{"total":156,"rows":[{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822,"area":null},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742,"area":null},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044,"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":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745,"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":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464,"area":null},{"id":"2301.11325","title":"MusicLM: Generating Music From Text","created":"2023-01-26","cited_by_count":448,"area":null},{"id":"2304.01186","title":"Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos","created":"2023-04-03","cited_by_count":314,"area":null},{"id":"2204.14217","title":"CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers","created":"2022-04-28","cited_by_count":307,"area":null},{"id":"2308.08089","title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","created":"2023-08-16","cited_by_count":264,"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":"2305.11846","title":"Any-to-Any Generation via Composable Diffusion","created":"2023-05-19","cited_by_count":204,"area":null},{"id":"2407.14505","title":"T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation","created":"2024-07-19","cited_by_count":185,"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":"2302.10035","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","created":"2023-02-20","cited_by_count":153,"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":"2309.15091","title":"VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning","created":"2023-09-26","cited_by_count":141,"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":"2311.17009","title":"Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfer","created":"2023-11-28","cited_by_count":124,"area":null},{"id":"2205.06803","title":"VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder","created":"2022-05-13","cited_by_count":116,"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":"2308.07926","title":"CoDeF: Content Deformation Fields for Temporally Consistent Video Processing","created":"2023-08-15","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":"2303.14717","title":"CelebV-Text: A Large-Scale Facial Text-Video Dataset","created":"2023-03-26","cited_by_count":104,"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":"2507.16869","title":"Controllable Video Generation: A Survey","created":"2025-07-22","cited_by_count":98,"area":null},{"id":"2205.10337","title":"UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes","created":"2022-05-20","cited_by_count":78,"area":null},{"id":"2210.00990","title":"Visual Prompt Tuning for Generative Transfer Learning","created":"2022-10-03","cited_by_count":75,"area":null},{"id":"2207.09814","title":"NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis","created":"2022-07-20","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":"2309.16429","title":"Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation","created":"2023-09-28","cited_by_count":69,"area":null},{"id":"2311.12886","title":"AnimateAnything: Fine-Grained Open Domain Image Animation with Motion Guidance","created":"2023-11-21","cited_by_count":66,"area":null},{"id":"2403.13430","title":"MTP: Advancing Remote Sensing Foundation Model via Multi-Task Pretraining","created":"2024-03-20","cited_by_count":66,"area":null},{"id":"2202.07765","title":"General-purpose, long-context autoregressive modeling with Perceiver AR","created":"2022-02-15","cited_by_count":60,"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":"2307.15139","title":"Online Clustered Codebook","created":"2023-07-27","cited_by_count":55,"area":null},{"id":"2112.13592","title":"Multimodal Image Synthesis and Editing: The Generative AI Era","created":"2021-12-27","cited_by_count":52,"area":null},{"id":"2305.14330","title":"DirecT2V: Large Language Models are Frame-Level Directors for Zero-Shot Text-to-Video Generation","created":"2023-05-23","cited_by_count":49,"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":"2307.16184","title":"UnIVAL: Unified Model for Image, Video, Audio and Language Tasks","created":"2023-07-30","cited_by_count":45,"area":null},{"id":"2305.12328","title":"InstructVid2Vid: Controllable Video Editing with Natural Language Instructions","created":"2023-05-21","cited_by_count":44,"area":null},{"id":"2211.11742","title":"SceneComposer: Any-Level Semantic Image Synthesis","created":"2022-11-21","cited_by_count":43,"area":null},{"id":"2410.18912","title":"Dynamic 3D Gaussian Tracking for Graph-Based Neural Dynamics Modeling","created":"2024-10-24","cited_by_count":43,"area":null},{"id":"2306.07257","title":"MovieFactory: Automatic Movie Creation from Text using Large Generative Models for Language and Images","created":"2023-06-12","cited_by_count":42,"area":null},{"id":"2112.15283","title":"ERNIE-ViLG: Unified Generative Pre-training for Bidirectional Vision-Language Generation","created":"2021-12-31","cited_by_count":41,"area":null},{"id":"2411.05902","title":"Autoregressive Models in Vision: A Survey","created":"2024-11-08","cited_by_count":39,"area":null},{"id":"2203.09494","title":"Transframer: Arbitrary Frame Prediction with Generative Models","created":"2022-03-17","cited_by_count":37,"area":null},{"id":"2512.15603","title":"Qwen-Image-Layered: Towards Inherent Editability via Layer Decomposition","created":"2025-12-17","cited_by_count":34,"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":"2403.20193","title":"Motion Inversion for Video Customization","created":"2024-03-29","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":"2308.11606","title":"StoryBench: A Multifaceted Benchmark for Continuous Story Visualization","created":"2023-08-22","cited_by_count":29,"area":null},{"id":"2403.09439","title":"3D-SceneDreamer: Text-Driven 3D-Consistent Scene