{"total":313,"rows":[{"id":"2309.07864","title":"The Rise and Potential of Large Language Model Based Agents: A Survey","created":"2023-09-14","cited_by_count":1439,"area":"agents"},{"id":"2403.05135","title":"ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment","created":"2024-03-08","cited_by_count":475,"area":"diffusion"},{"id":"2305.15393","title":"LayoutGPT: Compositional Visual Planning and Generation with Large Language Models","created":"2023-05-24","cited_by_count":347,"area":null},{"id":"2306.00986","title":"Diffusion Self-Guidance for Controllable Image Generation","created":"2023-06-01","cited_by_count":305,"area":null},{"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":"2307.06350","title":"T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation","created":"2023-07-12","cited_by_count":260,"area":null},{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247,"area":null},{"id":"2305.13655","title":"LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models","created":"2023-05-23","cited_by_count":243,"area":"diffusion"},{"id":"2401.11708","title":"Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs","created":"2024-01-22","cited_by_count":224,"area":"mllm"},{"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":"2407.14505","title":"T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation","created":"2024-07-19","cited_by_count":185,"area":null},{"id":"2402.03290","title":"InstanceDiffusion: Instance-level Control for Image Generation","created":"2024-02-05","cited_by_count":175,"area":"diffusion"},{"id":"2402.03162","title":"Direct-a-Video: Customized Video Generation with User-Directed Camera Movement and Object Motion","created":"2024-02-05","cited_by_count":167,"area":"diffusion"},{"id":"2306.05427","title":"Grounded Text-to-Image Synthesis with Attention Refocusing","created":"2023-06-08","cited_by_count":164,"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":"2404.07987","title":"ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback","created":"2024-04-11","cited_by_count":154,"area":"diffusion"},{"id":"2403.14572","title":"Implicit Style-Content Separation using B-LoRA","created":"2024-03-21","cited_by_count":135,"area":null},{"id":"2407.05600","title":"GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing","created":"2024-07-08","cited_by_count":133,"area":"mllm"},{"id":"2402.05408","title":"MIGC: Multi-Instance Generation Controller for Text-to-Image Synthesis","created":"2024-02-08","cited_by_count":124,"area":null},{"id":"2311.16090","title":"Self-correcting LLM-controlled Diffusion Models","created":"2023-11-27","cited_by_count":113,"area":"diffusion"},{"id":"2503.14492","title":"Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control","created":"2025-03-18","cited_by_count":106,"area":null},{"id":"2404.18929","title":"DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editing","created":"2024-04-29","cited_by_count":94,"area":null},{"id":"2312.07536","title":"FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition","created":"2023-12-12","cited_by_count":91,"area":"diffusion"},{"id":"2305.13921","title":"Compositional Text-to-Image Synthesis with Attention Map Control of Diffusion Models","created":"2023-05-23","cited_by_count":83,"area":"diffusion"},{"id":"2309.17444","title":"LLM-grounded Video Diffusion Models","created":"2023-09-29","cited_by_count":83,"area":"diffusion"},{"id":"2401.12244","title":"Large-scale Reinforcement Learning for Diffusion Models","created":"2024-01-20","cited_by_count":78,"area":"diffusion"},{"id":"2406.18522","title":"ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation","created":"2024-06-26","cited_by_count":75,"area":null},{"id":"2412.18597","title":"DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation","created":"2024-12-24","cited_by_count":74,"area":"diffusion"},{"id":"2305.18247","title":"TaleCrafter: Interactive Story Visualization with Multiple Characters","created":"2023-05-29","cited_by_count":73,"area":null},{"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":"2411.04989","title":"SG-I2V: Self-Guided Trajectory Control in Image-to-Video Generation","created":"2024-11-07","cited_by_count":68,"area":null},{"id":"2306.13754","title":"Zero-shot spatial layout conditioning for text-to-image diffusion models","created":"2023-06-23","cited_by_count":64,"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":"2312.00853","title":"Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolution","created":"2023-12-01","cited_by_count":59,"area":"diffusion"},{"id":"2312.02190","title":"Diffusion