{"total":113,"rows":[{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822,"area":null},{"id":"2404.01291","title":"Evaluating Text-to-Visual Generation with Image-to-Text Generation","created":"2024-04-01","cited_by_count":474,"area":null},{"id":"2407.05282","title":"UltraEdit: Instruction-based Fine-Grained Image Editing at Scale","created":"2024-07-07","cited_by_count":268,"area":null},{"id":"2312.14867","title":"VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation","created":"2023-12-22","cited_by_count":201,"area":null},{"id":"2406.13743","title":"GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation","created":"2024-06-19","cited_by_count":135,"area":null},{"id":"2404.19753","title":"DOCCI: Descriptions of Connected and Contrasting Images","created":"2024-04-30","cited_by_count":132,"area":null},{"id":"2406.16855","title":"DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation","created":"2024-06-24","cited_by_count":131,"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":"2406.04485","title":"GenAI Arena: An Open Evaluation Platform for Generative Models","created":"2024-06-06","cited_by_count":82,"area":null},{"id":"2404.04125","title":"No \"Zero-Shot\" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance","created":"2024-04-04","cited_by_count":75,"area":null},{"id":"2404.01030","title":"Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation","created":"2024-04-01","cited_by_count":66,"area":null},{"id":"2407.05965","title":"T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models","created":"2024-07-08","cited_by_count":66,"area":null},{"id":"2404.12241","title":"Introducing v0.5 of the AI Safety Benchmark from MLCommons","created":"2024-04-18","cited_by_count":62,"area":null},{"id":"2311.17138","title":"Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for now","created":"2023-11-28","cited_by_count":61,"area":null},{"id":"2408.14339","title":"ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty","created":"2024-08-26","cited_by_count":61,"area":null},{"id":"2501.12612","title":"T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation","created":"2025-01-22","cited_by_count":48,"area":null},{"id":"2411.13503","title":"VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models","created":"2024-11-20","cited_by_count":45,"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":"2406.11802","title":"PhyBench: A Physical Commonsense Benchmark for Evaluating Text-to-Image Models","created":"2024-06-17","cited_by_count":36,"area":null},{"id":"2405.01719","title":"Inherent Trade-Offs between Diversity and Stability in Multi-Task Benchmarks","created":"2024-05-02","cited_by_count":28,"area":null},{"id":"2312.03817","title":"Diffusion Illusions: Hiding Images in Plain Sight","created":"2023-12-06","cited_by_count":26,"area":null},{"id":"2311.07509","title":"A Benchmark to Understand the Role of Knowledge Graphs on Large Language Model's Accuracy for Question Answering on Enterprise SQL Databases","created":"2023-11-13","cited_by_count":25,"area":null},{"id":"2405.20574","title":"Open Ko-LLM Leaderboard: Evaluating Large Language Models in Korean with Ko-H5 Benchmark","created":"2024-05-31","cited_by_count":23,"area":null},{"id":"2311.12997","title":"Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks","created":"2023-11-21","cited_by_count":22,"area":null},{"id":"2407.03418","title":"HEMM: Holistic Evaluation of Multimodal Foundation Models","created":"2024-07-03","cited_by_count":21,"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":"2409.10566","title":"Eureka: Evaluating and Understanding Large Foundation Models","created":"2024-09-13","cited_by_count":18,"area":null},{"id":"2403.18493","title":"VersaT2I: Improving Text-to-Image Models with Versatile Reward","created":"2024-03-27","cited_by_count":17,"area":null},{"id":"2505.19415","title":"MMIG-Bench: Towards Comprehensive and Explainable Evaluation of Multi-Modal Image Generation Models","created":"2025-05-26","cited_by_count":17,"area":null},{"id":"2405.04457","title":"Towards Geographic Inclusion in the Evaluation of Text-to-Image Models","created":"2024-05-07","cited_by_count":16,"area":null},{"id":"2408.14468","title":"K-Sort Arena: Efficient and Reliable Benchmarking for Generative Models via K-wise Human Preferences","created":"2024-08-26","cited_by_count":16,"area":null},{"id":"2601.20354","title":"Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models","created":"2026-01-28","cited_by_count":16,"area":null},{"id":"2401.16092","title":"Multilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help You","created":"2024-01-29","cited_by_count":15,"area":null},{"id":"2412.18645","title":"Scendi