{"total":92,"rows":[{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382,"area":null},{"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":"2403.17804","title":"Improving Text-to-Image Consistency via Automatic Prompt Optimization","created":"2024-03-26","cited_by_count":90,"area":null},{"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":"2310.01382","title":"Compressing LLMs: The Truth is Rarely Pure and Never Simple","created":"2023-10-02","cited_by_count":62,"area":null},{"id":"2404.05014","title":"MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators","created":"2024-04-07","cited_by_count":51,"area":null},{"id":"2403.12532","title":"UniBind: LLM-Augmented Unified and Balanced Representation Space to Bind Them All","created":"2024-03-19","cited_by_count":49,"area":null},{"id":"2409.16280","title":"MonoFormer: One Transformer for Both Diffusion and Autoregression","created":"2024-09-24","cited_by_count":46,"area":null},{"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":"2310.10402","title":"Real-Fake: Effective Training Data Synthesis Through Distribution Matching","created":"2023-10-16","cited_by_count":36,"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":"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":"2310.12128","title":"DiagrammerGPT: Generating Open-Domain, Open-Platform Diagrams via LLM Planning","created":"2023-10-18","cited_by_count":29,"area":null},{"id":"2501.10913","title":"Know \"No\" Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP","created":"2025-01-19","cited_by_count":28,"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":"2410.21418","title":"Large Language Models for Manufacturing","created":"2024-10-28","cited_by_count":24,"area":null},{"id":"2410.15391","title":"Layout-your-3D: Controllable and Precise 3D Generation with 2D Blueprint","created":"2024-10-20","cited_by_count":21,"area":null},{"id":"2406.01388","title":"AutoStudio: Crafting Consistent Subjects in Multi-turn Interactive Image Generation","created":"2024-06-03","cited_by_count":20,"area":null},{"id":"2406.04331","title":"PaCE: Parsimonious Concept Engineering for Large Language Models","created":"2024-06-06","cited_by_count":19,"area":null},{"id":"2509.12446","title":"PromptSculptor: Multi-Agent Based Text-to-Image Prompt Optimization","created":"2025-09-15","cited_by_count":19,"area":null},{"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":"2507.22076","title":"Test-time Prompt Refinement for Text-to-Image Models","created":"2025-07-22","cited_by_count":16,"area":null},{"id":"2412.08580","title":"LAION-SG: An Enhanced Large-Scale Dataset for Training Complex Image-Text Models with Structural Annotations","created":"2024-12-11","cited_by_count":12,"area":null},{"id":"2506.01955","title":"Dual-Process Image Generation","created":"2025-06-02","cited_by_count":12,"area":null},{"id":"2411.17176","title":"ChatGen: Automatic Text-to-Image Generation From FreeStyle Chatting","created":"2024-11-26","cited_by_count":11,"area":null},{"id":"2312.00588","title":"LucidDreaming: Controllable Object-Centric 3D Generation","created":"2023-11-30","cited_by_count":10,"area":null},{"id":"2506.08210","title":"A Comprehensive Study of Decoder-Only LLMs for Text-to-Image Generation","created":"2025-06-09","cited_by_count":10,"area":null},{"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":"2411.16164","title":"Text-to-Image Synthesis: A Decade Survey","created":"2024-11-25","cited_by_count":9,"area":null},{"id":"2411.17066","title":"Relations, Negations, and Numbers: Looking for Logic in Generative Text-to-Image Models","created":"2024-11-26","cited_by_count":9,"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":"2412.08464","title":"CC-Diff: Enhancing Contextual Coherence in Remote Sensing Image Synthesis","created":"2024-12-11","cited_by_count":8,"area":null},{"id":"2506.21101","title":"OracleFusion: Assisting the Decipherment of Oracle Bone Script with Structurally Constrained Semantic Typography","created":"2025-06-26","cited_by_count":8,"area":null},{"id":"2507.04451","title":"CoT-lized Diffusion: Let's Reinforce T2I Generation Step-by-step","created":"2025-07-06","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":"2603.12829","title":"coDrawAgents: A Multi-Agent Dialogue Framework for Compositional Image Generation","created":"2026-03-13","cited_by_count":7,"area":null},{"id":"2312.09252","title":"FineControlNet: Fine-level Text Control for Image Generation with Spatially Aligned Text Control Injection","created":"2023-12-14","cited_by_count":6,"area":null},{"id":"2403.13589","title":"ReGround: Improving Textual and Spatial Grounding at No Cost","created":"2024-03-20","cited_by_count":6,"area":null},{"id":"2410.00292","title":"Insight: A Multi-Modal Diagnostic Pipeline using LLMs for Ocular Surface Disease Diagnosis","created":"2024-10-01","cited_by_count":6,"area":null},{"id":"2411.00852","title":"EF-LLM: Energy Forecasting LLM with AI-assisted Automation, Enhanced Sparse Prediction, Hallucination Detection","created":"2024-10-30","cited_by_count":6,"area":null},{"id":"2411.07664","title":"Evaluating the Generation of Spatial Relations in Text and Image Generative Models","created":"2024-11-12","cited_by_count":6,"area":null},{"id":"2411.15435","title":"What Makes a Scene ? Scene Graph-based Evaluation and Feedback for Controllable Generation","created":"2024-11-23","cited_by_count":6,"area":null},{"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":"2501.10542","title":"Improved IR-based Bug Localization with Intelligent Relevance Feedback","created":"2025-01-17","cited_by_count":5,"area":null},{"id":"2512.07702","title":"Guiding What Not to Generate: Automated Negative Prompting for Text-Image Alignment","created":"2025-12-08","cited_by_count":5,"area":null},{"id":"2606.20799","title":"GroundShot: Visually Consistent Multi-Shot Long Video Generation via Entity-Grounded Shot Scheduling","created":"2026-06-18","cited_by_count":5,"area":null},{"id":"2401.15688","title":"Divide and Conquer: Language Models can Plan and Self-Correct for Compositional Text-to-Image Generation","created":"2024-01-28","cited_by_count":4,"area":null},{"id":"2410.06243","title":"Unsupervised Model Diagnosis","created":"2024-10-08","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":"2412.08859","title":"ViUniT: Visual Unit Tests for More Robust Visual Programming","created":"2024-12-12","cited_by_count":4,"area":null},{"id":"2503.02399","title":"VisAgent: Narrative-Preserving Story Visualization Framework","created":"2025-03-04","cited_by_count":4,"area":null},{"id":"2503.06506","title":"Fine-Grained Alignment and Noise Refinement for Compositional Text-to-Image Generation","created":"2025-03-09","cited_by_count":4,"area":null},{"id":"2510.07940","title":"TTOM: Test-Time Optimization and Memorization for Compositional Video Generation","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2506.05688","title":"Voice Impression Control in Zero-Shot TTS","created":"2025-06-06","cited_by_count":3,"area":null},{"id":"2509.12046","title":"Layout-Conditioned Autoregressive Text-to-Image Generation via Structured Masking","created":"2025-09-15","cited_by_count":3,"area":null},{"id":"2604.25477","title":"DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing","created":"2026-04-28","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":"2405.18304","title":"Multi-modal Generation via Cross-Modal In-Context Learning","created":"2024-05-28","cited_by_count":2,"area":null},{"id":"2410.10672","title":"Large Language Model Evaluation via Matrix Nuclear-Norm","created":"2024-10-14","cited_by_count":2,"area":null},{"id":"2410.11963","title":"CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal Learning","created":"2024-10-15","cited_by_count":2,"area":null},{"id":"2411.19182","title":"SOWing Information: Cultivating Contextual Coherence with MLLMs in Image Generation","created":"2024-11-28","cited_by_count":2,"area":null},{"id":"2412.13486","title":"T$^3$-S2S: Training-free Triplet Tuning for Sketch to Scene Synthesis in Controllable Concept Art Generation","created":"2024-12-18","cited_by_count":2,"area":null},{"id":"2506.01370","title":"PointT2I: LLM-based text-to-image generation via keypoints","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2506.23418","title":"Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models","created":"2025-06-29","cited_by_count":2,"area":null},{"id":"2512.08180","title":"GeoLoom: High-quality Geometric Diagram