{"total":19,"rows":[{"id":"2407.06358","title":"MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions","created":"2024-07-08","cited_by_count":146,"area":null},{"id":"2403.11050","title":"Endora: Video Generation Models as Endoscopy Simulators","created":"2024-03-17","cited_by_count":55,"area":null},{"id":"2504.01647","title":"FlowR: Flowing from Sparse to Dense 3D Reconstructions","created":"2025-04-02","cited_by_count":28,"area":null},{"id":"2409.17280","title":"Disco4D: Disentangled 4D Human Generation and Animation from a Single Image","created":"2024-09-25","cited_by_count":17,"area":null},{"id":"2501.05382","title":"Large Physics Models: Towards a collaborative approach with Large Language Models and Foundation Models","created":"2025-01-09","cited_by_count":14,"area":null},{"id":"2412.09597","title":"LiftImage3D: Lifting Any Single Image to 3D Gaussians with Video Generation Priors","created":"2024-12-12","cited_by_count":12,"area":null},{"id":"2412.00730","title":"SEED4D: A Synthetic Ego--Exo Dynamic 4D Data Generator, Driving Dataset and Benchmark","created":"2024-12-01","cited_by_count":8,"area":null},{"id":"2512.07831","title":"UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation","created":"2025-12-08","cited_by_count":7,"area":null},{"id":"2411.13609","title":"What You See Is What Matters: A Novel Visual and Physics-Based Metric for Evaluating Video Generation Quality","created":"2024-11-20","cited_by_count":6,"area":null},{"id":"2602.03796","title":"3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation","created":"2026-02-03","cited_by_count":6,"area":null},{"id":"2506.23957","title":"GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Rendering","created":"2025-06-30","cited_by_count":5,"area":null},{"id":"2512.01843","title":"PhyDetEx: Detecting and Explaining the Physical Plausibility of T2V Models","created":"2025-12-01","cited_by_count":5,"area":null},{"id":"2603.03160","title":"Kling-MotionControl Technical Report","created":"2026-03-03","cited_by_count":4,"area":null},{"id":"2406.11859","title":"\"Sora is Incredible and Scary\": Emerging Governance Challenges of Text-to-Video Generative AI Models","created":"2024-04-10","cited_by_count":3,"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":"2412.16277","title":"Mapping the Mind of an Instruction-based Image Editing using SMILE","created":"2024-12-20","cited_by_count":3,"area":null},{"id":"2603.19048","title":"Measuring 3D Spatial Geometric Consistency in Dynamic Video Generation","created":"2026-03-19","cited_by_count":2,"area":null},{"id":"2606.24829","title":"GeoT2V-Bench: Benchmarking 3D Consistency in Text-to-Video Models via 3D Reconstruction","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2605.14703","title":"Generating HDR Video from SDR Video","created":"2026-05-14","cited_by_count":0,"area":null}],"next_cursor":null}