{"total":53,"rows":[{"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":"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":"2311.03335","title":"Cross-Image Attention for Zero-Shot Appearance Transfer","created":"2023-11-06","cited_by_count":136,"area":null},{"id":"2311.17946","title":"DreamSync: Aligning Text-to-Image Generation with Image Understanding Feedback","created":"2023-11-29","cited_by_count":58,"area":null},{"id":"2406.08656","title":"TC-Bench: Benchmarking Temporal Compositionality in Text-to-Video and Image-to-Video Generation","created":"2024-06-12","cited_by_count":43,"area":null},{"id":"2401.06105","title":"PALP: Prompt Aligned Personalization of Text-to-Image Models","created":"2024-01-11","cited_by_count":35,"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":"2403.11650","title":"Prioritized Semantic Learning for Zero-shot Instance Navigation","created":"2024-03-18","cited_by_count":31,"area":null},{"id":"2404.01294","title":"CosmicMan: A Text-to-Image Foundation Model for Humans","created":"2024-04-01","cited_by_count":30,"area":null},{"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":"2312.03766","title":"Mismatch Quest: Visual and Textual Feedback for Image-Text Misalignment","created":"2023-12-05","cited_by_count":18,"area":null},{"id":"2408.06518","title":"Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in Language Models","created":"2024-08-12","cited_by_count":15,"area":null},{"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":"2503.06956","title":"LatexBlend: Scaling Multi-concept Customized Generation with Latent Textual Blending","created":"2025-03-10","cited_by_count":10,"area":null},{"id":"2405.05966","title":"Natural Language Processing RELIES on Linguistics","created":"2024-05-09","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":"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":"2406.00687","title":"Lay-A-Scene: Personalized 3D Object Arrangement Using Text-to-Image Priors","created":"2024-06-02","cited_by_count":7,"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":"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":"2504.01137","title":"Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models","created":"2025-04-01","cited_by_count":4,"area":null},{"id":"2603.21937","title":"MultiBind: A Benchmark for Attribute Misbinding in Multi-Subject Generation","created":"2026-03-23","cited_by_count":4,"area":null},{"id":"2605.10079","title":"SocialDirector: Training-Free Social Interaction Control for Multi-Person Video Generation","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2512.01302","title":"DCText: Scheduled Attention Masking for Visual Text Generation via Divide-and-Conquer Strategy","created":"2025-12-01","cited_by_count":3,"area":null},{"id":"2412.11594","title":"VersaGen: Unleashing Versatile Visual Control for Text-to-Image Synthesis","created":"2024-12-16","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":"2507.17377","title":"A Conditional Probability Framework for Compositional Zero-shot Learning","created":"2025-07-23","cited_by_count":2,"area":null},{"id":"2508.13866","title":"SAGA: Learning Signal-Aligned Distributions for Improved Text-to-Image Generation","created":"2025-08-19","cited_by_count":2,"area":null},{"id":"2508.19791","title":"Color Bind: Exploring Color Perception in Text-to-Image Models","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2510.14376","title":"DOS: Directional Object Separation in Text Embeddings for Multi-Object Image Generation","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2510.15015","title":"DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2605.18018","title":"See What I Mean: Aligning Vision and Language Representations for Video Fine-grained Object Understanding","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2410.03505","title":"Classification-Denoising Networks","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2504.17525","title":"Text-to-Image Alignment in Denoising-Based Models through Step Selection","created":"2025-04-24","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":"2605.23178","title":"Composing People Together: Iterative Pose-Image Generation for Multi-Person Interaction Scenes","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2605.30925","title":"MultiAct: Text-to-Motion Generation from Composite Text via Tailored Attention Guidance","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2609.02255","title":"T2LSC-Bench: Benchmarking Localized Semantic Control in Text-to-Image Generation","created":"2026-09-02","cited_by_count":1,"area":null},{"id":"2309.04148","title":"Representation Synthesis by Probabilistic Many-Valued Logic Operation in Self-Supervised Learning","created":"2023-09-08","cited_by_count":0,"area":null},{"id":"2503.14428","title":"Comp-Attn: Present-and-Align Attention for Compositional Video Generation","created":"2025-03-18","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":"2506.22685","title":"Mitigating Semantic Collapse in Generative Personalization with Test-Time Embedding Adjustment","created":"2025-06-27","cited_by_count":0,"area":null},{"id":"2510.23515","title":"FreeFuse: Multi-Subject LoRA Fusion via Adaptive Token-Level Routing at Test Time","created":"2025-10-27","cited_by_count":0,"area":null},{"id":"2511.06002","title":"MALeR: Improving Compositional Fidelity in Layout-Guided Generation","created":"2025-11-08","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":"2512.09095","title":"Food Image Generation on Multi-Noun Categories","created":"2025-12-09","cited_by_count":0,"area":null},{"id":"2601.17666","title":"Training-Free Text-to-Image Compositional Food Generation via Prompt Grafting","created":"2026-01-25","cited_by_count":0,"area":null},{"id":"2602.18282","title":"DEIG: Detail-Enhanced Instance Generation with Fine-Grained Semantic Control","created":"2026-02-20","cited_by_count":0,"area":null},{"id":"2606.22550","title":"Training-Free Semantic Correction for Autoregressive Visual Models","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2608.00410","title":"Where did the ambiguity go? Examining how multimodal models interpret polysemous words","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2608.14403","title":"CRAFT: Constrained Reward via Attention Fine-Tuning for Subject Personalization without Composed Targets","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2609.20816","title":"Paint-Anything: Unified Any-Color Control for Image Generation and Editing","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2610.03512","title":"ProgressNet: Sketching and Prompting with a Frozen Text-to-Image Model","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}