{"total":58,"rows":[{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492,"area":null},{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477,"area":null},{"id":"2407.02371","title":"OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation","created":"2024-07-02","cited_by_count":341,"area":null},{"id":"2305.10874","title":"Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation","created":"2023-05-18","cited_by_count":154,"area":null},{"id":"2410.08260","title":"Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content","created":"2024-10-10","cited_by_count":135,"area":null},{"id":"2406.09399","title":"OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation","created":"2024-06-13","cited_by_count":118,"area":null},{"id":"2309.08587","title":"Compositional Foundation Models for Hierarchical Planning","created":"2023-09-15","cited_by_count":95,"area":null},{"id":"2309.07906","title":"Generative Image Dynamics","created":"2023-09-14","cited_by_count":94,"area":null},{"id":"2307.06940","title":"Animate-A-Story: Storytelling with Retrieval-Augmented Video Generation","created":"2023-07-13","cited_by_count":90,"area":null},{"id":"2407.01094","title":"Evaluation of Text-to-Video Generation Models: A Dynamics Perspective","created":"2024-07-01","cited_by_count":67,"area":null},{"id":"2312.06734","title":"DiffCast: A Unified Framework via Residual Diffusion for Precipitation Nowcasting","created":"2023-12-11","cited_by_count":61,"area":null},{"id":"2408.13239","title":"CustomCrafter: Customized Video Generation with Preserving Motion and Concept Composition Abilities","created":"2024-08-23","cited_by_count":60,"area":null},{"id":"2404.12391","title":"On the Content Bias in Fr\\'echet Video Distance","created":"2024-04-18","cited_by_count":52,"area":null},{"id":"2305.03989","title":"LEO: Generative Latent Image Animator for Human Video Synthesis","created":"2023-05-06","cited_by_count":40,"area":null},{"id":"2403.16407","title":"A Survey on Long Video Generation: Challenges, Methods, and Prospects","created":"2024-03-25","cited_by_count":40,"area":null},{"id":"2411.05902","title":"Autoregressive Models in Vision: A Survey","created":"2024-11-08","cited_by_count":39,"area":null},{"id":"2411.06525","title":"I2VControl-Camera: Precise Video Camera Control with Adjustable Motion Strength","created":"2024-11-10","cited_by_count":39,"area":null},{"id":"2501.12389","title":"Taming Teacher Forcing for Masked Autoregressive Video Generation","created":"2025-01-21","cited_by_count":30,"area":null},{"id":"2308.14177","title":"AI-Generated Content (AIGC) for Various Data Modalities: A Survey","created":"2023-08-27","cited_by_count":25,"area":null},{"id":"2411.17765","title":"I2VControl: Disentangled and Unified Video Motion Synthesis Control","created":"2024-11-26","cited_by_count":20,"area":null},{"id":"2406.00808","title":"EchoNet-Synthetic: Privacy-preserving Video Generation for Safe Medical Data Sharing","created":"2024-06-02","cited_by_count":18,"area":null},{"id":"2306.11503","title":"The Age of Synthetic Realities: Challenges and Opportunities","created":"2023-06-09","cited_by_count":15,"area":null},{"id":"2411.13552","title":"REDUCIO! Generating 1K Video within 16 Seconds using Extremely Compressed Motion Latents","created":"2024-11-20","cited_by_count":14,"area":null},{"id":"2406.07398","title":"Visual Representation Learning with Stochastic Frame Prediction","created":"2024-06-11","cited_by_count":10,"area":null},{"id":"2311.14294","title":"Decouple Content and Motion for Conditional Image-to-Video Generation","created":"2023-11-24","cited_by_count":9,"area":null},{"id":"2407.13545","title":"DiffuX2CT: Diffusion Learning to Reconstruct CT Images from Biplanar X-Rays","created":"2024-07-18","cited_by_count":9,"area":null},{"id":"2505.13437","title":"FinePhys: Fine-grained Human Action Generation by Explicitly Incorporating Physical Laws for Effective Skeletal Guidance","created":"2025-05-19","cited_by_count":9,"area":null},{"id":"2401.10822","title":"ActAnywhere: Subject-Aware Video Background Generation","created":"2024-01-19","cited_by_count":8,"area":null},{"id":"2407.09774","title":"ContextualStory: Consistent Visual Storytelling with Spatially-Enhanced and Storyline Context","created":"2024-07-13","cited_by_count":8,"area":null},{"id":"2412.01987","title":"ShowHowTo: Generating Scene-Conditioned Step-by-Step Visual Instructions","created":"2024-12-02","cited_by_count":8,"area":null},{"id":"2412.18688","title":"Video