Attention Extraction","created":"2025-11-07","cited_by_count":3,"area":"diffusion"},{"id":"2511.08252","title":"Melodia: Training-Free Music Editing Guided by Attention Probing in Diffusion Models","created":"2025-11-11","cited_by_count":3,"area":"diffusion"},{"id":"2512.12375","title":"V-Warper: Appearance-Consistent Video Diffusion Personalization via Value Warping","created":"2025-12-13","cited_by_count":3,"area":"diffusion"},{"id":"2601.02211","title":"TexTailor: Inference-Time Textual Guidance Tailoring for Multimodal Diffusion Transformers","created":"2026-01-05","cited_by_count":3,"area":"diffusion"},{"id":"2601.06338","title":"Circuit Mechanisms for Spatial Relation Generation in Diffusion Transformers","created":"2026-01-09","cited_by_count":3,"area":"diffusion"},{"id":"2603.06178","title":"Making Training-Free Diffusion Segmentors Scale with the Generative Power","created":"2026-03-06","cited_by_count":3,"area":"diffusion"},{"id":"2409.17740","title":"AnyLogo: Symbiotic Subject-Driven Diffusion System with Gemini Status","created":"2024-09-26","cited_by_count":2,"area":"diffusion"},{"id":"2501.13692","title":"Training-Free, Identity-Preserving Image Editing for Fashion Pose Alignment and Normalization","created":"2025-01-23","cited_by_count":2,"area":"diffusion"},{"id":"2505.00751","title":"InstructAttribute: Fine-grained Object Attributes editing with Instruction","created":"2025-05-01","cited_by_count":2,"area":"diffusion"},{"id":"2506.18438","title":"CPAM: Context-Preserving Adaptive Manipulation for Zero-Shot Real Image Editing","created":"2025-06-23","cited_by_count":2,"area":"diffusion"},{"id":"2507.10578","title":"When and Where do Data Poisons Attack Textual Inversion?","created":"2025-07-11","cited_by_count":2,"area":"diffusion"},{"id":"2508.18235","title":"Sealing The Backdoor: Unlearning Adversarial Text Triggers In Diffusion Models Using Knowledge Distillation","created":"2025-08-20","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":"2605.14270","title":"Diagnosing and Correcting Concept Omission in Multimodal Diffusion Transformers","created":"2026-05-14","cited_by_count":2,"area":"diffusion"},{"id":"2408.13335","title":"Latent Space Disentanglement in Diffusion Transformers Enables Zero-shot Fine-grained Semantic Editing","created":"2024-08-23","cited_by_count":1,"area":"diffusion"},{"id":"2410.14429","title":"FashionR2R: Texture-preserving Rendered-to-Real Image Translation with Diffusion Models","created":"2024-10-18","cited_by_count":1,"area":"diffusion"},{"id":"2412.20062","title":"MADiff: Text-Guided Fashion Image Editing with Mask Prediction and Attention-Enhanced Diffusion","created":"2024-12-28","cited_by_count":1,"area":"diffusion"},{"id":"2504.03471","title":"Dynamic Importance in Diffusion U-Net for Enhanced Image Synthesis","created":"2025-04-04","cited_by_count":1,"area":"diffusion"},{"id":"2504.05594","title":"Tuning-Free Image Editing with Fidelity and Editability via Unified Latent Diffusion Model","created":"2025-04-08","cited_by_count":1,"area":"diffusion"},{"id":"2505.19425","title":"Structure Disruption: Subverting Malicious Diffusion-Based Inpainting via Self-Attention Query Perturbation","created":"2025-05-26","cited_by_count":1,"area":"diffusion"},{"id":"2507.13598","title":"GIFT: Gradient-aware Immunization of diffusion models against malicious Fine-Tuning with safe concepts retention","created":"2025-07-18","cited_by_count":1,"area":"diffusion"},{"id":"2508.02004","title":"Devil is in the Detail: Towards Injecting Fine Details of Image Prompt in Image Generation via Conflict-free Guidance and Stratified Attention","created":"2025-08-04","cited_by_count":1,"area":"diffusion"},{"id":"2509.03044","title":"DCDB: Dynamic Conditional Dual Diffusion Bridge for Ill-posed Multi-Tasks","created":"2025-09-03","cited_by_count":1,"area":"diffusion"},{"id":"2605.20777","title":"AttriStory: Fine-grained Attribute Realization for Visual Storytelling with Diffusion Models","created":"2026-05-20","cited_by_count":1,"area":"diffusion"},{"id":"2606.13247","title":"EPIG: Emotion-Based Prompting for Personalised Image Generation","created":"2026-06-11","cited_by_count":1,"area":"diffusion"},{"id":"2412.03812","title":"Pinco: Position-induced Consistent Adapter for Diffusion Transformer in Foreground-conditioned Inpainting","created":"2024-12-05","cited_by_count":0,"area":"diffusion"},{"id":"2502.20904","title":"DiffBrush:Just Painting the Art by Your Hands","created":"2025-02-28","cited_by_count":0,"area":"diffusion"},{"id":"2505.15812","title":"Leveraging the Powerful Attention of a Pre-trained Diffusion Model for Exemplar-based Image Colorization","created":"2025-05-21","cited_by_count":0,"area":"diffusion"},{"id":"2506.09955","title":"Canonical Latent Representations in Conditional Diffusion Models","created":"2025-06-11","cited_by_count":0,"area":"diffusion"},{"id":"2506.11772","title":"CLIP Meets Diffusion: A Synergistic Approach to Anomaly Detection","created":"2025-06-13","cited_by_count":0,"area":"diffusion"},{"id":"2508.11550","title":"Training-Free Anomaly Generation via Dual-Attention Enhancement in Diffusion Model","created":"2025-08-15","cited_by_count":0,"area":"diffusion"},{"id":"2509.18948","title":"One-shot Embroidery Customization via Contrastive LoRA Modulation","created":"2025-09-23","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":"2601.02987","title":"LAMS-Edit: Latent and Attention Mixing with Schedulers for Improved Content Preservation in Diffusion-Based Image and Style Editing","created":"2026-01-06","cited_by_count":0,"area":"diffusion"},{"id":"2602.10662","title":"Dynamic Frequency Modulation for Controllable Text-driven Image Generation","created":"2026-02-11","cited_by_count":0,"area":"diffusion"},{"id":"2602.13585","title":"Diff-Aid: Inference-time Adaptive Interaction Denoising for Rectified Text-to-Image Generation","created":"2026-02-14","cited_by_count":0,"area":"diffusion"},{"id":"2603.02883","title":"SemanticDialect: Semantic-Aware Mixed-Format Quantization for Video Diffusion Transformers","created":"2026-03-03","cited_by_count":0,"area":"diffusion"},{"id":"2603.13299","title":"DreamReader: An Interpretability Toolkit for Text-to-Image Models","created":"2026-03-02","cited_by_count":0,"area":"diffusion"},{"id":"2603.28114","title":"Attention Frequency Modulation: Training-Free Spectral Modulation of Diffusion Cross-Attention","created":"2026-03-30","cited_by_count":0,"area":"diffusion"},{"id":"2604.25128","title":"ResetEdit: Precise Text-guided Editing of Generated Image via Resettable Starting Latent","created":"2026-04-28","cited_by_count":0,"area":"diffusion"},{"id":"2605.19698","title":"Awakening the Hydra: Stabilizing Multi-Concept Backdoor Injection in Text-to-Image Diffusion Models","created":"2026-05-19","cited_by_count":0,"area":"diffusion"},{"id":"2605.25763","title":"AI-T2I: Aggregating-and-Isolating Cross-Attention to Diffusion Models for Text-to-Image Synthesis","created":"2026-05-25","cited_by_count":0,"area":"diffusion"},{"id":"2606.04107","title":"Reflection Separation from a Single Image via Joint Latent Diffusion","created":"2026-06-02","cited_by_count":0,"area":"diffusion"},{"id":"2606.10046","title":"Inside the Latent Flow: Causal Deciphering of Attention Dynamics in Audio Separation Foundation Models","created":"2026-06-08","cited_by_count":0,"area":"diffusion"},{"id":"2606.14035","title":"Toward 360-Degree Indoor Panorama Editing via Tuning-Free Diffusion Model with Refocusing Cross-Attention","created":"2026-06-12","cited_by_count":0,"area":"diffusion"},{"id":"2607.02563","title":"Attention Dynamics in Diffusion Models: A Visual Analytics Framework for Human-AI Collaboration","created":"2026-06-28","cited_by_count":0,"area":"diffusion"},{"id":"2607.12121","title":"FlashDiff: Efficient Regional Execution and Scheduling for Diffusion Model Serving","created":"2026-07-13","cited_by_count":0,"area":"diffusion"},{"id":"2609.32420","title":"Carnator: Fast Text-to-Video Generation with Generation-Native Compatibility-Guided Cross-Request Reuse","created":"2026-09-26","cited_by_count":0,"area":"diffusion"},{"id":"2609.36832","title":"Motion Concept Unlearning in Video Diffusion Models","created":"2026-09-29","cited_by_count":0,"area":"diffusion"},{"id":"2610.17829","title":"QK-Edit: Revisiting Attention-based Injection in MM-DiT for Image and Video Editing","created":"2026-10-13","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}