{"total":52,"rows":[{"id":"2501.09038","title":"Do generative video models understand physical principles?","created":"2025-01-14","cited_by_count":161,"area":null},{"id":"2502.04507","title":"Fast Video Generation with Sliding Tile Attention","created":"2025-02-06","cited_by_count":128,"area":"diffusion"},{"id":"2411.08380","title":"EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation","created":"2024-11-13","cited_by_count":41,"area":null},{"id":"2406.04324","title":"SF-V: Single Forward Video Generation Model","created":"2024-06-06","cited_by_count":40,"area":"diffusion"},{"id":"2406.08659","title":"Vivid-ZOO: Multi-View Video Generation with Diffusion Model","created":"2024-06-12","cited_by_count":40,"area":"diffusion"},{"id":"2506.03517","title":"DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models","created":"2025-06-04","cited_by_count":34,"area":"diffusion"},{"id":"2408.04631","title":"Puppet-Master: Scaling Interactive Video Generation as a Motion Prior for Part-Level Dynamics","created":"2024-08-08","cited_by_count":28,"area":null},{"id":"2410.05203","title":"Beyond FVD: Enhanced Evaluation Metrics for Video Generation Quality","created":"2024-10-07","cited_by_count":22,"area":null},{"id":"2412.07583","title":"Mobile Video Diffusion","created":"2024-12-10","cited_by_count":18,"area":"diffusion"},{"id":"2412.14018","title":"SurgSora: Object-Aware Diffusion Model for Controllable Surgical Video Generation","created":"2024-12-18","cited_by_count":15,"area":"diffusion"},{"id":"2411.01171","title":"Fast and Memory-Efficient Video Diffusion Using Streamlined Inference","created":"2024-11-02","cited_by_count":14,"area":"diffusion"},{"id":"2506.07177","title":"Frame Guidance: Training-Free Guidance for Frame-Level Control in Video Diffusion Models","created":"2025-06-08","cited_by_count":11,"area":"diffusion"},{"id":"2512.05394","title":"Delving into Latent Spectral Biasing of Video VAEs for Superior Diffusability","created":"2025-12-05","cited_by_count":11,"area":"diffusion"},{"id":"2505.00209","title":"Direct Motion Models for Assessing Generated Videos","created":"2025-04-30","cited_by_count":10,"area":null},{"id":"2508.06082","title":"SwiftVideo: A Unified Framework for Few-Step Video Generation through Trajectory-Distribution Alignment","created":"2025-08-08","cited_by_count":10,"area":null},{"id":"2604.02329","title":"Generative World Renderer","created":"2026-04-02","cited_by_count":10,"area":null},{"id":"2601.01425","title":"DreamID-V:Bridging the Image-to-Video Gap for High-Fidelity Face Swapping via Diffusion Transformer","created":"2026-01-04","cited_by_count":9,"area":"diffusion"},{"id":"2603.13024","title":"SAW: Toward a Surgical Action World Model via Controllable and Scalable Video Generation","created":"2026-03-13","cited_by_count":9,"area":"wm"},{"id":"2411.01647","title":"Optical Flow Representation Alignment Mamba Diffusion Model for Medical Video Generation","created":"2024-11-03","cited_by_count":8,"area":"diffusion"},{"id":"2411.18375","title":"Individual Content and Motion Dynamics Preserved Pruning for Video Diffusion Models","created":"2024-11-27","cited_by_count":8,"area":"diffusion"},{"id":"2409.20556","title":"Inverse Painting: Reconstructing The Painting Process","created":"2024-09-30","cited_by_count":6,"area":null},{"id":"2509.26555","title":"Stable Cinemetrics : Structured Taxonomy and Evaluation for Professional Video Generation","created":"2025-09-30","cited_by_count":6,"area":null},{"id":"2608.04653","title":"Overcoming Statistical Bias in Action-Controllable World Models","created":"2026-08-05","cited_by_count":6,"area":"wm"},{"id":"2503.08122","title":"Toward Stable World Models: Measuring and Addressing World Instability in Generative Environments","created":"2025-03-11","cited_by_count":5,"area":"wm"},{"id":"2601.21716","title":"DreamActor-M2: Universal Character Image Animation via Spatiotemporal In-Context Learning","created":"2026-01-29","cited_by_count":5,"area":null},{"id":"2506.04956","title":"FEAT: Full-Dimensional Efficient Attention Transformer for Medical Video Generation","created":"2025-06-05","cited_by_count":4,"area":null},{"id":"2502.17863","title":"A Survey: Spatiotemporal Consistency in Video