{"total":84,"rows":[{"id":"2306.00986","title":"Diffusion Self-Guidance for Controllable Image Generation","created":"2023-06-01","cited_by_count":305,"area":null},{"id":"2412.08629","title":"FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models","created":"2024-12-11","cited_by_count":217,"area":null},{"id":"2305.15391","title":"A Neural Space-Time Representation for Text-to-Image Personalization","created":"2023-05-24","cited_by_count":123,"area":null},{"id":"2211.11695","title":"Disentangled Representation Learning","created":"2022-11-21","cited_by_count":112,"area":null},{"id":"2504.12782","title":"Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts","created":"2025-04-17","cited_by_count":62,"area":null},{"id":"2401.11430","title":"Exploring Diffusion Time-steps for Unsupervised Representation Learning","created":"2024-01-21","cited_by_count":36,"area":null},{"id":"2406.19370","title":"Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space","created":"2024-06-27","cited_by_count":35,"area":null},{"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":"2402.05468","title":"Implicit Diffusion: Efficient Optimization through Stochastic Sampling","created":"2024-02-08","cited_by_count":24,"area":null},{"id":"2404.09554","title":"Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda","created":"2024-04-15","cited_by_count":22,"area":null},{"id":"2506.03107","title":"ByteMorph: Benchmarking Instruction-Guided Image Editing with Non-Rigid Motions","created":"2025-06-03","cited_by_count":19,"area":null},{"id":"2510.08532","title":"Kontinuous Kontext: Continuous Strength Control for Instruction-based Image Editing","created":"2025-10-09","cited_by_count":18,"area":null},{"id":"2304.12944","title":"Latent Traversals in Generative Models as Potential Flows","created":"2023-04-25","cited_by_count":17,"area":null},{"id":"2406.00519","title":"Learning Discrete Concepts in Latent Hierarchical Models","created":"2024-06-01","cited_by_count":17,"area":null},{"id":"2210.14267","title":"A Survey on Deep Generative 3D-aware Image Synthesis","created":"2022-10-25","cited_by_count":16,"area":null},{"id":"2309.13167","title":"Flow Factorized Representation Learning","created":"2023-09-22","cited_by_count":11,"area":null},{"id":"2403.04321","title":"Discriminative Probing and Tuning for Text-to-Image Generation","created":"2024-03-07","cited_by_count":11,"area":null},{"id":"2408.01571","title":"Counterfactual Explanations for Medical Image Classification and Regression using Diffusion Autoencoder","created":"2024-08-02","cited_by_count":10,"area":null},{"id":"2507.04051","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","created":"2025-07-05","cited_by_count":10,"area":null},{"id":"2306.01735","title":"Multilingual Conceptual Coverage in Text-to-Image Models","created":"2023-06-02","cited_by_count":9,"area":null},{"id":"2310.10461","title":"Model Selection of Anomaly Detectors in the Absence of Labeled Validation Data","created":"2023-10-16","cited_by_count":8,"area":null},{"id":"2406.00432","title":"Localize, Understand, Collaborate: Semantic-Aware Dragging via Intention Reasoner","created":"2024-06-01","cited_by_count":8,"area":null},{"id":"2408.08558","title":"Linear combinations of latents in generative models: subspaces and beyond","created":"2024-08-16","cited_by_count":8,"area":null},{"id":"2403.20231","title":"U-VAP: User-specified Visual Appearance Personalization via Decoupled Self Augmentation","created":"2024-03-29","cited_by_count":7,"area":null},{"id":"2406.18534","title":"Towards Compositionality in Concept Learning","created":"2024-06-26","cited_by_count":7,"area":null},{"id":"2407.07249","title":"Few-Shot Image Generation by Conditional Relaxing Diffusion Inversion","created":"2024-07-09","cited_by_count":7,"area":null},{"id":"2405.03987","title":"Navigating Chemical Space with Latent Flows","created":"2024-05-07","cited_by_count":6,"area":null},{"id":"2410.11374","title":"Preserve or Modify? Context-Aware Evaluation for Balancing Preservation and Modification in Text-Guided Image Editing","created":"2024-10-15","cited_by_count":6,"area":null},{"id":"2412.00857","title":"Coherent Video Inpainting Using Optical Flow-Guided Efficient Diffusion","created":"2024-12-01","cited_by_count":6,"area":null},{"id":"2403.19235","title":"DreamSalon: A Staged Diffusion Framework for Preserving Identity-Context in Editable Face Generation","created":"2024-03-28","cited_by_count":5,"area":null},{"id":"2411.14521","title":"MyTimeMachine: Personalized Facial Age Transformation","created":"2024-11-21","cited_by_count":5,"area":null},{"id":"2504.21646","title":"Diffusion-based Adversarial Identity Manipulation for Facial Privacy Protection","created":"2025-04-30","cited_by_count":5,"area":null},{"id":"2310.02230","title":"Leveraging Diffusion Disentangled Representations to Mitigate Shortcuts in Underspecified Visual Tasks","created":"2023-10-03","cited_by_count":4,"area":null},{"id":"2311.16176","title":"Mitigating Shortcut Learning with Diffusion Counterfactuals and Diverse Ensembles","created":"2023-11-23","cited_by_count":4,"area":null},{"id":"2405.16823","title":"Unified Editing of Panorama, 3D Scenes, and Videos Through Disentangled Self-Attention Injection","created":"2024-05-27","cited_by_count":4,"area":null},{"id":"2410.06243","title":"Unsupervised Model Diagnosis","created":"2024-10-08","cited_by_count":4,"area":null},{"id":"2310.08785","title":"DeltaSpace: A Semantic-aligned Feature Space for Flexible Text-guided Image Editing","created":"2023-10-12","cited_by_count":3,"area":null},{"id":"2506.20977","title":"From Cradle to Cane: A Two-Pass Framework for High-Fidelity Lifespan Face Aging","created":"2025-06-26","cited_by_count":3,"area":null},{"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":"2512.14884","title":"Vibe Spaces for Creatively Connecting and Expressing Visual Concepts","created":"2025-12-16","cited_by_count":3,"area":null},{"id":"2311.17898","title":"Contextual Knowledge Pursuit for Faithful Visual Synthesis","created":"2023-11-29","cited_by_count":2,"area":null},{"id":"2406.18588","title":"Varying Manifolds in Diffusion: From Time-varying Geometries to Visual Saliency","created":"2024-06-07","cited_by_count":2,"area":null},{"id":"2407.01331","title":"Restyling Unsupervised Concept Based Interpretable Networks with Generative Models","created":"2024-07-01","cited_by_count":2,"area":null},{"id":"2407.13449","title":"All Roads Lead to Rome? Exploring Representational Similarities Between Latent Spaces of Generative Image Models","created":"2024-07-18","cited_by_count":2,"area":null},{"id":"2409.14379","title":"GroupDiff: Diffusion-based Group Portrait Editing","created":"2024-09-22","cited_by_count":2,"area":null},{"id":"2410.05564","title":"Unsupervised Representation Learning from Sparse Transformation Analysis","created":"2024-10-07","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":"2506.21008","title":"The Aging Multiverse: Generating Condition-Aware Facial Aging Tree via Training-Free Diffusion","created":"2025-06-26","cited_by_count":2,"area":null},{"id":"2603.08021","title":"AffordGrasp: Cross-Modal Diffusion for Affordance-Aware Grasp Synthesis","created":"2026-03-09","cited_by_count":2,"area":null},{"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":"2309.02478","title":"Enhancing Semantic Communication with Deep Generative Models -- An ICASSP Special Session Overview","created":"2023-09-05","cited_by_count":1,"area":null},{"id":"2312.10539","title":"DETER: Detecting Edited Regions for Deterring Generative Manipulations","created":"2023-12-16","cited_by_count":1,"area":null},{"id":"2405.05769","title":"Exploring Text-Guided Single Image Editing for Remote Sensing Images","created":"2024-05-09","cited_by_count":1,"area":null},{"id":"2406.11882","title":"Applications of Explainable artificial intelligence in Earth system science","created":"2024-06-12","cited_by_count":1,"area":null},{"id":"2407.11514","title":"ColorwAI: Generative Colorways of Textiles through GAN and Diffusion Disentanglement","created":"2024-07-16","cited_by_count":1,"area":null},{"id":"2412.13565","title":"CA-Edit: Causality-Aware Condition Adapter for High-Fidelity Local Facial Attribute Editing","created":"2024-12-18","cited_by_count":1,"area":null},{"id":"2502.11509","title":"DifCluE: Generating Counterfactual Explanations with Diffusion Autoencoders and modal clustering","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2502.16799","title":"Hierarchical Semantic Compression for Consistent