{"total":343,"rows":[{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322,"area":null},{"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":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492,"area":null},{"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":"2312.13139","title":"Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation","created":"2023-12-20","cited_by_count":364,"area":null},{"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":"2311.10709","title":"Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning","created":"2023-11-17","cited_by_count":255,"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":"2207.12393","title":"CelebV-HQ: A Large-Scale Video Facial Attributes Dataset","created":"2022-07-25","cited_by_count":250,"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":"2203.13055","title":"Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory","created":"2022-03-24","cited_by_count":212,"area":null},{"id":"2402.02368","title":"Timer: Generative Pre-trained Transformers Are Large Time Series Models","created":"2024-02-04","cited_by_count":208,"area":null},{"id":"2503.00200","title":"Unified Video Action Model","created":"2025-02-28","cited_by_count":205,"area":null},{"id":"2406.19680","title":"MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance","created":"2024-06-28","cited_by_count":198,"area":null},{"id":"2404.10667","title":"VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time","created":"2024-04-16","cited_by_count":187,"area":null},{"id":"2202.10571","title":"Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks","created":"2022-02-21","cited_by_count":186,"area":null},{"id":"2205.09911","title":"Can Foundation Models Wrangle Your Data?","created":"2022-05-20","cited_by_count":175,"area":null},{"id":"2506.03141","title":"Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval","created":"2025-06-03","cited_by_count":163,"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":"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":"2210.05861","title":"SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models","created":"2022-10-12","cited_by_count":147,"area":null},{"id":"2311.10982","title":"Make Pixels Dance: High-Dynamic Video Generation","created":"2023-11-18","cited_by_count":140,"area":null},{"id":"2110.08791","title":"Taming Visually Guided Sound Generation","created":"2021-10-17","cited_by_count":136,"area":null},{"id":"2209.09002","title":"MoVQ: Modulating Quantized Vectors for High-Fidelity Image Generation","created":"2022-09-19","cited_by_count":125,"area":null},{"id":"2108.08827","title":"ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis","created":"2021-08-19","cited_by_count":122,"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":"2406.07548","title":"Image and Video Tokenization with Binary Spherical Quantization","created":"2024-06-11","cited_by_count":112,"area":null},{"id":"2203.13880","title":"Reinforcement Learning with Action-Free Pre-Training from Videos","created":"2022-03-25","cited_by_count":108,"area":null},{"id":"2402.14797","title":"Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis","created":"2024-02-22","cited_by_count":105,"area":null},{"id":"2308.09710","title":"SimDA: Simple Diffusion Adapter for Efficient Video Generation","created":"2023-08-18","cited_by_count":101,"area":null},{"id":"2410.02757","title":"Loong: Generating Minute-level Long Videos with Autoregressive Language Models","created":"2024-10-03","cited_by_count":99,"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":"2106.13195","title":"FitVid: Overfitting in Pixel-Level Video Prediction","created":"2021-06-24","cited_by_count":87,"area":null},{"id":"2305.08842","title":"Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks","created":"2023-05-15","cited_by_count":82,"area":null},{"id":"2305.14343","title":"Video Prediction Models as Rewards for Reinforcement Learning","created":"2023-05-23","cited_by_count":78,"area":null},{"id":"2511.01266","title":"MotionStream: Real-Time Video Generation with Interactive Motion Controls","created":"2025-11-03","cited_by_count":76,"area":null},{"id":"2209.06192","title":"StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation","created":"2022-09-13","cited_by_count":74,"area":null},{"id":"2209.14855","title":"Continuous PDE Dynamics Forecasting with Implicit Neural Representations","created":"2022-09-29","cited_by_count":73,"area":null},{"id":"2309.01157","title":"Large Language Models for Generative Recommendation: A Survey and Visionary Discussions","created":"2023-09-03","cited_by_count":73,"area":null},{"id":"2306.07303","title":"A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks","created":"2023-06-11","cited_by_count":71,"area":null},{"id":"2401.09414","title":"Vlogger: Make Your Dream A Vlog","created":"2024-01-17","cited_by_count":70,"area":null},{"id":"2201.08361","title":"Stitch it in Time: GAN-Based Facial Editing of Real Videos","created":"2022-01-20","cited_by_count":68,"area":null},{"id":"2312.03047","title":"MagicStick: Controllable Video Editing via Control Handle Transformations","created":"2023-12-05","cited_by_count":62,"area":null},{"id":"2412.15119","title":"Parallelized Autoregressive Visual Generation","created":"2024-12-19","cited_by_count":60,"area":null},{"id":"2402.09368","title":"Magic-Me: Identity-Specific Video Customized Diffusion","created":"2024-02-14","cited_by_count":59,"area":null},{"id":"2407.16124","title":"Fr\\'echet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videos","created":"2024-07-23","cited_by_count":58,"area":null},{"id":"2211.06627","title":"MARLIN: Masked Autoencoder for facial video Representation LearnINg","created":"2022-11-12","cited_by_count":57,"area":null},{"id":"2106.11250","title":"VIMPAC: Video Pre-Training via Masked Token Prediction and Contrastive Learning","created":"2021-06-21","cited_by_count":56,"area":null},{"id":"2307.15139","title":"Online Clustered