{"total":135,"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":"2408.13239","title":"CustomCrafter: Customized Video Generation with Preserving Motion and Concept Composition Abilities","created":"2024-08-23","cited_by_count":60,"area":null},{"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":"2412.01197","title":"InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differences","created":"2024-12-02","cited_by_count":34,"area":null},{"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":"2412.08503","title":"StyleStudio: Text-Driven Style Transfer with Selective Control of Style Elements","created":"2024-12-11","cited_by_count":26,"area":null},{"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":"2505.02370","title":"SuperEdit: Rectifying and Facilitating Supervision for Instruction-Based Image Editing","created":"2025-05-05","cited_by_count":18,"area":null},{"id":"2505.04320","title":"Multi-turn Consistent Image Editing","created":"2025-05-07","cited_by_count":18,"area":null},{"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":"2601.07823","title":"Robotic Video World Models: A Survey of Applications, Research Challenges, Future Directions","created":"2026-01-12","cited_by_count":13,"area":"wm"},{"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":"2507.17657","title":"Attention (as Discrete-Time Markov) Chains","created":"2025-07-23","cited_by_count":11,"area":null},{"id":"2512.00752","title":"Charts Are Not Images: On the Challenges of Scientific Chart Editing","created":"2025-11-30","cited_by_count":11,"area":null},{"id":"2508.00728","title":"YOLO-Count: Differentiable Object Counting for Text-to-Image Generation","created":"2025-08-01","cited_by_count":10,"area":null},{"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":"2503.12526","title":"EditID: Training-Free Editable ID Customization for Text-to-Image Generation","created":"2025-03-16","cited_by_count":8,"area":null},{"id":"2506.01921","title":"MedEBench: Diagnosing Reliability in Text-Guided Medical Image Editing","created":"2025-06-02","cited_by_count":8,"area":null},{"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":"2508.20505","title":"Describe, Don't Dictate: Semantic Image Editing with Natural Language Intent","created":"2025-08-28","cited_by_count":7,"area":null},{"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":"2503.15283","title":"TF-TI2I: Training-Free Text-and-Image-to-Image Generation via Multi-Modal Implicit-Context Learning in Text-to-Image Models","created":"2025-03-19","cited_by_count":6,"area":null},{"id":"2510.17803","title":"ConsistEdit: Highly Consistent and Precise Training-free Visual Editing","created":"2025-10-20","cited_by_count":6,"area":null},{"id":"2503.20318","title":"EditCLIP: Representation Learning for Image Editing","created":"2025-03-26","cited_by_count":5,"area":null},{"id":"2508.07842","title":"DETACH: Cross-domain Learning for Long-Horizon Tasks via Mixture of Disentangled Experts","created":"2025-08-11","cited_by_count":5,"area":null},{"id":"2408.03632","title":"Concept Conductor: Orchestrating Multiple Personalized Concepts in Text-to-Image Synthesis","created":"2024-08-07","cited_by_count":4,"area":null},{"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":"2508.20965","title":"DrivingGaussian++: Towards Realistic Reconstruction and Editable Simulation for Surrounding Dynamic Driving Scenes","created":"2025-08-28","cited_by_count":4,"area":"driving"},{"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":"2502.02465","title":"Towards Consistent and Controllable Image Synthesis for Face Editing","created":"2025-02-04","cited_by_count":3,"area":null},{"id":"2503.10697","title":"Zero-Shot Subject-Centric Generation for Creative Application Using Entropy Fusion","created":"2025-03-12","cited_by_count":3,"area":null},{"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":"2507.07106","title":"Towards Multimodal Understanding via Stable Diffusion as a Task-Aware Feature Extractor","created":"2025-07-09","cited_by_count":3,"area":"mllm"},{"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":"2512.12800","title":"Learning Common and Salient Generative Factors Between Two Image Datasets","created":"2025-12-14","cited_by_count":3,"area":null},{"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":"2411.13981","title":"On the Fairness, Diversity and Reliability of Text-to-Image Generative Models","created":"2024-11-21","cited_by_count":2,"area":null},{"id":"2411.15277","title":"Foundation Cures Personalization: Improving Personalized Models' Prompt Consistency via Hidden Foundation Knowledge","created":"2024-11-22","cited_by_count":2,"area":null},{"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":"2503.21541","title":"LOCATEdit: Graph Laplacian Optimized Cross Attention for Localized Text-Guided Image Editing","created":"2025-03-27","cited_by_count":2,"area":null},{"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":"2508.07636","title":"Attribution Explanations for Deep Neural Networks: A Theoretical Perspective","created":"2025-08-11","cited_by_count":2,"area":null},{"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":"2508.19791","title":"Color Bind: Exploring Color Perception in Text-to-Image Models","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2510.22960","title":"FAME: Fairness-aware Attention-modulated Video Editing","created":"2025-10-27","cited_by_count":2,"area":null},{"id":"2512.01334","title":"AlignVid: Training-Free Attention Scaling for Semantic Fidelity in Text-Guided Image-to-Video Generation","created":"2025-12-01","cited_by_count":2,"area":null},{"id":"2602.02388","title":"Personalized Image Generation via Human-in-the-loop Bayesian Optimization","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2603.17651","title":"Anchoring and Rescaling Attention for Semantically Coherent Inbetweening","created":"2026-03-18","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":"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":"2409.09610","title":"TextureDiffusion: Target Prompt Disentangled Editing for Various Texture Transfer","created":"2024-09-15","cited_by_count":1,"area":null},{"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":"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":"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":"2504.10822","title":"IlluSign: Illustrating Sign Language Videos by Leveraging the Attention Mechanism","created":"2025-04-15","cited_by_count":1,"area":null},{"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":"2507.13753","title":"Encapsulated Composition of Text-to-Image and Text-to-Video Models for High-Quality Video Synthesis","created":"2025-07-18","cited_by_count":1,"area":null},{"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":"2508.19244","title":"Articulate3D: Zero-Shot Text-Driven 3D Object Posing","created":"2025-08-26","cited_by_count":1,"area":null},{"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":"2512.12425","title":"Boosting Monocular Metric Depth Estimation via Bokeh Rendering","created":"2025-12-13","cited_by_count":1,"area":null},{"id":"2602.22819","title":"Face Time Traveller : Travel Through Ages Without Losing Identity","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2603.28367","title":"Rethinking Structure Preservation in Text-Guided Image Editing with Visual Autoregressive Models","created":"2026-03-30","cited_by_count":1,"area":null},{"id":"2603.28605","title":"Unsafe2Safe: Controllable Image Anonymization for Downstream Utility","created":"2026-03-30","cited_by_count":1,"area":null},{"id":"2605.07455","title":"EditTransfer++: Toward Faithful and Efficient Visual-Prompt-Guided Image Editing","created":"2026-05-08","cited_by_count":1,"area":null},{"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"}],"next_cursor":"100"}