{"total":164,"rows":[{"id":"2403.06135","title":"MACE: Mass Concept Erasure in Diffusion Models","created":"2024-03-10","cited_by_count":307,"area":"diffusion"},{"id":"2307.10816","title":"BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion","created":"2023-07-20","cited_by_count":282,"area":"diffusion"},{"id":"2307.11410","title":"Subject-Diffusion:Open Domain Personalized Text-to-Image Generation without Test-time Fine-tuning","created":"2023-07-21","cited_by_count":191,"area":"diffusion"},{"id":"2308.12964","title":"Dense Text-to-Image Generation with Attention Modulation","created":"2023-08-24","cited_by_count":163,"area":"diffusion"},{"id":"2309.17444","title":"LLM-grounded Video Diffusion Models","created":"2023-09-29","cited_by_count":83,"area":"diffusion"},{"id":"2403.04279","title":"Controllable Generation with Text-to-Image Diffusion Models: A Survey","created":"2024-03-07","cited_by_count":83,"area":"diffusion"},{"id":"2312.07509","title":"PEEKABOO: Interactive Video Generation via Masked-Diffusion","created":"2023-12-12","cited_by_count":76,"area":"wm"},{"id":"2403.16990","title":"Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation","created":"2024-03-25","cited_by_count":69,"area":"diffusion"},{"id":"2407.04842","title":"MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?","created":"2024-07-05","cited_by_count":66,"area":"diffusion"},{"id":"2311.12631","title":"GPT4Motion: Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planning","created":"2023-11-21","cited_by_count":61,"area":"diffusion"},{"id":"2404.03653","title":"CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching","created":"2024-04-04","cited_by_count":61,"area":"diffusion"},{"id":"2412.03859","title":"CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation","created":"2024-12-05","cited_by_count":60,"area":"diffusion"},{"id":"2403.11627","title":"LoRA-Composer: Leveraging Low-Rank Adaptation for Multi-Concept Customization in Training-Free Diffusion Models","created":"2024-03-18","cited_by_count":55,"area":"diffusion"},{"id":"2310.10640","title":"LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts","created":"2023-10-16","cited_by_count":54,"area":"diffusion"},{"id":"2502.17258","title":"VideoGrain: Modulating Space-Time Attention for Multi-grained Video Editing","created":"2025-02-24","cited_by_count":50,"area":"diffusion"},{"id":"2406.10210","title":"Make It Count: Text-to-Image Generation with an Accurate Number of Objects","created":"2024-06-14","cited_by_count":47,"area":"diffusion"},{"id":"2404.14239","title":"MultiBooth: Towards Generating All Your Concepts in an Image from Text","created":"2024-04-22","cited_by_count":45,"area":null},{"id":"2406.11831","title":"Exploring the Role of Large Language Models in Prompt Encoding for Diffusion Models","created":"2024-06-17","cited_by_count":45,"area":"diffusion"},{"id":"2407.20727","title":"SceneTeller: Language-to-3D Scene Generation","created":"2024-07-30","cited_by_count":43,"area":null},{"id":"2310.16656","title":"A Picture is Worth a Thousand Words: Principled Recaptioning Improves Image Generation","created":"2023-10-25","cited_by_count":41,"area":"diffusion"},{"id":"2311.11243","title":"AutoStory: Generating Diverse Storytelling Images with Minimal Human Effort","created":"2023-11-19","cited_by_count":38,"area":null},{"id":"2405.08246","title":"Compositional Text-to-Image Generation with Dense Blob Representations","created":"2024-05-14","cited_by_count":38,"area":null},{"id":"2505.19114","title":"CreatiDesign: A Unified Multi-Conditional Diffusion Transformer for Creative Graphic Design","created":"2025-05-25","cited_by_count":36,"area":"diffusion"},{"id":"2309.13042","title":"MosaicFusion: Diffusion Models as Data Augmenters for Large Vocabulary Instance Segmentation","created":"2023-09-22","cited_by_count":35,"area":"diffusion"},{"id":"2401.06105","title":"PALP: Prompt Aligned Personalization of Text-to-Image