Generation","created":"2024-03-14","cited_by_count":29,"area":null},{"id":"2503.16430","title":"Bridging Continuous and Discrete Tokens for Autoregressive Visual Generation","created":"2025-03-20","cited_by_count":29,"area":null},{"id":"2203.01922","title":"Vision-Language Intelligence: Tasks, Representation Learning, and Large Models","created":"2022-03-03","cited_by_count":28,"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":"2302.05496","title":"MaskSketch: Unpaired Structure-guided Masked Image Generation","created":"2023-02-10","cited_by_count":27,"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":"2401.17093","title":"StrokeNUWA: Tokenizing Strokes for Vector Graphic Synthesis","created":"2024-01-30","cited_by_count":26,"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":"2308.14177","title":"AI-Generated Content (AIGC) for Various Data Modalities: A Survey","created":"2023-08-27","cited_by_count":25,"area":null},{"id":"2310.19961","title":"ExPT: Synthetic Pretraining for Few-Shot Experimental Design","created":"2023-10-30","cited_by_count":22,"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":"2411.17765","title":"I2VControl: Disentangled and Unified Video Motion Synthesis Control","created":"2024-11-26","cited_by_count":20,"area":null},{"id":"2202.05009","title":"N\\\"UWA-LIP: Language Guided Image Inpainting with Defect-free VQGAN","created":"2022-02-10","cited_by_count":19,"area":null},{"id":"2301.01413","title":"Attribute-Centric Compositional Text-to-Image Generation","created":"2023-01-04","cited_by_count":19,"area":null},{"id":"2304.08551","title":"Generative Disco: Text-to-Video Generation for Music Visualization","created":"2023-04-17","cited_by_count":19,"area":null},{"id":"2303.10126","title":"IRGen: Generative Modeling for Image Retrieval","created":"2023-03-17","cited_by_count":18,"area":null},{"id":"2303.15616","title":"Fine-grained Audible Video Description","created":"2023-03-27","cited_by_count":18,"area":null},{"id":"2309.14623","title":"Text-to-Image Generation for Abstract Concepts","created":"2023-09-26","cited_by_count":18,"area":null},{"id":"2312.02919","title":"Fine-grained Controllable Video Generation via Object Appearance and Context","created":"2023-12-05","cited_by_count":18,"area":null},{"id":"2203.15836","title":"VPTR: Efficient Transformers for Video Prediction","created":"2022-03-29","cited_by_count":17,"area":null},{"id":"2212.04408","title":"OFASys: A Multi-Modal Multi-Task Learning System for Building Generalist Models","created":"2022-12-08","cited_by_count":17,"area":null},{"id":"2311.06329","title":"A Survey of AI Text-to-Image and AI Text-to-Video Generators","created":"2023-11-10","cited_by_count":17,"area":null},{"id":"2404.12347","title":"AniClipart: Clipart Animation with Text-to-Video Priors","created":"2024-04-18","cited_by_count":17,"area":null},{"id":"2406.00025","title":"SCALM: Towards Semantic Caching for Automated Chat Services with Large Language Models","created":"2024-05-24","cited_by_count":16,"area":null},{"id":"2504.07940","title":"Beyond the Frame: Generating 360 Panoramic Videos from Perspective Videos","created":"2025-04-10","cited_by_count":16,"area":null},{"id":"2505.17011","title":"Learning Adaptive and Temporally Causal Video Tokenization in a 1D Latent Space","created":"2025-05-22","cited_by_count":16,"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":"2311.05698","title":"Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities","created":"2023-11-09","cited_by_count":15,"area":null},{"id":"2312.02503","title":"SAVE: Protagonist Diversification with Structure Agnostic Video Editing","created":"2023-12-05","cited_by_count":15,"area":null},{"id":"2401.00430","title":"Brain-Conditional Multimodal Synthesis: A Survey and Taxonomy","created":"2023-12-31","cited_by_count":15,"area":null},{"id":"2503.20782","title":"Zero-Shot Audio-Visual Editing via Cross-Modal Delta Denoising","created":"2025-03-26","cited_by_count":14,"area":null},{"id":"2407.21408","title":"Benchmarking Multi-dimensional AIGC Video Quality Assessment: A Dataset and Unified Model","created":"2024-07-31","cited_by_count":13,"area":null},{"id":"2203.04907","title":"KPE: Keypoint Pose Encoding for Transformer-based Image Generation","created":"2022-03-09","cited_by_count":12,"area":null},{"id":"2212.06026","title":"Video Prediction by Efficient Transformers","created":"2022-12-12","cited_by_count":12,"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":"2409.13037","title":"DNI: Dilutional Noise Initialization for Diffusion Video Editing","created":"2024-09-19","cited_by_count":12,"area":null},{"id":"2512.05115","title":"Light-X: Generative 4D Video Rendering with Camera and Illumination Control","created":"2025-12-04","cited_by_count":12,"area":null},{"id":"2503.06956","title":"LatexBlend: Scaling Multi-concept Customized Generation with Latent Textual Blending","created":"2025-03-10","cited_by_count":10,"area":null},{"id":"2505.00209","title":"Direct Motion Models for Assessing Generated Videos","created":"2025-04-30","cited_by_count":10,"area":null},{"id":"2309.04302","title":"Have We Ever Encountered This Before? Retrieving Out-of-Distribution Road Obstacles from Driving Scenes","created":"2023-09-08","cited_by_count":9,"area":null},{"id":"2310.19626","title":"Transformation vs Tradition: Artificial General Intelligence (AGI) for Arts and Humanities","created":"2023-10-30","cited_by_count":9,"area":null},{"id":"2411.11361","title":"Scalable Autoregressive Monocular Depth Estimation","created":"2024-11-18","cited_by_count":9,"area":null},{"id":"2411.16619","title":"Human-Activity AGV Quality Assessment: A Benchmark Dataset and an Objective Evaluation Metric","created":"2024-11-25","cited_by_count":9,"area":null},{"id":"2211.06119","title":"SSGVS: Semantic Scene Graph-to-Video Synthesis","created":"2022-11-11","cited_by_count":8,"area":null}],"next_cursor":"100"}