Is Worth a Thousand Images: Exploring the Latest Trends in Long Video Generation","created":"2024-12-24","cited_by_count":7,"area":null},{"id":"2403.09669","title":"STREAM: Spatio-TempoRal Evaluation and Analysis Metric for Video Generative Models","created":"2024-01-30","cited_by_count":6,"area":null},{"id":"2411.14762","title":"Efficient Long Video Tokenization via Coordinate-based Patch Reconstruction","created":"2024-11-22","cited_by_count":6,"area":null},{"id":"2506.08456","title":"Improving Motion in Image-to-Video Models via Adaptive Low-Pass Guidance","created":"2025-06-10","cited_by_count":6,"area":null},{"id":"2401.13363","title":"Do You Guys Want to Dance: Zero-Shot Compositional Human Dance Generation with Multiple Persons","created":"2024-01-24","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":"2312.04561","title":"GenDeF: Learning Generative Deformation Field for Video Generation","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2402.03040","title":"InteractiveVideo: User-Centric Controllable Video Generation with Synergistic Multimodal Instructions","created":"2024-02-05","cited_by_count":3,"area":null},{"id":"2405.02845","title":"Data-Efficient Molecular Generation with Hierarchical Textual Inversion","created":"2024-05-05","cited_by_count":3,"area":null},{"id":"2405.13951","title":"Text Prompting for Multi-Concept Video Customization by Autoregressive Generation","created":"2024-05-22","cited_by_count":3,"area":null},{"id":"2410.20657","title":"Video to Video Generative Adversarial Network for Few-shot Learning Based on Policy Gradient","created":"2024-10-28","cited_by_count":3,"area":null},{"id":"2507.04559","title":"MambaVideo for Discrete Video Tokenization with Channel-Split Quantization","created":"2025-07-06","cited_by_count":2,"area":null},{"id":"2507.04678","title":"ChangeBridge: Spatiotemporal Image Generation with Multimodal Controls for Remote Sensing","created":"2025-07-07","cited_by_count":2,"area":null},{"id":"2604.07402","title":"Accelerating Training of Autoregressive Video Generation Models via Local Optimization with Representation Continuity","created":"2026-04-08","cited_by_count":2,"area":null},{"id":"2402.15579","title":"CI w/o TN: Context Injection without Task Name for Procedure Planning","created":"2024-02-23","cited_by_count":1,"area":null},{"id":"2404.09000","title":"MaSkel: A Model for Human Whole-body X-rays Generation from Human Masking Images","created":"2024-04-13","cited_by_count":1,"area":null},{"id":"2509.21119","title":"MotionFlow:Learning Implicit Motion Flow for Complex Camera Trajectory Control in Video Generation","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2512.21276","title":"GriDiT: Factorized Grid-Based Diffusion for Efficient Long Image Sequence Generation","created":"2025-12-24","cited_by_count":1,"area":null},{"id":"2606.17590","title":"TivTok: Broadcasting Time-Invariant Tokens for Scalable Video Tokenization","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2310.17835","title":"One Style is All you Need to Generate a Video","created":"2023-10-27","cited_by_count":0,"area":null},{"id":"2311.14343","title":"Highly Detailed and Temporal Consistent Video Stylization via Synchronized Multi-Frame Diffusion","created":"2023-11-24","cited_by_count":0,"area":null},{"id":"2403.06356","title":"Video Generation with Consistency Tuning","created":"2024-03-11","cited_by_count":0,"area":null},{"id":"2405.07857","title":"Synergistic Integration of Coordinate Network and Tensorial Feature for Improving Neural Radiance Fields from Sparse Inputs","created":"2024-05-13","cited_by_count":0,"area":null},{"id":"2410.21462","title":"Constrained Transformer-Based Porous Media Generation to Spatial Distribution of Rock Properties","created":"2024-10-28","cited_by_count":0,"area":null},{"id":"2412.04452","title":"Factorized Video Autoencoders for Efficient Generative Modelling","created":"2024-12-05","cited_by_count":0,"area":null},{"id":"2412.12877","title":"PRIMEdit: Probability Redistribution for Instance-Aware Multi-Object Video Editing With a New Benchmark Dataset","created":"2024-12-17","cited_by_count":0,"area":null},{"id":"2603.22091","title":"P-Flow: Prompting Visual Effects Generation","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2606.23000","title":"MotionMAR: Multi-scale Auto-Regressive Human Motion Reconstruction from Sparse Observations","created":"2026-06-22","cited_by_count":0,"area":null}],"next_cursor":null}