Handles: Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D","created":"2023-12-02","cited_by_count":59,"area":"diffusion"},{"id":"2404.05384","title":"Rethinking the Spatial Inconsistency in Classifier-Free Diffusion Guidance","created":"2024-04-08","cited_by_count":59,"area":"diffusion"},{"id":"2312.05208","title":"ControlRoom3D: Room Generation using Semantic Proxy Rooms","created":"2023-12-08","cited_by_count":56,"area":null},{"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":"2306.04744","title":"WOUAF: Weight Modulation for User Attribution and Fingerprinting in Text-to-Image Diffusion Models","created":"2023-06-07","cited_by_count":53,"area":"diffusion"},{"id":"2312.02150","title":"Readout Guidance: Learning Control from Diffusion Features","created":"2023-12-04","cited_by_count":52,"area":"diffusion"},{"id":"2502.04320","title":"ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features","created":"2025-02-06","cited_by_count":52,"area":"diffusion"},{"id":"2404.05014","title":"MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators","created":"2024-04-07","cited_by_count":51,"area":null},{"id":"2406.04277","title":"VideoTetris: Towards Compositional Text-to-Video Generation","created":"2024-06-06","cited_by_count":51,"area":"diffusion"},{"id":"2407.12899","title":"DreamStory: Open-Domain Story Visualization by LLM-Guided Multi-Subject Consistent Diffusion","created":"2024-07-17","cited_by_count":47,"area":"diffusion"},{"id":"2412.07744","title":"StyleMaster: Stylize Your Video with Artistic Generation and Translation","created":"2024-12-10","cited_by_count":47,"area":null},{"id":"2312.03048","title":"DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control","created":"2023-12-05","cited_by_count":45,"area":"diffusion"},{"id":"2410.09049","title":"SceneCraft: Layout-Guided 3D Scene Generation","created":"2024-10-11","cited_by_count":41,"area":null},{"id":"2410.14324","title":"HiCo: Hierarchical Controllable Diffusion Model for Layout-to-image Generation","created":"2024-10-18","cited_by_count":41,"area":"diffusion"},{"id":"2312.03626","title":"TokenCompose: Text-to-Image Diffusion with Token-level Supervision","created":"2023-12-06","cited_by_count":40,"area":"diffusion"},{"id":"2312.15540","title":"Amodal Completion via Progressive Mixed Context Diffusion","created":"2023-12-24","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":"2312.09246","title":"SHAP-EDITOR: Instruction-guided Latent 3D Editing in Seconds","created":"2023-12-14","cited_by_count":37,"area":null},{"id":"2406.02366","title":"Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models","created":"2024-06-04","cited_by_count":37,"area":"diffusion"},{"id":"2407.02329","title":"MIGC++: Advanced Multi-Instance Generation Controller for Image Synthesis","created":"2024-07-02","cited_by_count":35,"area":null},{"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":"2410.07171","title":"IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation","created":"2024-10-09","cited_by_count":33,"area":"diffusion"},{"id":"2404.06637","title":"GeoSynth: Contextually-Aware High-Resolution Satellite Image Synthesis","created":"2024-04-09","cited_by_count":32,"area":null},{"id":"2403.18551","title":"Attention Calibration for Disentangled Text-to-Image Personalization","created":"2024-03-27","cited_by_count":31,"area":null},{"id":"2411.18810","title":"All Seeds Are Not Equal: Enhancing Compositional Text-to-Image Generation with Reliable Random Seeds","created":"2024-11-27","cited_by_count":31,"area":"diffusion"},{"id":"2312.06573","title":"ControlNet-XS: Rethinking the Control of Text-to-Image Diffusion Models as Feedback-Control Systems","created":"2023-12-11","cited_by_count":30,"area":"diffusion"},{"id":"2404.01197","title":"Getting it Right: Improving Spatial Consistency in Text-to-Image Models","created":"2024-04-01","cited_by_count":30,"area":null},{"id":"2406.09292","title":"Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Models","created":"2024-06-13","cited_by_count":30,"area":"diffusion"},{"id":"2410.22376","title":"Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance","created":"2024-10-29","cited_by_count":30,"area":"diffusion"},{"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":"2405.05538","title":"A Survey on Personalized Content Synthesis with Diffusion