Score: Prompt-Aware Diversity Evaluation via Schur Complement of CLIP Embeddings","created":"2024-12-24","cited_by_count":15,"area":null},{"id":"2412.04300","title":"T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts","created":"2024-12-05","cited_by_count":14,"area":null},{"id":"2506.07998","title":"Generative Modeling of Weights: Generalization or Memorization?","created":"2025-06-09","cited_by_count":14,"area":null},{"id":"2405.20701","title":"Unveiling the Lexical Sensitivity of LLMs: Combinatorial Optimization for Prompt Enhancement","created":"2024-05-31","cited_by_count":13,"area":null},{"id":"2509.09666","title":"Unified Multimodal Models as Auto-Encoders","created":"2025-09-11","cited_by_count":13,"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":"2406.14774","title":"Evaluating Numerical Reasoning in Text-to-Image Models","created":"2024-06-20","cited_by_count":12,"area":null},{"id":"2411.13842","title":"Detecting Human Artifacts from Text-to-Image Models","created":"2024-11-21","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":"2406.16746","title":"The Responsible Foundation Model Development Cheatsheet: A Review of Tools & Resources","created":"2024-06-24","cited_by_count":11,"area":null},{"id":"2402.19472","title":"Efficient Lifelong Model Evaluation in an Era of Rapid Progress","created":"2024-02-29","cited_by_count":10,"area":null},{"id":"2405.17512","title":"On Fairness of Low-Rank Adaptation of Large Models","created":"2024-05-27","cited_by_count":9,"area":null},{"id":"2407.00138","title":"Analyzing Quality, Bias, and Performance in Text-to-Image Generative Models","created":"2024-06-28","cited_by_count":9,"area":null},{"id":"2408.12682","title":"MultiMed: Massively Multimodal and Multitask Medical Understanding","created":"2024-08-22","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":"2502.20170","title":"Re-evaluating Open-ended Evaluation of Large Language Models","created":"2025-02-27","cited_by_count":8,"area":null},{"id":"2410.05920","title":"FINALLY: fast and universal speech enhancement with studio-like quality","created":"2024-10-08","cited_by_count":7,"area":null},{"id":"2410.18615","title":"FairQueue: Rethinking Prompt Learning for Fair Text-to-Image Generation","created":"2024-10-24","cited_by_count":7,"area":null},{"id":"2412.11767","title":"IDEA-Bench: How Far are Generative Models from Professional Designing?","created":"2024-12-16","cited_by_count":7,"area":null},{"id":"2412.15677","title":"AI-generated Image Quality Assessment in Visual Communication","created":"2024-12-20","cited_by_count":7,"area":null},{"id":"2404.17255","title":"SDFD: Building a Versatile Synthetic Face Image Dataset with Diverse Attributes","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2407.09230","title":"Surgical Text-to-Image Generation","created":"2024-07-12","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":"2510.19557","title":"The Intricate Dance of Prompt Complexity, Quality, Diversity, and Consistency in T2I Models","created":"2025-10-22","cited_by_count":6,"area":null},{"id":"2412.04189","title":"HANDI: Hand-Centric Text-and-Image Conditioned Video Generation","created":"2024-12-05","cited_by_count":5,"area":null},{"id":"2412.10604","title":"EvalGIM: A Library for Evaluating Generative Image Models","created":"2024-12-13","cited_by_count":5,"area":null},{"id":"2608.12122","title":"HandEdit: A Unified Benchmark for Egocentric Human-to-Robot Dexterous Hand Image Editing","created":"2026-08-12","cited_by_count":5,"area":null},{"id":"2404.12104","title":"Ethical-Lens: Curbing Malicious Usages of Open-Source Text-to-Image Models","created":"2024-04-18","cited_by_count":4,"area":null},{"id":"2406.08845","title":"Rethinking Human Evaluation Protocol for Text-to-Video Models: Enhancing Reliability,Reproducibility, and Practicality","created":"2024-06-13","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":"2410.22551","title":"FairSkin: Fair Diffusion for Skin Disease Image Generation","created":"2024-10-29","cited_by_count":4,"area":null},{"id":"2411.02437","title":"TypeScore: A Text Fidelity Metric for Text-to-Image Generative Models","created":"2024-11-02","cited_by_count":4,"area":null},{"id":"2505.19614","title":"Multiplicity is an Inevitable and Inherent Challenge in Multimodal Learning","created":"2025-05-26","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":"2412.12774","title":"A Framework for Critical Evaluation of Text-to-Image Models: Integrating Art Historical Analysis, Artistic Exploration, and Critical Prompt Engineering","created":"2024-12-17","cited_by_count":3,"area":null},{"id":"2507.22100","title":"Trade-offs in Image