Codebook","created":"2023-07-27","cited_by_count":55,"area":null},{"id":"2304.08483","title":"Text2Performer: Text-Driven Human Video Generation","created":"2023-04-17","cited_by_count":53,"area":null},{"id":"2403.08268","title":"Follow-Your-Click: Open-domain Regional Image Animation via Short Prompts","created":"2024-03-13","cited_by_count":52,"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":"2410.06424","title":"Restructuring Vector Quantization with the Rotation Trick","created":"2024-10-08","cited_by_count":51,"area":null},{"id":"2311.13608","title":"Breathing Life Into Sketches Using Text-to-Video Priors","created":"2023-11-21","cited_by_count":48,"area":null},{"id":"2402.13185","title":"UniEdit: A Unified Tuning-Free Framework for Video Motion and Appearance Editing","created":"2024-02-20","cited_by_count":48,"area":null},{"id":"2410.08368","title":"ElasticTok: Adaptive Tokenization for Image and Video","created":"2024-10-10","cited_by_count":46,"area":null},{"id":"2410.21264","title":"LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior","created":"2024-10-28","cited_by_count":46,"area":null},{"id":"2412.11673","title":"DINO-Foresight: Looking into the Future with DINO","created":"2024-12-16","cited_by_count":45,"area":null},{"id":"2511.04675","title":"InfinityStar: Unified Spacetime AutoRegressive Modeling for Visual Generation","created":"2025-11-06","cited_by_count":45,"area":null},{"id":"2210.02396","title":"Temporally Consistent Transformers for Video Generation","created":"2022-10-05","cited_by_count":44,"area":null},{"id":"2305.11421","title":"PastNet: Introducing Physical Inductive Biases for Spatio-temporal Video Prediction","created":"2023-05-19","cited_by_count":44,"area":null},{"id":"2502.07825","title":"Pre-Trained Video Generative Models as World Simulators","created":"2025-02-10","cited_by_count":44,"area":null},{"id":"2512.04519","title":"VideoSSM: Autoregressive Long Video Generation with Hybrid State-Space Memory","created":"2025-12-04","cited_by_count":42,"area":null},{"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":"2508.14033","title":"InfiniteTalk: Audio-driven Video Generation for Sparse-Frame Video Dubbing","created":"2025-08-19","cited_by_count":41,"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":"2305.18378","title":"Disentanglement via Latent Quantization","created":"2023-05-28","cited_by_count":40,"area":null},{"id":"2311.13627","title":"Vamos: Versatile Action Models for Video Understanding","created":"2023-11-22","cited_by_count":40,"area":null},{"id":"2404.19664","title":"Towards Generalist Robot Learning from Internet Video: A Survey","created":"2024-04-30","cited_by_count":40,"area":null},{"id":"2407.02797","title":"Solving Motion Planning Tasks with a Scalable Generative Model","created":"2024-07-03","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":"2210.01448","title":"Rhythmic Gesticulator: Rhythm-Aware Co-Speech Gesture Synthesis with Hierarchical Neural Embeddings","created":"2022-10-04","cited_by_count":38,"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":"2304.02777","title":"MoStGAN-V: Video Generation with Temporal Motion Styles","created":"2023-04-05","cited_by_count":37,"area":null},{"id":"2204.09273","title":"Sound-Guided Semantic Video Generation","created":"2022-04-20","cited_by_count":35,"area":null},{"id":"2407.02329","title":"MIGC++: Advanced Multi-Instance Generation Controller for Image Synthesis","created":"2024-07-02","cited_by_count":35,"area":null},{"id":"2412.13061","title":"VidTok: A Versatile and Open-Source Video Tokenizer","created":"2024-12-17","cited_by_count":35,"area":null},{"id":"2210.08465","title":"Character-Centric Story Visualization via Visual Planning and Token Alignment","created":"2022-10-16","cited_by_count":33,"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":"2407.09777","title":"Graph Transformers: A Survey","created":"2024-07-13","cited_by_count":32,"area":null},{"id":"2502.05179","title":"FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video Generation","created":"2025-02-07","cited_by_count":32,"area":null},{"id":"2212.03185","title":"Rethinking the Objectives of Vector-Quantized Tokenizers for Image Synthesis","created":"2022-12-06","cited_by_count":31,"area":null},{"id":"2503.23307","title":"MoCha: Towards Movie-Grade Talking Character Synthesis","created":"2025-03-30","cited_by_count":31,"area":null},{"id":"2401.13505","title":"Generative Human Motion Stylization in Latent Space","created":"2024-01-24","cited_by_count":30,"area":null},{"id":"2403.20193","title":"Motion Inversion for Video Customization","created":"2024-03-29","cited_by_count":30,"area":null},{"id":"2404.12388","title":"VideoGigaGAN: Towards Detail-rich Video Super-Resolution","created":"2024-04-18","cited_by_count":30,"area":null},{"id":"2412.16211","title":"Is Your World Simulator a Good Story Presenter? A Consecutive Events-Based Benchmark for Future Long Video Generation","created":"2024-12-17","cited_by_count":30,"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":"2509.14476","title":"AToken: A Unified Tokenizer for Vision","created":"2025-09-17","cited_by_count":30,"area":null},{"id":"2405.10674","title":"From Sora What We Can See: A Survey of Text-to-Video Generation","created":"2024-05-17","cited_by_count":27,"area":null},{"id":"2412.04842","title":"UniMLVG: Unified Framework for Multi-view Long Video Generation with Comprehensive Control Capabilities for Autonomous Driving","created":"2024-12-06","cited_by_count":27,"area":null},{"id":"2412.18619","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","created":"2024-12-16","cited_by_count":27,"area":null},{"id":"2603.12513","title":"MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens","created":"2026-03-12","cited_by_count":27,"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":"2303.15555","title":"Object Discovery from Motion-Guided Tokens","created":"2023-03-27","cited_by_count":25,"area":null}],"next_cursor":"100"}