{"list":"other","total":54,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2310.11513","title":"GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment","created":"2023-10-17","cited_by_count":972},{"id":"2405.09818","title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","created":"2024-05-16","cited_by_count":927},{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897},{"id":"2501.17811","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","created":"2025-01-29","cited_by_count":812},{"id":"2409.18869","title":"Emu3: Next-Token Prediction is All You Need","created":"2024-09-27","cited_by_count":781},{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752},{"id":"2306.10012","title":"MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing","created":"2023-06-16","cited_by_count":624},{"id":"2505.08775","title":"HealthBench: Evaluating Large Language Models Towards Improved Human Health","created":"2025-05-13","cited_by_count":429},{"id":"2409.04429","title":"VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation","created":"2024-09-06","cited_by_count":295},{"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},{"id":"2506.15564","title":"Show-o2: Improved Native Unified Multimodal Models","created":"2025-06-18","cited_by_count":250},{"id":"1903.02741","title":"RAVEN: A Dataset for Relational and Analogical Visual rEasoNing","created":"2019-03-07","cited_by_count":226},{"id":"2503.07265","title":"WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation","created":"2025-03-10","cited_by_count":204},{"id":"2505.11831","title":"ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems","created":"2025-05-17","cited_by_count":190},{"id":"2310.18235","title":"Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation","created":"2023-10-27","cited_by_count":171},{"id":"2501.05444","title":"Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark","created":"2025-01-09","cited_by_count":134},{"id":"2504.02826","title":"Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing","created":"2025-04-03","cited_by_count":99},{"id":"2505.02567","title":"Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities","created":"2025-05-05","cited_by_count":85},{"id":"2406.07546","title":"Commonsense-T2I Challenge: Can Text-to-Image Generation Models Understand Commonsense?","created":"2024-06-11","cited_by_count":52},{"id":"2601.06521","title":"BabyVision: Visual Reasoning Beyond Language","created":"2026-01-10","cited_by_count":49},{"id":"2508.17472","title":"T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation","created":"2025-08-24","cited_by_count":38},{"id":"2406.11802","title":"PhyBench: A Physical Commonsense Benchmark for Evaluating Text-to-Image Models","created":"2024-06-17","cited_by_count":36},{"id":"2602.20159","title":"A Very Big Video Reasoning Suite","created":"2026-02-23","cited_by_count":34},{"id":"2505.23493","title":"R2I-Bench: Benchmarking Reasoning-Driven Text-to-Image Generation","created":"2025-05-29","cited_by_count":32},{"id":"2406.10424","title":"What is the Visual Cognition Gap between Humans and Multimodal LLMs?","created":"2024-06-14","cited_by_count":30},{"id":"2510.13759","title":"Uni-MMMU: A Massive Multi-discipline Multimodal Unified Benchmark","created":"2025-10-15","cited_by_count":29},{"id":"2407.17773","title":"KiVA: Kid-inspired Visual Analogies for Testing Large Multimodal Models","created":"2024-07-25","cited_by_count":24},{"id":"2504.03641","title":"MME-Unify: A Comprehensive Benchmark for Unified Multimodal Understanding and Generation Models","created":"2025-04-04","cited_by_count":24},{"id":"2602.01756","title":"Mind-Brush: Integrating Agentic Cognitive Search and Reasoning into Image Generation","created":"2026-02-02","cited_by_count":23},{"id":"2511.16668","title":"V-ReasonBench: Toward Unified Reasoning Benchmark Suite for Video Generation Models","created":"2025-11-20","cited_by_count":22},{"id":"2506.10963","title":"MMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image Reasoning","created":"2025-06-12","cited_by_count":16},{"id":"2510.11026","title":"GIR-Bench: Versatile Benchmark for Generating Images with Reasoning","created":"2025-10-13","cited_by_count":15},{"id":"2502.16435","title":"Human Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMs","created":"2025-02-23","cited_by_count":13},{"id":"2603.23500","title":"UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation","created":"2026-03-24","cited_by_count":13},{"id":"2602.02140","title":"Quantifying the Gap between Understanding and Generation within Unified Multimodal Models","created":"2026-02-02","cited_by_count":12},{"id":"2601.22155","title":"UEval: A Benchmark for Unified Multimodal Generation","created":"2026-01-29","cited_by_count":9},{"id":"2603.02024","title":"MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image Reasoning","created":"2026-03-02","cited_by_count":9},{"id":"2508.12026","title":"Bongard-RWR+: Real-World Representations of Fine-Grained Concepts in Bongard Problems","created":"2025-08-16","cited_by_count":7},{"id":"2602.02465","title":"MentisOculi: Revealing the Limits of Reasoning with Mental Imagery","created":"2026-02-02","cited_by_count":7},{"id":"2507.11932","title":"Hyperphantasia: A Benchmark for Evaluating the Mental Visualization Capabilities of Multimodal LLMs","created":"2025-07-16","cited_by_count":5},{"id":"2511.18271","title":"Beyond Words and Pixels: A Benchmark for Implicit World Knowledge Reasoning in Generative Models","created":"2025-11-23","cited_by_count":4},{"id":"2512.06759","title":"VisChainBench: A Benchmark for Multi-Turn, Multi-Image Visual Reasoning Beyond Language Priors","created":"2025-12-07","cited_by_count":3},{"id":"2602.12196","title":"Visual Reasoning Benchmark: Evaluating Multimodal LLMs on Classroom-Authentic Visual Problems from Primary Education","created":"2026-02-12","cited_by_count":2},{"id":"2603.25823","title":"ViGoR-Bench: How Far Are Visual Generative Models From Zero-Shot Visual Reasoners?","created":"2026-03-26","cited_by_count":2}],"next_cursor":null}