{"total":106,"rows":[{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985,"area":null},{"id":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658,"area":"wm"},{"id":"2401.03048","title":"Latte: Latent Diffusion Transformer for Video Generation","created":"2024-01-05","cited_by_count":546,"area":"diffusion"},{"id":"2210.02399","title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","created":"2022-10-05","cited_by_count":484,"area":null},{"id":"2211.13221","title":"Latent Video Diffusion Models for High-Fidelity Long Video Generation","created":"2022-11-23","cited_by_count":388,"area":"diffusion"},{"id":"2207.01696","title":"TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts","created":"2022-07-04","cited_by_count":359,"area":null},{"id":"2212.05199","title":"MAGVIT: Masked Generative Video Transformer","created":"2022-12-10","cited_by_count":346,"area":"wm"},{"id":"2205.09853","title":"MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation","created":"2022-05-19","cited_by_count":309,"area":"diffusion"},{"id":"2112.14683","title":"StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN2","created":"2021-12-29","cited_by_count":301,"area":null},{"id":"2104.14806","title":"GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions","created":"2021-04-30","cited_by_count":256,"area":null},{"id":"2111.12417","title":"N\\\"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion","created":"2021-11-24","cited_by_count":253,"area":null},{"id":"2204.03638","title":"Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer","created":"2022-04-07","cited_by_count":244,"area":null},{"id":"2203.09481","title":"Diffusion Probabilistic Modeling for Video Generation","created":"2022-03-16","cited_by_count":238,"area":"diffusion"},{"id":"2202.10571","title":"Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks","created":"2022-02-21","cited_by_count":186,"area":null},{"id":"2206.05099","title":"SimVP: Simpler yet Better Video Prediction","created":"2022-06-09","cited_by_count":184,"area":null},{"id":"2302.07685","title":"Video Probabilistic Diffusion Models in Projected Latent Space","created":"2023-02-15","cited_by_count":171,"area":"diffusion"},{"id":"2205.04421","title":"NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality","created":"2022-05-09","cited_by_count":152,"area":null},{"id":"2207.05833","title":"Earthformer: Exploring Space-Time Transformers for Earth System Forecasting","created":"2022-07-12","cited_by_count":152,"area":null},{"id":"2408.12588","title":"Real-Time Video Generation with Pyramid Attention Broadcast","created":"2024-08-22","cited_by_count":149,"area":null},{"id":"2110.08791","title":"Taming Visually Guided Sound Generation","created":"2021-10-17","cited_by_count":136,"area":null},{"id":"2206.07696","title":"Diffusion Models for Video Prediction and Infilling","created":"2022-06-15","cited_by_count":135,"area":"diffusion"},{"id":"2411.00769","title":"GameGen-X: Interactive Open-world Game Video Generation","created":"2024-11-01","cited_by_count":128,"area":"wm"},{"id":"2209.09002","title":"MoVQ: Modulating Quantized Vectors for High-Fidelity Image Generation","created":"2022-09-19","cited_by_count":125,"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":"2206.11894","title":"MaskViT: Masked Visual Pre-Training for Video Prediction","created":"2022-06-23","cited_by_count":114,"area":null},{"id":"2206.03429","title":"Generating Long Videos of Dynamic Scenes","created":"2022-06-07","cited_by_count":113,"area":null},{"id":"2307.10422","title":"PreDiff: Precipitation Nowcasting with Latent Diffusion Models","created":"2023-07-19","cited_by_count":98,"area":"diffusion"},{"id":"2106.13195","title":"FitVid: Overfitting in Pixel-Level Video Prediction","created":"2021-06-24","cited_by_count":87,"area":null},{"id":"2311.18834","title":"ART$\\boldsymbol{\\cdot}$V: Auto-Regressive Text-to-Video Generation with Diffusion Models","created":"2023-11-30","cited_by_count":76,"area":"diffusion"},{"id":"2303.10462","title":"Machine learning with data assimilation and uncertainty quantification for dynamical systems: a review","created":"2023-03-18","cited_by_count":75,"area":null},{"id":"2107.08037","title":"CCVS: Context-aware Controllable Video Synthesis","created":"2021-07-16","cited_by_count":69,"area":null},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2211.14575","title":"Efficient Video Prediction via Sparsely Conditioned Flow Matching","created":"2022-11-26","cited_by_count":55,"area":"diffusion"},{"id":"2307.15139","title":"Online Clustered Codebook","created":"2023-07-27","cited_by_count":55,"area":null},{"id":"2105.04551","title":"Stochastic Image-to-Video Synthesis using cINNs","created":"2021-05-10","cited_by_count":49,"area":null},{"id":"2210.02396","title":"Temporally Consistent Transformers for Video Generation","created":"2022-10-05","cited_by_count":44,"area":null},{"id":"2403.14148","title":"Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition","created":"2024-03-21","cited_by_count":42,"area":"diffusion"},{"id":"2211.14842","title":"Unified Discrete Diffusion for Simultaneous Vision-Language Generation","created":"2022-11-27","cited_by_count":39,"area":"diffusion"},{"id":"2411.05902","title":"Autoregressive Models in Vision: A Survey","created":"2024-11-08","cited_by_count":39,"area":null},{"id":"2203.02573","title":"Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning","created":"2022-03-04","cited_by_count":37,"area":null},{"id":"2203.09494","title":"Transframer: Arbitrary Frame Prediction with Generative Models","created":"2022-03-17","cited_by_count":37,"area":null},{"id":"2211.12824","title":"Tell Me What Happened: Unifying Text-guided Video Completion via Multimodal Masked Video Generation","created":"2022-11-23","cited_by_count":32,"area":null},{"id":"2507.02092","title":"Energy-Based Transformers are Scalable Learners and Thinkers","created":"2025-07-02","cited_by_count":31,"area":"lr"},{"id":"2303.09998","title":"TBP-Former: Learning Temporal Bird's-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Driving","created":"2023-03-17","cited_by_count":30,"area":null},{"id":"2207.09840","title":"EleGANt: Exquisite and Locally Editable GAN for Makeup Transfer","created":"2022-07-20","cited_by_count":28,"area":null},{"id":"2502.07737","title":"Next Block Prediction: Video Generation via Semi-Autoregressive Modeling","created":"2025-02-11","cited_by_count":26,"area":null},{"id":"2107.09240","title":"Generative Video Transformer: Can Objects be the Words?","created":"2021-07-20","cited_by_count":24,"area":null},{"id":"2405.03025","title":"Matten: Video Generation with Mamba-Attention","created":"2024-05-05","cited_by_count":24,"area":"diffusion"},{"id":"2202.07816","title":"ProsoSpeech: Enhancing Prosody With Quantized Vector Pre-training in Text-to-Speech","created":"2022-02-16","cited_by_count":22,"area":null},{"id":"2209.07143","title":"HARP: Autoregressive Latent Video Prediction with High-Fidelity Image Generator","created":"2022-09-15","cited_by_count":22,"area":null},{"id":"2211.12509","title":"SimVPv2: Towards Simple yet Powerful Spatiotemporal Predictive Learning","created":"2022-11-22","cited_by_count":22,"area":null},{"id":"2304.11603","title":"LaMD: Latent Motion Diffusion for Image-Conditional Video Generation","created":"2023-04-23","cited_by_count":22,"area":"diffusion"},{"id":"2404.15955","title":"Beyond