Models","created":"2024-01-11","cited_by_count":35,"area":null},{"id":"2407.15861","title":"Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Survey","created":"2024-07-10","cited_by_count":35,"area":"diffusion"},{"id":"2411.07132","title":"Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis","created":"2024-11-11","cited_by_count":35,"area":"inference"},{"id":"2310.08872","title":"R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation","created":"2023-10-13","cited_by_count":29,"area":"diffusion"},{"id":"2503.12885","title":"DreamRenderer: Taming Multi-Instance Attribute Control in Large-Scale Text-to-Image Models","created":"2025-03-17","cited_by_count":28,"area":null},{"id":"2412.08486","title":"Learning Flow Fields in Attention for Controllable Person Image Generation","created":"2024-12-11","cited_by_count":27,"area":null},{"id":"2507.19024","title":"A Survey of Multimodal Hallucination Evaluation and Detection","created":"2025-07-25","cited_by_count":27,"area":"mllm"},{"id":"2308.13142","title":"A Survey of Diffusion Based Image Generation Models: Issues and Their Solutions","created":"2023-08-25","cited_by_count":25,"area":"diffusion"},{"id":"2403.03485","title":"NoiseCollage: A Layout-Aware Text-to-Image Diffusion Model Based on Noise Cropping and Merging","created":"2024-03-06","cited_by_count":25,"area":"diffusion"},{"id":"2404.06451","title":"SmartControl: Enhancing ControlNet for Handling Rough Visual Conditions","created":"2024-04-09","cited_by_count":25,"area":null},{"id":"2306.17567","title":"Counting Guidance for High Fidelity Text-to-Image Synthesis","created":"2023-06-30","cited_by_count":24,"area":"diffusion"},{"id":"2312.04655","title":"ECLIPSE: A Resource-Efficient Text-to-Image Prior for Image Generations","created":"2023-12-07","cited_by_count":24,"area":"diffusion"},{"id":"2410.20474","title":"GrounDiT: Grounding Diffusion Transformers via Noisy Patch Transplantation","created":"2024-10-27","cited_by_count":24,"area":"diffusion"},{"id":"2311.12342","title":"LoCo: Locally Constrained Training-Free Layout-to-Image Synthesis","created":"2023-11-21","cited_by_count":21,"area":"diffusion"},{"id":"2312.11396","title":"MAG-Edit: Localized Image Editing in Complex Scenarios via Mask-Based Attention-Adjusted Guidance","created":"2023-12-18","cited_by_count":21,"area":"diffusion"},{"id":"2504.11739","title":"The Devil is in the Prompts: Retrieval-Augmented Prompt Optimization for Text-to-Video Generation","created":"2025-04-16","cited_by_count":21,"area":"rag"},{"id":"2403.01852","title":"PLACE: Adaptive Layout-Semantic Fusion for Semantic Image Synthesis","created":"2024-03-04","cited_by_count":20,"area":null},{"id":"2503.20672","title":"BizGen: Advancing Article-level Visual Text Rendering for Infographics Generation","created":"2025-03-26","cited_by_count":20,"area":null},{"id":"2506.07986","title":"Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformers","created":"2025-06-09","cited_by_count":20,"area":"diffusion"},{"id":"2311.15773","title":"Check, Locate, Rectify: A Training-Free Layout Calibration System for Text-to-Image Generation","created":"2023-11-27","cited_by_count":19,"area":"diffusion"},{"id":"2406.01970","title":"The Crystal Ball Hypothesis in diffusion models: Anticipating object positions from initial noise","created":"2024-06-04","cited_by_count":19,"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":"2402.12908","title":"RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models","created":"2024-02-20","cited_by_count":18,"area":"diffusion"},{"id":"2404.16035","title":"MaGGIe: Masked Guided Gradual Human Instance Matting","created":"2024-04-24","cited_by_count":18,"area":null},{"id":"2309.04399","title":"MaskDiffusion: Boosting Text-to-Image Consistency with Conditional Mask","created":"2023-09-08","cited_by_count":17,"area":"diffusion"},{"id":"2403.16111","title":"EVA: Zero-shot Accurate Attributes and Multi-Object Video Editing","created":"2024-03-24","cited_by_count":17,"area":"diffusion"},{"id":"2406.05191","title":"DiffusionPID: Interpreting Diffusion via Partial Information Decomposition","created":"2024-06-07","cited_by_count":16,"area":"diffusion"},{"id":"2411.18936","title":"Self-Cross Diffusion Guidance for Text-to-Image Synthesis of Similar Subjects","created":"2024-11-28","cited_by_count":16,"area":"diffusion"},{"id":"2506.01320","title":"Psi-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models","created":"2025-06-02","cited_by_count":15,"area":"diffusion"},{"id":"2403.06952","title":"SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Data","created":"2024-03-11","cited_by_count":14,"area":null},{"id":"2501.01424","title":"Object-level Visual Prompts for Compositional Image Generation","created":"2025-01-02","cited_by_count":14,"area":"diffusion"},{"id":"2503.17671","title":"ComfyGPT: A Self-Optimizing Multi-Agent System for Comprehensive ComfyUI Workflow Generation","created":"2025-03-22","cited_by_count":14,"area":"agents"},{"id":"2310.07419","title":"Multi-Concept T2I-Zero: Tweaking Only The Text Embeddings and Nothing Else","created":"2023-10-11","cited_by_count":13,"area":"diffusion"},{"id":"2508.15773","title":"Scaling Group Inference for Diverse and High-Quality Generation","created":"2025-08-21","cited_by_count":12,"area":null},{"id":"2406.11820","title":"Composing Object Relations and Attributes for Image-Text Matching","created":"2024-06-17","cited_by_count":11,"area":null},{"id":"2403.15330","title":"Selectively Informative Description can Reduce Undesired Embedding Entanglements in Text-to-Image Personalization","created":"2024-03-22","cited_by_count":10,"area":null},{"id":"2403.19776","title":"Contrastive Test-Time Composition of Multiple LoRA Models for Image Generation","created":"2024-03-28","cited_by_count":10,"area":null},{"id":"2406.05000","title":"AttnDreamBooth: Towards Text-Aligned Personalized Text-to-Image Generation","created":"2024-06-07","cited_by_count":10,"area":null},{"id":"2410.16646","title":"TopoDiffusionNet: A Topology-aware Diffusion Model","created":"2024-10-22","cited_by_count":10,"area":"diffusion"},{"id":"2501.00637","title":"Flash-Split: 2D Reflection Removal with Flash Cues and Latent Diffusion Separation","created":"2024-12-31","cited_by_count":10,"area":"diffusion"},{"id":"2509.16691","title":"InstanceAssemble: Layout-Aware Image Generation via Instance Assembling Attention","created":"2025-09-20","cited_by_count":10,"area":"diffusion"},{"id":"2509.19282","title":"OverLayBench: A Benchmark for Layout-to-Image Generation with Dense Overlaps","created":"2025-09-23","cited_by_count":10,"area":null},{"id":"2510.20206","title":"RAPO++: Cross-Stage Prompt Optimization for Text-to-Video Generation via Data Alignment and Test-Time Scaling","created":"2025-10-23","cited_by_count":10,"area":"lr"},{"id":"2311.18435","title":"Layered Rendering Diffusion Model for Controllable Zero-Shot Image Synthesis","created":"2023-11-30","cited_by_count":9,"area":"diffusion"},{"id":"2404.13899","title":"Towards Better Text-to-Image Generation Alignment via Attention Modulation","created":"2024-04-22","cited_by_count":9,"area":"diffusion"},{"id":"2411.17949","title":"ROICtrl: Boosting Instance Control for Visual Generation","created":"2024-11-27","cited_by_count":9,"area":"diffusion"},{"id":"2411.05473","title":"Improving image synthesis with diffusion-negative sampling","created":"2024-11-08","cited_by_count":8,"area":"diffusion"},{"id":"2412.08464","title":"CC-Diff: Enhancing Contextual Coherence in Remote Sensing Image Synthesis","created":"2024-12-11","cited_by_count":8,"area":null},{"id":"2311.16635","title":"MotionZero:Exploiting Motion Priors for Zero-shot Text-to-Video Generation","created":"2023-11-28","cited_by_count":7,"area":null},{"id":"2412.13195","title":"CoMPaSS: Enhancing Spatial Understanding in Text-to-Image Diffusion Models","created":"2024-12-17","cited_by_count":7,"area":"diffusion"},{"id":"2311.16122","title":"Semantic Generative Augmentations