Generation from Textual Input","created":"2025-12-09","cited_by_count":2,"area":null},{"id":"2605.11722","title":"EPIC: Efficient Predicate-Guided Inference-Time Control for Compositional Text-to-Image Generation","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2404.04376","title":"ClickDiffusion: Harnessing LLMs for Interactive Precise Image Editing","created":"2024-04-05","cited_by_count":1,"area":null},{"id":"2509.23452","title":"FoR-SALE: Frame of Reference-guided Spatial Adjustment in LLM-based Diffusion Editing","created":"2025-09-27","cited_by_count":1,"area":null},{"id":"2510.00806","title":"From Seeing to Predicting: A Vision-Language Framework for Trajectory Forecasting and Controlled Video Generation","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2512.01686","title":"DreamingComics: A Story Visualization Pipeline via Subject and Layout Customized Generation using Video Models","created":"2025-12-01","cited_by_count":1,"area":null},{"id":"2512.08645","title":"Chain-of-Image Generation: Toward Monitorable and Controllable Image Generation","created":"2025-12-09","cited_by_count":1,"area":null},{"id":"2512.10669","title":"Learning by Analogy: A Causal Framework for Composition Generalization","created":"2025-12-11","cited_by_count":1,"area":null},{"id":"2601.04706","title":"Forge-and-Quench: Enhancing Image Generation for Higher Fidelity in Unified Multimodal Models","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2606.00477","title":"Do Text Edits Generalize to Visual Generation? Benchmarking Cross-Modal Knowledge Editing in UMMs","created":"2026-05-30","cited_by_count":1,"area":null},{"id":"2311.09680","title":"Trustworthy Large Models in Vision: A Survey","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2401.12671","title":"Context Matters: Pushing the Boundaries of Open-Ended Answer Generation with Graph-Structured Knowledge Context","created":"2024-01-23","cited_by_count":0,"area":null},{"id":"2412.14085","title":"Future Research Avenues for Artificial Intelligence in Digital Gaming: An Exploratory Report","created":"2024-12-18","cited_by_count":0,"area":null},{"id":"2501.14046","title":"LLM-guided Instance-level Image Manipulation with Diffusion U-Net Cross-Attention Maps","created":"2025-01-23","cited_by_count":0,"area":null},{"id":"2504.08714","title":"Generating Fine Details of Entity Interactions","created":"2025-04-11","cited_by_count":0,"area":null},{"id":"2505.24086","title":"ComposeAnything: Composite Object Priors for Text-to-Image Generation","created":"2025-05-30","cited_by_count":0,"area":null},{"id":"2511.18378","title":"Synthetic Curriculum Reinforces Compositional Text-to-Image Generation","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2601.05546","title":"MoGen: A Unified Collaborative Framework for Controllable Multi-Object Image Generation","created":"2026-01-09","cited_by_count":0,"area":null},{"id":"2603.17895","title":"A Creative Agent is Worth a 64-Token Template","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2604.17749","title":"Ego-InBetween: Generating Object State Transitions in Ego-Centric Videos","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2604.22302","title":"Knowledge Visualization: A Benchmark and Method for Knowledge-Intensive Text-to-Image Generation","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2607.14945","title":"Introspective Attention Modulation for Safe Text-to-Image Generation","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2608.20336","title":"WithEveryone: Unified Planning and Identity Grounding for Group Image Generation","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2609.07029","title":"LoGAN: Multilingual Font Localization with Generative Agents","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.32389","title":"RefCompose: Multi-Reference Image Generation via LoRA-Conditioned Diffusion","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.00383","title":"EvoGen-Harness: Learning Where and How to Evolve Image-Generation Harnesses","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.03084","title":"NegT2IBench: When Negation Changes the Picture. A Polarity Benchmark for Text-to-Image Models","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}