{"list":"other","total":52,"rows":[{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"2503.21755","title":"VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness","created":"2025-03-27","cited_by_count":315},{"id":"2506.09113","title":"Seedance 1.0: Exploring the Boundaries of Video Generation Models","created":"2025-06-10","cited_by_count":259},{"id":"2506.18871","title":"OmniGen2: Towards Instruction-Aligned Multimodal Generation","created":"2025-06-23","cited_by_count":253},{"id":"2406.03520","title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","created":"2024-06-05","cited_by_count":228},{"id":"2509.20328","title":"Video models are zero-shot learners and reasoners","created":"2025-09-24","cited_by_count":220},{"id":"2512.14614","title":"WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling","created":"2025-12-16","cited_by_count":170},{"id":"2501.16411","title":"PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding","created":"2025-01-27","cited_by_count":160},{"id":"2511.18870","title":"HunyuanVideo 1.5 Technical Report","created":"2025-11-24","cited_by_count":160},{"id":"2604.14148","title":"Seedance 2.0: Advancing Video Generation for World Complexity","created":"2026-04-15","cited_by_count":160},{"id":"2601.20540","title":"Advancing Open-source World Models","created":"2026-01-28","cited_by_count":154},{"id":"2106.08261","title":"Physion: Evaluating Physical Prediction from Vision in Humans and Machines","created":"2021-06-15","cited_by_count":153},{"id":"2503.06800","title":"VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation","created":"2025-03-09","cited_by_count":149},{"id":"2502.20694","title":"WorldModelBench: Judging Video Generation Models As World Models","created":"2025-02-28","cited_by_count":124},{"id":"2510.08377","title":"UniVideo: Unified Understanding, Generation, and Editing for Videos","created":"2025-10-09","cited_by_count":87},{"id":"2512.13507","title":"Seedance 1.5 pro: A Native Audio-Visual Joint Generation Foundation Model","created":"2025-12-15","cited_by_count":80},{"id":"1803.07616","title":"IntPhys: A Framework and Benchmark for Visual Intuitive Physics Reasoning","created":"2018-03-20","cited_by_count":73},{"id":"2512.16776","title":"Kling-Omni Technical Report","created":"2025-12-18","cited_by_count":71},{"id":"2502.11831","title":"Intuitive physics understanding emerges from self-supervised pretraining on natural videos","created":"2025-02-17","cited_by_count":70},{"id":"2506.09849","title":"IntPhys 2: Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments","created":"2025-06-11","cited_by_count":52},{"id":"2604.14268","title":"HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds","created":"2026-04-15","cited_by_count":44},{"id":"2510.26802","title":"Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark","created":"2025-10-30","cited_by_count":43},{"id":"2507.12465","title":"PhysX-3D: Physical-Grounded 3D Asset Generation","created":"2025-07-16","cited_by_count":42},{"id":"2511.04570","title":"Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm","created":"2025-11-06","cited_by_count":42},{"id":"2505.15929","title":"PhyX: Does Your Model Have the \"Wits\" for Physical Reasoning?","created":"2025-05-21","cited_by_count":38},{"id":"2506.00318","title":"Chain-of-Frames: Advancing Video Understanding in Multimodal LLMs via Frame-Aware Reasoning","created":"2025-05-31","cited_by_count":37},{"id":"2511.13648","title":"PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image","created":"2025-11-17","cited_by_count":37},{"id":"2507.13428","title":"\"PhyWorldBench\": A Comprehensive Evaluation of Physical Realism in Text-to-Video Models","created":"2025-07-17","cited_by_count":36},{"id":"2510.07172","title":"NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents","created":"2025-10-08","cited_by_count":36},{"id":"2602.20159","title":"A Very Big Video Reasoning Suite","created":"2026-02-23","cited_by_count":34},{"id":"2510.05094","title":"VChain: Chain-of-Visual-Thought for Reasoning in Video Generation","created":"2025-10-06","cited_by_count":32},{"id":"2512.00425","title":"What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewards","created":"2025-11-29","cited_by_count":25},{"id":"2511.16668","title":"V-ReasonBench: Toward Unified Reasoning Benchmark Suite for Video Generation Models","created":"2025-11-20","cited_by_count":22},{"id":"2512.19526","title":"QuantiPhy: A Quantitative Benchmark Evaluating Physical Reasoning Abilities of Vision-Language Models","created":"2025-12-22","cited_by_count":20},{"id":"2511.13704","title":"TiViBench: Benchmarking Think-in-Video Reasoning for Video Generative Models","created":"2025-11-17","cited_by_count":19},{"id":"2603.22212","title":"Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models","created":"2026-03-23","cited_by_count":18},{"id":"2603.16870","title":"Demystifying Video Reasoning","created":"2026-03-17","cited_by_count":14},{"id":"2511.15700","title":"First Frame Is the Place to Go for Video Content Customization","created":"2025-11-19","cited_by_count":12},{"id":"2605.21572","title":"PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects","created":"2026-05-20","cited_by_count":11},{"id":"2601.21037","title":"Thinking in Frames: How Visual Context and Test-Time Scaling Empower Video Reasoning","created":"2026-01-28","cited_by_count":10},{"id":"2601.10061","title":"CoF-T2I: Video Models as Pure Visual Reasoners for Text-to-Image Generation","created":"2026-01-15","cited_by_count":9},{"id":"2604.09415","title":"PhysInOne: Visual Physics Learning and Reasoning in One Suite","created":"2026-04-10","cited_by_count":9},{"id":"2602.12279","title":"UniT: Unified Multimodal Chain-of-Thought Test-time Scaling","created":"2026-02-12","cited_by_count":8},{"id":"2512.02942","title":"Benchmarking Scientific Understanding and Reasoning for Video Generation using VideoScience-Bench","created":"2025-12-02","cited_by_count":7},{"id":"2604.04746","title":"Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning","created":"2026-04-06","cited_by_count":7},{"id":"2601.16532","title":"AnchoredDream: Zero-Shot 360{\\deg} Indoor Scene Generation from a Single View via Geometric Grounding","created":"2026-01-23","cited_by_count":5},{"id":"2512.24952","title":"Beyond the Last Frame: Process-aware Evaluation for Generative Video Reasoning","created":"2025-12-31","cited_by_count":4}],"next_cursor":null}