Generation: How Do Different Dimensions Interact?","created":"2025-07-29","cited_by_count":3,"area":null},{"id":"2508.20410","title":"UI-Bench: A Benchmark for Evaluating Design Capabilities of AI Text-to-App Tools","created":"2025-08-28","cited_by_count":3,"area":null},{"id":"2510.14949","title":"DialectGen: Benchmarking and Improving Dialect Robustness in Multimodal Generation","created":"2025-10-16","cited_by_count":3,"area":null},{"id":"2603.26154","title":"IPV-Bench: Benchmarking Image Protection Methods under Diverse Image-to-Video Generation Scenarios","created":"2026-03-27","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":"2404.18316","title":"Position: Do Not Explain Vision Models Without Context","created":"2024-04-28","cited_by_count":2,"area":null},{"id":"2406.14473","title":"Data-Centric AI in the Age of Large Language Models","created":"2024-06-20","cited_by_count":2,"area":null},{"id":"2407.19775","title":"Model Agnostic Hybrid Sharding For Heterogeneous Distributed Inference","created":"2024-07-29","cited_by_count":2,"area":null},{"id":"2409.03257","title":"Understanding LLM Development Through Longitudinal Study: Insights from the Open Ko-LLM Leaderboard","created":"2024-09-05","cited_by_count":2,"area":null},{"id":"2411.01099","title":"Few-Class Arena: A Benchmark for Efficient Selection of Vision Models and Dataset Difficulty Measurement","created":"2024-11-02","cited_by_count":2,"area":null},{"id":"2411.13787","title":"Adaptive Routing of Text-to-Image Generation Requests Between Large Cloud Model and Light-Weight Edge Model","created":"2024-11-21","cited_by_count":2,"area":null},{"id":"2505.11314","title":"CROC: Evaluating and Training T2I Metrics with Pseudo- and Human-Labeled Contrastive Robustness Checks","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2506.02308","title":"MINT: Multimodal Instruction Tuning with Multimodal Interaction Grouping","created":"2025-06-02","cited_by_count":2,"area":null},{"id":"2509.08940","title":"Discovering Divergent Representations between Text-to-Image Models","created":"2025-09-10","cited_by_count":2,"area":null},{"id":"2510.07441","title":"DynamicEval: Rethinking Evaluation for Dynamic Text-to-Video Synthesis","created":"2025-10-08","cited_by_count":2,"area":null},{"id":"2608.09666","title":"Open Evaluation Agent: Efficient and Promptable Evaluation of Visual Generative Models","created":"2026-08-10","cited_by_count":2,"area":null},{"id":"2403.02118","title":"Position: Towards Implicit Prompt For Text-To-Image Models","created":"2024-03-04","cited_by_count":1,"area":null},{"id":"2410.02230","title":"Mitigating Downstream Model Risks via Model Provenance","created":"2024-10-03","cited_by_count":1,"area":null},{"id":"2410.18218","title":"Optimizing the role of human evaluation in LLM-based spoken document summarization systems","created":"2024-10-23","cited_by_count":1,"area":null},{"id":"2411.15509","title":"Interactive Visual Assessment for Text-to-Image Generation Models","created":"2024-11-23","cited_by_count":1,"area":null},{"id":"2503.17669","title":"TDRI: Two-Phase Dialogue Refinement and Co-Adaptation for Interactive Image Generation","created":"2025-03-22","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":"2506.01493","title":"Efficiency without Compromise: CLIP-aided Text-to-Image GANs with Increased Diversity","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2507.18633","title":"Identifying Prompted Artist Names from Generated Images","created":"2025-07-24","cited_by_count":1,"area":null},{"id":"2509.00849","title":"Prompting Away Stereotypes? Evaluating Bias in Text-to-Image Models for Occupations","created":"2025-08-31","cited_by_count":1,"area":null},{"id":"2512.16303","title":"PixelArena: A benchmark for Pixel-Precision Visual Intelligence","created":"2025-12-18","cited_by_count":1,"area":null},{"id":"2602.07593","title":"Beyond Arrow: From Impossibility to Possibilities in Multi-Criteria Benchmarking","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2604.25119","title":"Evaluation without Generation: Non-Generative Assessment of Harmful Model Specialization with Applications to CSAM","created":"2026-04-28","cited_by_count":1,"area":null},{"id":"2607.11199","title":"DynEval: Holistic Evaluations of T2I Generative Models in the Wild","created":"2026-07-13","cited_by_count":1,"area":null},{"id":"2608.01780","title":"Investigating Social Bias in Narrative Image Generation","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2608.14976","title":"Benchmarking Frontier Text-to-Image Models on Image-Description Prompts","created":"2026-08-15","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}],"next_cursor":"100"}