Deepfake Images: Detecting AI-Generated Videos","created":"2024-04-24","cited_by_count":22,"area":null},{"id":"2205.07211","title":"GenerSpeech: Towards Style Transfer for Generalizable Out-Of-Domain Text-to-Speech","created":"2022-05-15","cited_by_count":21,"area":null},{"id":"2302.11850","title":"Object-Centric Video Prediction via Decoupling of Object Dynamics and Interactions","created":"2023-02-23","cited_by_count":19,"area":null},{"id":"2308.16154","title":"MMVP: Motion-Matrix-based Video Prediction","created":"2023-08-30","cited_by_count":18,"area":null},{"id":"2206.14797","title":"3D-Aware Video Generation","created":"2022-06-29","cited_by_count":17,"area":null},{"id":"2212.04655","title":"MIMO Is All You Need : A Strong Multi-In-Multi-Out Baseline for Video Prediction","created":"2022-12-09","cited_by_count":17,"area":null},{"id":"2303.16541","title":"Sounding Video Generator: A Unified Framework for Text-guided Sounding Video Generation","created":"2023-03-29","cited_by_count":15,"area":null},{"id":"2306.02562","title":"Video Diffusion Models with Local-Global Context Guidance","created":"2023-06-05","cited_by_count":15,"area":"diffusion"},{"id":"2603.04553","title":"Latent Particle World Models: Self-supervised Object-centric Stochastic Dynamics Modeling","created":"2026-03-04","cited_by_count":15,"area":"wm"},{"id":"2305.17783","title":"Visual Affordance Prediction for Guiding Robot Exploration","created":"2023-05-28","cited_by_count":14,"area":null},{"id":"2502.12632","title":"MALT Diffusion: Memory-Augmented Latent Transformers for Any-Length Video Generation","created":"2025-02-18","cited_by_count":14,"area":"diffusion"},{"id":"2504.16081","title":"Survey of Video Diffusion Models: Foundations, Implementations, and Applications","created":"2025-04-22","cited_by_count":14,"area":"diffusion"},{"id":"2312.12917","title":"Sign Language Production with Latent Motion Transformer","created":"2023-12-20","cited_by_count":13,"area":null},{"id":"2404.13573","title":"Exploring AIGC Video Quality: A Focus on Visual Harmony, Video-Text Consistency and Domain Distribution Gap","created":"2024-04-21","cited_by_count":13,"area":null},{"id":"2212.07413","title":"Towards Smooth Video Composition","created":"2022-12-14","cited_by_count":12,"area":null},{"id":"2303.03684","title":"MOSO: Decomposing MOtion, Scene and Object for Video Prediction","created":"2023-03-07","cited_by_count":12,"area":null},{"id":"2601.21282","title":"WorldBench: Benchmarking Physical Understanding of World Models by Isolating Physics Concepts","created":"2026-01-29","cited_by_count":12,"area":"wm"},{"id":"2603.20169","title":"EgoForge: Goal-Directed Egocentric World Simulator","created":"2026-03-20","cited_by_count":12,"area":"wm"},{"id":"2312.02819","title":"Deterministic Guidance Diffusion Model for Probabilistic Weather Forecasting","created":"2023-12-05","cited_by_count":9,"area":null},{"id":"2602.00869","title":"Improving Flow Matching by Aligning Flow Divergence","created":"2026-01-31","cited_by_count":9,"area":"diffusion"},{"id":"2211.06119","title":"SSGVS: Semantic Scene Graph-to-Video Synthesis","created":"2022-11-11","cited_by_count":8,"area":null},{"id":"2301.08846","title":"Regeneration Learning: A Learning Paradigm for Data Generation","created":"2023-01-21","cited_by_count":8,"area":null},{"id":"2501.08303","title":"Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers","created":"2025-01-14","cited_by_count":8,"area":null},{"id":"2111.12747","title":"Layered Controllable Video Generation","created":"2021-11-24","cited_by_count":7,"area":null},{"id":"2303.11251","title":"Towards End-to-End Generative Modeling of Long Videos with Memory-Efficient