for Few-Shot Counting","created":"2023-10-26","cited_by_count":6,"area":"diffusion"},{"id":"2403.13589","title":"ReGround: Improving Textual and Spatial Grounding at No Cost","created":"2024-03-20","cited_by_count":6,"area":null},{"id":"2405.17965","title":"AttenCraft: Attention-guided Disentanglement of Multiple Concepts for Text-to-Image Customization","created":"2024-05-28","cited_by_count":6,"area":"diffusion"},{"id":"2412.14484","title":"Llama Learns to Direct: DirectorLLM for Human-Centric Video Generation","created":"2024-12-19","cited_by_count":6,"area":null},{"id":"2503.10365","title":"Piece it Together: Part-Based Concepting with IP-Priors","created":"2025-03-13","cited_by_count":6,"area":null},{"id":"2504.01515","title":"Training-free Dense-Aligned Diffusion Guidance for Modular Conditional Image Synthesis","created":"2025-04-02","cited_by_count":6,"area":null},{"id":"2507.03257","title":"LACONIC: A 3D Layout Adapter for Controllable Image Creation","created":"2025-07-04","cited_by_count":6,"area":null},{"id":"2512.23519","title":"IdentityStory: Taming Your Identity-Preserving Generator for Human-Centric Story Generation","created":"2025-12-29","cited_by_count":6,"area":null},{"id":"2402.13404","title":"Layout-to-Image Generation with Localized Descriptions using ControlNet with Cross-Attention Control","created":"2024-02-20","cited_by_count":5,"area":"diffusion"},{"id":"2409.08271","title":"DreamBeast: Distilling 3D Fantastical Animals with Part-Aware Knowledge Transfer","created":"2024-09-12","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":"2503.13816","title":"MOSAIC: Generating Consistent, Privacy-Preserving Scenes from Multiple Depth Views in Multi-Room Environments","created":"2025-03-18","cited_by_count":5,"area":null},{"id":"2503.23011","title":"Geometrical Properties of Text Token Embeddings for Strong Semantic Binding in Text-to-Image Generation","created":"2025-03-29","cited_by_count":5,"area":null},{"id":"2509.25940","title":"Steer Away From Mode Collisions: Improving Composition In Diffusion Models","created":"2025-09-30","cited_by_count":5,"area":"diffusion"},{"id":"2603.05769","title":"Layer-wise Instance Binding for Regional and Occlusion Control in Text-to-Image Diffusion Transformers","created":"2026-03-06","cited_by_count":5,"area":"diffusion"},{"id":"2402.16305","title":"Referee Can Play: An Alternative Approach to Conditional Generation via Model Inversion","created":"2024-02-26","cited_by_count":4,"area":"diffusion"},{"id":"2407.06469","title":"Sketch-Guided Scene Image Generation","created":"2024-07-09","cited_by_count":4,"area":"diffusion"},{"id":"2407.17847","title":"Move and Act: Enhanced Object Manipulation and Background Integrity for Image Editing","created":"2024-07-25","cited_by_count":4,"area":null},{"id":"2407.19205","title":"Faster Image2Video Generation: A Closer Look at CLIP Image Embedding's Impact on Spatio-Temporal Cross-Attentions","created":"2024-07-27","cited_by_count":4,"area":"diffusion"},{"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":"2410.13564","title":"Imagining the Unseen: Generative Location Modeling for Object Placement","created":"2024-10-17","cited_by_count":4,"area":null},{"id":"2410.21638","title":"Adapting Diffusion Models for Improved Prompt Compliance and Controllable Image Synthesis","created":"2024-10-29","cited_by_count":4,"area":"diffusion"},{"id":"2411.10495","title":"Training-Free Layout-to-Image Generation with Marginal Attention Constraints","created":"2024-11-15","cited_by_count":4,"area":"diffusion"},{"id":"2406.04337","title":"Coherent Zero-Shot Visual Instruction Generation","created":"2024-06-06","cited_by_count":3,"area":"diffusion"},{"id":"2406.11384","title":"Understanding Multi-Granularity for Open-Vocabulary Part Segmentation","created":"2024-06-17","cited_by_count":3,"area":null},{"id":"2408.07116","title":"Generative Photomontage","created":"2024-08-13","cited_by_count":3,"area":null}],"next_cursor":"100"}