Models","created":"2024-05-09","cited_by_count":29,"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":"2404.05268","title":"MC$^2$: Multi-concept Guidance for Customized Multi-concept Generation","created":"2024-04-08","cited_by_count":26,"area":null},{"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":"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":"2404.06425","title":"ZeST: Zero-Shot Material Transfer from a Single Image","created":"2024-04-09","cited_by_count":24,"area":null},{"id":"2410.20474","title":"GrounDiT: Grounding Diffusion Transformers via Noisy Patch Transplantation","created":"2024-10-27","cited_by_count":24,"area":"diffusion"},{"id":"2411.07126","title":"Edify Image: High-Quality Image Generation with Pixel Space Laplacian Diffusion Models","created":"2024-11-11","cited_by_count":23,"area":"diffusion"},{"id":"2406.01594","title":"DiffUHaul: A Training-Free Method for Object Dragging in Images","created":"2024-06-03","cited_by_count":22,"area":"diffusion"},{"id":"2406.16476","title":"ResMaster: Mastering High-Resolution Image Generation via Structural and Fine-Grained Guidance","created":"2024-06-24","cited_by_count":22,"area":"diffusion"},{"id":"2504.15473","title":"Emergence and Evolution of Interpretable Concepts in Diffusion Models","created":"2025-04-21","cited_by_count":22,"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":"2403.01852","title":"PLACE: Adaptive Layout-Semantic Fusion for Semantic Image Synthesis","created":"2024-03-04","cited_by_count":20,"area":null},{"id":"2403.14487","title":"DesignEdit: Multi-Layered Latent Decomposition and Fusion for Unified & Accurate Image Editing","created":"2024-03-21","cited_by_count":20,"area":null},{"id":"2405.15321","title":"SG-Adapter: Enhancing Text-to-Image Generation with Scene Graph Guidance","created":"2024-05-24","cited_by_count":20,"area":"diffusion"},{"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":"2312.08048","title":"Compositional Inversion for Stable Diffusion Models","created":"2023-12-13","cited_by_count":19,"area":"diffusion"},{"id":"2409.19967","title":"Magnet: We Never Know How Text-to-Image Diffusion Models Work, Until We Learn How Vision-Language Models Function","created":"2024-09-30","cited_by_count":19,"area":"mllm"},{"id":"2312.05039","title":"SmartMask: Context Aware High-Fidelity Mask Generation for Fine-grained Object Insertion and Layout Control","created":"2023-12-08","cited_by_count":18,"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":"2403.11821","title":"A Survey on Quality Metrics for Text-to-Image Generation","created":"2024-03-18","cited_by_count":18,"area":null},{"id":"2408.14819","title":"Build-A-Scene: Interactive 3D Layout Control for Diffusion-Based Image Generation","created":"2024-08-27","cited_by_count":18,"area":"diffusion"},{"id":"2409.08240","title":"IFAdapter: Instance Feature Control for Grounded Text-to-Image Generation","created":"2024-09-12","cited_by_count":18,"area":"diffusion"},{"id":"2503.10127","title":"PlanGen: Towards Unified Layout Planning and Image Generation in Auto-Regressive Vision Language Models","created":"2025-03-13","cited_by_count":18,"area":"mllm"},{"id":"2505.04320","title":"Multi-turn Consistent Image Editing","created":"2025-05-07","cited_by_count":18,"area":null},{"id":"2305.15808","title":"Towards Language-guided Interactive 3D Generation: LLMs as Layout Interpreter with Generative Feedback","created":"2023-05-25","cited_by_count":17,"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":"2312.08822","title":"Planning and Rendering: Towards Product Poster Generation with Diffusion Models","created":"2023-12-14","cited_by_count":16,"area":"diffusion"},{"id":"2507.22076","title":"Test-time Prompt Refinement for Text-to-Image Models","created":"2025-07-22","cited_by_count":16,"area":null},{"id":"2306.14153","title":"DomainStudio: Fine-Tuning Diffusion Models for Domain-Driven Image Generation using Limited Data","created":"2023-06-25","cited_by_count":15,"area":"diffusion"},{"id":"2312.06038","title":"Correcting Diffusion Generation through Resampling","created":"2023-12-10","cited_by_count":15,"area":"diffusion"},{"id":"2401.16157","title":"Spatial-Aware Latent Initialization for Controllable Image Generation","created":"2024-01-29","cited_by_count":15,"area":"diffusion"},{"id":"2501.07647","title":"BlobGEN-Vid: Compositional Text-to-Video Generation with Blob Video Representations","created":"2025-01-13","cited_by_count":15,"area":"diffusion"}],"next_cursor":"100"}