Bidirectional Transformers","created":"2023-03-20","cited_by_count":7,"area":null},{"id":"2306.03988","title":"Learn the Force We Can: Enabling Sparse Motion Control in Multi-Object Video Generation","created":"2023-06-06","cited_by_count":7,"area":null},{"id":"2401.14718","title":"A Survey on Future Frame Synthesis: Bridging Deterministic and Generative Approaches","created":"2024-01-26","cited_by_count":7,"area":"wm"},{"id":"2407.21126","title":"Self-supervised Multi-future Occupancy Forecasting for Autonomous Driving","created":"2024-07-30","cited_by_count":7,"area":"wm"},{"id":"2604.06339","title":"Evolution of Video Generative Foundations","created":"2026-04-07","cited_by_count":7,"area":"wm"},{"id":"2103.07292","title":"VDSM: Unsupervised Video Disentanglement with State-Space Modeling and Deep Mixtures of Experts","created":"2021-03-12","cited_by_count":6,"area":"moe"},{"id":"2209.00185","title":"SketchBetween: Video-to-Video Synthesis for Sprite Animation via Sketches","created":"2022-09-01","cited_by_count":6,"area":null},{"id":"2212.14376","title":"Long-horizon video prediction using a dynamic latent hierarchy","created":"2022-12-29","cited_by_count":4,"area":null},{"id":"2606.09156","title":"OmniGen-AR: AutoRegressive Any-to-Image Generation","created":"2026-06-08","cited_by_count":4,"area":null},{"id":"2205.15894","title":"VQ-AR: Vector Quantized Autoregressive Probabilistic Time Series Forecasting","created":"2022-05-31","cited_by_count":3,"area":null},{"id":"2206.04003","title":"Patch-based Object-centric Transformers for Efficient Video Generation","created":"2022-06-08","cited_by_count":3,"area":null},{"id":"2206.07435","title":"Forecasting of depth and ego-motion with transformers and self-supervision","created":"2022-06-15","cited_by_count":3,"area":null},{"id":"2402.06088","title":"Animated Stickers: Bringing Stickers to Life with Video Diffusion","created":"2024-02-08","cited_by_count":3,"area":"diffusion"},{"id":"2105.00602","title":"OCTOPUS: Overcoming Performance andPrivatization Bottlenecks in Distributed Learning","created":"2021-05-03","cited_by_count":2,"area":null},{"id":"2401.00869","title":"FlashVideo: A Framework for Swift Inference in Text-to-Video Generation","created":"2023-12-30","cited_by_count":2,"area":"diffusion"},{"id":"2401.09084","title":"UniVG: Towards UNIfied-modal Video Generation","created":"2024-01-17","cited_by_count":2,"area":"diffusion"},{"id":"2405.17450","title":"The Power of Next-Frame Prediction for Learning Physical Laws","created":"2024-05-21","cited_by_count":2,"area":null},{"id":"2411.07619","title":"Artificial Intelligence for Biomedical Video Generation","created":"2024-11-12","cited_by_count":2,"area":null},{"id":"2306.10346","title":"Fast Fourier Inception Networks for Occluded Video Prediction","created":"2023-06-17","cited_by_count":1,"area":null},{"id":"2402.18044","title":"SFTformer: A Spatial-Frequency-Temporal Correlation-Decoupling Transformer for Radar Echo Extrapolation","created":"2024-02-28","cited_by_count":1,"area":null},{"id":"2412.04929","title":"Continuous Video Process: Modeling Videos as Continuous Multi-Dimensional Processes for Video Prediction","created":"2024-12-06","cited_by_count":1,"area":"diffusion"},{"id":"2412.05633","title":"Efficient Continuous Video Flow Model for Video Prediction","created":"2024-12-07","cited_by_count":1,"area":"diffusion"},{"id":"2502.11655","title":"TextOCVP: Object-Centric Video Prediction with Language Guidance","created":"2025-02-17","cited_by_count":1,"area":null},{"id":"2510.19527","title":"PoseCrafter: Extreme Pose Estimation with Hybrid Video Synthesis","created":"2025-10-22","cited_by_count":1,"area":null}],"next_cursor":"100"}