{"total":48,"rows":[{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592,"area":null},{"id":"2304.03373","title":"Training-Free Layout Control with Cross-Attention Guidance","created":"2023-04-06","cited_by_count":313,"area":null},{"id":"2505.02567","title":"Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities","created":"2025-05-05","cited_by_count":85,"area":null},{"id":"2310.00367","title":"AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ","created":"2023-09-30","cited_by_count":79,"area":null},{"id":"2305.15328","title":"Visual Programming for Text-to-Image Generation and Evaluation","created":"2023-05-24","cited_by_count":54,"area":null},{"id":"2404.16820","title":"Revisiting Text-to-Image Evaluation with Gecko: On Metrics, Prompts, and Human Ratings","created":"2024-04-25","cited_by_count":44,"area":null},{"id":"2306.05357","title":"Unsupervised Compositional Concepts Discovery with Text-to-Image Generative Models","created":"2023-06-08","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":"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":"2302.03675","title":"Auditing Gender Presentation Differences in Text-to-Image Models","created":"2023-02-07","cited_by_count":22,"area":null},{"id":"2501.08537","title":"Complexity Control Facilitates Reasoning-Based Compositional Generalization in Transformers","created":"2025-01-15","cited_by_count":20,"area":null},{"id":"2307.05134","title":"TIAM -- A Metric for Evaluating Alignment in Text-to-Image Generation","created":"2023-07-11","cited_by_count":18,"area":null},{"id":"2312.03766","title":"Mismatch Quest: Visual and Textual Feedback for Image-Text Misalignment","created":"2023-12-05","cited_by_count":18,"area":null},{"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":"2405.05409","title":"Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing","created":"2024-05-08","cited_by_count":17,"area":null},{"id":"2308.04553","title":"From Fake to Real: Pretraining on Balanced Synthetic Images to Prevent Spurious Correlations in Image Recognition","created":"2023-08-08","cited_by_count":12,"area":null},{"id":"2312.02338","title":"A Contrastive Compositional Benchmark for Text-to-Image Synthesis: A Study with Unified Text-to-Image Fidelity Metrics","created":"2023-12-04","cited_by_count":12,"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":"2403.04321","title":"Discriminative Probing and Tuning for Text-to-Image Generation","created":"2024-03-07","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":"2411.16164","title":"Text-to-Image Synthesis: A Decade Survey","created":"2024-11-25","cited_by_count":9,"area":null},{"id":"2403.16394","title":"Skews in the Phenomenon Space Hinder Generalization in Text-to-Image Generation","created":"2024-03-25","cited_by_count":8,"area":null},{"id":"2404.05783","title":"A Survey on Responsible Generative AI: What to Generate and What Not","created":"2024-04-08","cited_by_count":8,"area":null},{"id":"2403.00467","title":"When ControlNet Meets Inexplicit Masks: A Case Study of ControlNet on its Contour-following Ability","created":"2024-03-01","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":"2305.15026","title":"Transferring Visual Attributes from Natural Language to Verified Image Generation","created":"2023-05-24","cited_by_count":4,"area":null},{"id":"2404.08540","title":"On the Robustness of Language Guidance for Low-Level Vision Tasks: Findings from Depth Estimation","created":"2024-04-12","cited_by_count":4,"area":null},{"id":"2410.10291","title":"Evaluating Semantic Variation in Text-to-Image Synthesis: A Causal Perspective","created":"2024-10-14","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":"2410.08534","title":"Quality Prediction of AI Generated Images and Videos: Emerging Trends and Opportunities","created":"2024-10-11","cited_by_count":3,"area":null},{"id":"2412.15922","title":"RiTTA: Modeling Event Relations in Text-to-Audio Generation","created":"2024-12-20","cited_by_count":3,"area":null},{"id":"2607.04423","title":"Transferability Between Understanding and Generation in Unified Multimodal Models","created":"2026-07-05","cited_by_count":3,"area":null},{"id":"2406.07699","title":"CUPID: Contextual Understanding of Prompt-conditioned Image Distributions","created":"2024-06-11","cited_by_count":2,"area":null},{"id":"2410.01816","title":"Automatic Scene Generation: State-of-the-Art Techniques, Models, Datasets, Challenges, and Future Prospects","created":"2024-09-14","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":"2510.15508","title":"Theoretical Refinement of CLIP by Utilizing Linear Structure of Optimal Similarity","created":"2025-10-17","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":"2607.21072","title":"Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text","created":"2026-07-23","cited_by_count":2,"area":null},{"id":"2401.14212","title":"Explicitly Representing Syntax Improves Sentence-to-layout Prediction of Unexpected Situations","created":"2024-01-25","cited_by_count":1,"area":null},{"id":"2502.19973","title":"Can Large Language Models Unveil the Mysteries? An Exploration of Their Ability to Unlock Information in Complex Scenarios","created":"2025-02-27","cited_by_count":1,"area":null},{"id":"2505.18730","title":"Align Beyond Prompts: Evaluating World Knowledge Alignment in Text-to-Image Generation","created":"2025-05-24","cited_by_count":1,"area":null},{"id":"2603.23924","title":"DepthArb: Training-Free Depth-Arbitrated Generation for Occlusion-Robust Image Synthesis","created":"2026-03-25","cited_by_count":1,"area":null},{"id":"2604.02482","title":"SEDGE: Structural Extrapolated Data Generation","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2603.00166","title":"Exploring the AI Obedience: Why is Generating a Pure Color Image Harder than CyberPunk?","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2604.16993","title":"Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectification","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2606.19941","title":"Compositionality Emerges in a Narrow Depth-Connectivity Regime: Architecture Constraints and Solution Manifolds","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2608.21713","title":"The Plan, Not the Decoder: Diagnosing and Repairing Compositional Failure in Reasoning-Augmented Text-to-Image Generation","created":"2026-08-22","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}