Generation","created":"2025-02-25","cited_by_count":3,"area":null},{"id":"2508.21052","title":"FakeParts: a New Family of AI-Generated DeepFakes","created":"2025-08-28","cited_by_count":3,"area":null},{"id":"2603.17426","title":"SHIFT: Motion Alignment in Video Diffusion Models with Adversarial Hybrid Fine-Tuning","created":"2026-03-18","cited_by_count":3,"area":"diffusion"},{"id":"2605.30346","title":"YoCausal: How Far is Video Generation from World Model? A Causality Perspective","created":"2026-05-28","cited_by_count":3,"area":"wm"},{"id":"2606.00133","title":"World Models: A Comprehensive Survey of Architectures, Methodologies, Reasoning Paradigms, and Applications","created":"2026-05-28","cited_by_count":3,"area":"wm"},{"id":"2608.13556","title":"V-RAE: Rethinking Video Latent Spaces for Generation","created":"2026-08-13","cited_by_count":3,"area":null},{"id":"2509.08818","title":"GeneVA: A Dataset of Human Annotations for Generative Text to Video Artifacts","created":"2025-09-10","cited_by_count":2,"area":null},{"id":"2509.17476","title":"Stable Video-Driven Portraits","created":"2025-09-22","cited_by_count":2,"area":"diffusion"},{"id":"2603.19048","title":"Measuring 3D Spatial Geometric Consistency in Dynamic Video Generation","created":"2026-03-19","cited_by_count":2,"area":null},{"id":"2602.11117","title":"HairWeaver: Few-Shot Photorealistic Hair Motion Synthesis with Sim-to-Real Guided Video Diffusion","created":"2026-02-11","cited_by_count":1,"area":"diffusion"},{"id":"2603.00194","title":"SKeDA: A Generative Watermarking Framework for Text-to-video Diffusion Models","created":"2026-02-27","cited_by_count":1,"area":"diffusion"},{"id":"2604.27443","title":"ABC: Any-Subset Autoregression via Non-Markovian Diffusion Bridges in Continuous Time and Space","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2606.21172","title":"BadDreamer: Transferable Backdoor Attacks against Video World Models for Autonomous Driving","created":"2026-06-19","cited_by_count":1,"area":"wm"},{"id":"2606.31004","title":"Auditing Generalization in AI-Generated Video Detection: A Six-Control Protocol and the VidAudit Toolkit","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2609.13006","title":"Physics-Aware Video Generation via Agentic Planning and Graph-Guided Optimization","created":"2026-07-16","cited_by_count":1,"area":"diffusion"},{"id":"2408.14227","title":"TC-PDM: Temporally Consistent Patch Diffusion Models for Infrared-to-Visible Video Translation","created":"2024-08-26","cited_by_count":0,"area":"diffusion"},{"id":"2409.06074","title":"SVS-GAN: Leveraging GANs for Semantic Video Synthesis","created":"2024-09-09","cited_by_count":0,"area":"diffusion"},{"id":"2512.06977","title":"Physics-Guided Diffusion Priors for Multi-Slice Reconstruction in Scientific Imaging","created":"2025-12-07","cited_by_count":0,"area":"diffusion"},{"id":"2605.20624","title":"Accelerating Video Inverse Problem Solvers with Autoregressive Diffusion Models","created":"2026-05-20","cited_by_count":0,"area":"diffusion"},{"id":"2606.07891","title":"C3VD-DEFCOL: A Deformable Colonoscopy Dataset with Time-Resolved 3D Ground Truth and Realistic Appearance","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.26384","title":"What Do Deepfake Benchmarks Measure? An Audit Using Frozen Self-Supervised Representations","created":"2026-06-24","cited_by_count":0,"area":"mechinterp"},{"id":"2608.01944","title":"UniMoCa: Unifying Motion and Camera Controls as Visual Proxies for Faithful Human Video Generation","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.15818","title":"FlowDance: Music-Driven Dance Video Generation with Parallel Pose and RGB Streams","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2609.04867","title":"PRISM-Bench: An Audio-Centric Diagnostic Benchmark for Text-to-Audio-Video Generation","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.35491","title":"From Scores to Samples: Elastic Forcing for Autoregressive Video Generation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.06847","title":"S2PD: Serial-to-Parallel Diffusion for Physically and Logically Consistent Video Generation","created":"2026-10-05","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}