{"total":347,"rows":[{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615,"area":"mllm"},{"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":"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":"2312.09067","title":"Holodeck: Language Guided Generation of 3D Embodied AI Environments","created":"2023-12-14","cited_by_count":268,"area":"wm"},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254,"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":"2309.17102","title":"Guiding Instruction-based Image Editing via Multimodal Large Language Models","created":"2023-09-29","cited_by_count":185,"area":"mllm"},{"id":"2402.03290","title":"InstanceDiffusion: Instance-level Control for Image Generation","created":"2024-02-05","cited_by_count":175,"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":"2309.15091","title":"VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning","created":"2023-09-26","cited_by_count":141,"area":null},{"id":"2311.16465","title":"TextDiffuser-2: Unleashing the Power of Language Models for Text Rendering","created":"2023-11-28","cited_by_count":140,"area":"diffusion"},{"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":"2401.03428","title":"Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects","created":"2024-01-07","cited_by_count":132,"area":"agents"},{"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":"2406.04312","title":"ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization","created":"2024-06-06","cited_by_count":119,"area":"alignment"},{"id":"2402.04717","title":"InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior","created":"2024-02-07","cited_by_count":117,"area":null},{"id":"2311.16090","title":"Self-correcting LLM-controlled Diffusion Models","created":"2023-11-27","cited_by_count":113,"area":"diffusion"},{"id":"2402.07207","title":"GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splatting","created":"2024-02-11","cited_by_count":109,"area":null},{"id":"2503.10639","title":"GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing","created":"2025-03-13","cited_by_count":104,"area":"lr"},{"id":"2402.03161","title":"Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization","created":"2024-02-05","cited_by_count":100,"area":"mllm"},{"id":"2412.02193","title":"LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models","created":"2024-12-03","cited_by_count":96,"area":"lr"},{"id":"2310.12945","title":"3D-GPT: Procedural 3D Modeling with Large Language Models","created":"2023-10-19","cited_by_count":95,"area":null},{"id":"2507.21809","title":"HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels","created":"2025-07-29","cited_by_count":94,"area":null},{"id":"2404.02838","title":"I-Design: Personalized LLM Interior Designer","created":"2024-04-03","cited_by_count":87,"area":null},{"id":"2309.17444","title":"LLM-grounded Video Diffusion Models","created":"2023-09-29","cited_by_count":83,"area":"diffusion"},{"id":"2312.06644","title":"AnyHome: Open-Vocabulary Generation of Structured and Textured 3D Homes","created":"2023-12-11","cited_by_count":82,"area":"wm"},{"id":"2311.17002","title":"Ranni: Taming Text-to-Image Diffusion for Accurate Instruction Following","created":"2023-11-28","cited_by_count":77,"area":"diffusion"},{"id":"2410.16499","title":"SINGAPO: Single Image Controlled Generation of Articulated Parts in Objects","created":"2024-10-21","cited_by_count":69,"area":null},{"id":"2505.02836","title":"Scenethesis: A Language and Vision Agentic Framework for 3D Scene Generation","created":"2025-05-05","cited_by_count":67,"area":"agents"},{"id":"2312.03052","title":"Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models","created":"2023-12-05","cited_by_count":66,"area":"lr"},{"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":"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":"2509.20414","title":"SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent","created":"2025-09-24","cited_by_count":56,"area":"agents"},{"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":"2508.15769","title":"SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass","created":"2025-08-21","cited_by_count":54,"area":null},{"id":"2602.10116","title":"SAGE: Scalable Agentic 3D Scene Generation for Embodied AI","created":"2026-02-10","cited_by_count":50,"area":"agents"},{"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":"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":"2404.14368","title":"Graphic Design with Large Multimodal Model","created":"2024-04-22","cited_by_count":40,"area":null},{"id":"2311.14284","title":"Paragraph-to-Image Generation with Information-Enriched Diffusion Model","created":"2023-11-24","cited_by_count":39,"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":"2411.09823","title":"Architect: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D Inpainting","created":"2024-11-14","cited_by_count":38,"area":null},{"id":"2411.16602","title":"Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models","created":"2024-11-25","cited_by_count":38,"area":"diffusion"},{"id":"2411.06558","title":"Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement","created":"2024-11-10","cited_by_count":37,"area":null},{"id":"2502.18364","title":"ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation","created":"2025-02-25","cited_by_count":37,"area":null},{"id":"2311.13602","title":"Retrieval-Augmented Layout Transformer for Content-Aware Layout Generation","created":"2023-11-22","cited_by_count":35,"area":"rag"},{"id":"2404.00995","title":"PosterLlama: Bridging Design Ability of Langauge Model to Contents-Aware Layout Generation","created":"2024-04-01","cited_by_count":35,"area":null},{"id":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"area":null},{"id":"2407.02329","title":"MIGC++: Advanced Multi-Instance Generation Controller for Image Synthesis","created":"2024-07-02","cited_by_count":35,"area":null},{"id":"2406.03866","title":"LLplace: The 3D Indoor Scene Layout Generation and Editing via Large Language Model","created":"2024-06-06","cited_by_count":34,"area":null},{"id":"2405.21066","title":"Mixed Diffusion for 3D Indoor Scene Synthesis","created":"2024-05-31","cited_by_count":32,"area":"diffusion"},{"id":"2510.13678","title":"FlashWorld: High-quality 3D Scene Generation within Seconds","created":"2025-10-15","cited_by_count":32,"area":"diffusion"},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","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":"2504.01786","title":"BlenderGym: Benchmarking Foundational Model Systems for Graphics Editing","created":"2025-04-02","cited_by_count":31,"area":null},{"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":"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":"2310.12128","title":"DiagrammerGPT: Generating Open-Domain, Open-Platform Diagrams via LLM Planning","created":"2023-10-18","cited_by_count":29,"area":null},{"id":"2503.18476","title":"Global-Local Tree Search in VLMs for 3D Indoor Scene Generation","created":"2025-03-24","cited_by_count":29,"area":"mllm"},{"id":"2506.00742","title":"ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediary","created":"2025-05-31","cited_by_count":28,"area":null},{"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":"2506.05341","title":"Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning","created":"2025-06-05","cited_by_count":28,"area":"lr"},{"id":"2406.04983","title":"CityCraft: A Real Crafter for 3D City Generation","created":"2024-06-07","cited_by_count":26,"area":null},{"id":"2503.14756","title":"SceneEval: Evaluating Semantic Coherence in Text-Conditioned 3D Indoor Scene Synthesis","created":"2025-03-18","cited_by_count":26,"area":null},{"id":"2506.16960","title":"Visual-Instructed Degradation Diffusion for All-in-One Image Restoration","created":"2025-06-20","cited_by_count":26,"area":null},{"id":"2411.05815","title":"Graph Neural Networks for Financial Fraud Detection: A Review","created":"2024-11-01","cited_by_count":25,"area":null},{"id":"2503.04919","title":"FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placement","created":"2025-03-06","cited_by_count":25,"area":"lr"},{"id":"2410.20474","title":"GrounDiT: Grounding Diffusion Transformers via Noisy Patch Transplantation","created":"2024-10-27","cited_by_count":24,"area":"diffusion"},{"id":"2501.04648","title":"FlairGPT: Repurposing LLMs for Interior Designs","created":"2025-01-08","cited_by_count":24,"area":null},{"id":"2503.16848","title":"HSM: Hierarchical Scene Motifs for Multi-Scale Indoor Scene Generation","created":"2025-03-21","cited_by_count":24,"area":null},{"id":"2505.05474","title":"3D Scene Generation: A Survey","created":"2025-05-08","cited_by_count":24,"area":"diffusion"},{"id":"2505.02648","title":"MCCD: Multi-Agent Collaboration-based Compositional Diffusion for Complex Text-to-Image Generation","created":"2025-05-05","cited_by_count":23,"area":"diffusion"},{"id":"2310.06046","title":"LLM for SoC Security: A Paradigm Shift","created":"2023-10-09","cited_by_count":22,"area":null},{"id":"2312.04494","title":"AVA: Towards Autonomous Visualization Agents through Visual Perception-Driven Decision-Making","created":"2023-12-07","cited_by_count":21,"area":"agents"},{"id":"2403.18187","title":"LayoutFlow: Flow Matching for Layout Generation","created":"2024-03-27","cited_by_count":21,"area":"diffusion"},{"id":"2406.06465","title":"AID: Adapting Image2Video Diffusion Models for Instruction-guided Video Prediction","created":"2024-06-10","cited_by_count":21,"area":"diffusion"},{"id":"2502.15601","title":"WorldCraft: Photo-Realistic 3D World Creation and Customization via LLM Agents","created":"2025-02-21","cited_by_count":21,"area":"agents"},{"id":"2409.18336","title":"DeBaRA: Denoising-Based 3D Room Arrangement Generation","created":"2024-09-26","cited_by_count":20,"area":"diffusion"},{"id":"2309.09506","title":"LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models","created":"2023-09-18","cited_by_count":19,"area":null},{"id":"2311.15813","title":"FlowZero: Zero-Shot Text-to-Video Synthesis with LLM-Driven Dynamic Scene Syntax","created":"2023-11-27","cited_by_count":19,"area":"diffusion"},{"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":"2404.04251","title":"Who Evaluates the Evaluations? Objectively Scoring Text-to-Image Prompt Coherence Metrics with T2IScoreScore (TS2)","created":"2024-04-05","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":"2409.00558","title":"Compositional 3D-aware Video Generation with LLM Director","created":"2024-08-31","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":"2508.03692","title":"LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences","created":"2025-08-05","cited_by_count":17,"area":"wm"},{"id":"2505.07843","title":"PosterO: Structuring Layout Trees to Enable Language Models in Generalized Content-Aware Layout Generation","created":"2025-05-06","cited_by_count":16,"area":null},{"id":"2507.22076","title":"Test-time Prompt Refinement for Text-to-Image Models","created":"2025-07-22","cited_by_count":16,"area":null},{"id":"2310.15455","title":"UI Layout Generation with LLMs Guided by UI Grammar","created":"2023-10-24","cited_by_count":15,"area":null},{"id":"2410.12836","title":"EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editing","created":"2024-10-03","cited_by_count":15,"area":null},{"id":"2412.04237","title":"VASCAR: Content-Aware Layout Generation via Visual-Aware Self-Correction","created":"2024-12-05","cited_by_count":15,"area":null},{"id":"2412.05818","title":"SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation","created":"2024-12-08","cited_by_count":15,"area":"mllm"},{"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"},{"id":"2508.05899","title":"HOLODECK 2.0: Vision-Language-Guided 3D World Generation with Editing","created":"2025-08-07","cited_by_count":15,"area":null},{"id":"2504.19478","title":"CasaGPT: Cuboid Arrangement and Scene Assembly for Interior Design","created":"2025-04-28","cited_by_count":14,"area":null},{"id":"2506.07570","title":"OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization","created":"2025-06-09","cited_by_count":14,"area":"synth"},{"id":"2509.14981","title":"SPATIALGEN: Layout-guided 3D Indoor Scene Generation","created":"2025-09-18","cited_by_count":14,"area":null},{"id":"2312.08768","title":"Local Conditional Controlling for Text-to-Image Diffusion Models","created":"2023-12-14","cited_by_count":13,"area":"diffusion"}],"next_cursor":"100"}