Image Semantic Restoration","created":"2025-02-24","cited_by_count":1,"area":null},{"id":"2504.00396","title":"SPF-Portrait: Towards Pure Text-to-Portrait Customization with Semantic Pollution-Free Fine-Tuning","created":"2025-04-01","cited_by_count":1,"area":null},{"id":"2504.17525","title":"Text-to-Image Alignment in Denoising-Based Models through Step Selection","created":"2025-04-24","cited_by_count":1,"area":null},{"id":"2506.09916","title":"Only-Style: Stylistic Consistency in Image Generation without Content Leakage","created":"2025-06-11","cited_by_count":1,"area":null},{"id":"2508.01590","title":"A Plug-and-Play Multi-Criteria Guidance for Diverse In-Betweening Human Motion Generation","created":"2025-08-03","cited_by_count":1,"area":null},{"id":"2510.20595","title":"Diffusion Autoencoders with Perceivers for Long, Irregular and Multimodal Astronomical Sequences","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2604.25119","title":"Evaluation without Generation: Non-Generative Assessment of Harmful Model Specialization with Applications to CSAM","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2605.19511","title":"Are Watermarked Images Editable? SafeMark for Watermark-Preserving Text-Guided Image Editing","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2606.27371","title":"Don't Settle at the Mode! Mitigating Diversity Collapse in Pretrained Flow Models via Feature Self-Guidance","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2608.27727","title":"Probing Perceptual Priors of MLLMs via Gibbs Sampling with Interpretable Generative Controls","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2401.12596","title":"UniHDA: A Unified and Versatile Framework for Multi-Modal Hybrid Domain Adaptation","created":"2024-01-23","cited_by_count":0,"area":null},{"id":"2404.01984","title":"Fashion Style Editing with Generative Human Prior","created":"2024-04-02","cited_by_count":0,"area":null},{"id":"2408.01553","title":"Multi-task SAR Image Processing via GAN-based Unsupervised Manipulation","created":"2024-08-02","cited_by_count":0,"area":null},{"id":"2410.04421","title":"Disentangling Regional Primitives for Image Generation","created":"2024-10-06","cited_by_count":0,"area":null},{"id":"2410.16431","title":"Conjuring Semantic Similarity","created":"2024-10-21","cited_by_count":0,"area":null},{"id":"2504.15145","title":"\"I Know It When I See It\": Mood Spaces for Connecting and Expressing Visual Concepts","created":"2025-04-21","cited_by_count":0,"area":null},{"id":"2504.21368","title":"Revisiting Diffusion Autoencoder Training for Image Reconstruction Quality","created":"2025-04-30","cited_by_count":0,"area":null},{"id":"2506.22304","title":"Unfolding Generative Flows with Koopman Operators: Trajectory-Preserving Linearization","created":"2025-06-27","cited_by_count":0,"area":null},{"id":"2512.08826","title":"CARLoS: Retrieval via Concise Assessment Representation of LoRAs at Scale","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2601.17927","title":"RemEdit: Efficient Diffusion Editing with Riemannian Geometry","created":"2026-01-25","cited_by_count":0,"area":null},{"id":"2603.04825","title":"Mitigating Instance Entanglement in Instance-Dependent Partial Label Learning","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.11795","title":"Intrinsic Concept Extraction Based on Compositional Interpretability","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2605.31053","title":"AnchorSteer: Self-Discovered Concept Injection for Structure-Preserving Music Editing","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.04881","title":"DiverAge: Reliable Pluralistic Face Aging with Cross-Age Identity Relation Guidance","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.05652","title":"CoFi-UCGen: Coarse-to-Fine Unsupervised Conditional Generation without Label Priors","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.13022","title":"Quality-Preserving Imperceptible Adversarial Attack on Skeleton-based Human Action Recognition","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2607.17138","title":"Denoising Models Develop Human-Like Perceptual Illusion Representations Across Architectures","created":"2026-07-19","cited_by_count":0,"area":null}],"next_cursor":null}