{"total":484,"rows":[{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581,"area":"wm"},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261,"area":"wm"},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822,"area":null},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476,"area":"diffusion"},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023,"area":"diffusion"},{"id":"2212.11565","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","created":"2022-12-22","cited_by_count":961,"area":"diffusion"},{"id":"2306.13649","title":"On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes","created":"2023-06-23","cited_by_count":939,"area":"synth"},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747,"area":"wm"},{"id":"2303.13439","title":"Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators","created":"2023-03-23","cited_by_count":670,"area":"diffusion"},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640,"area":"diffusion"},{"id":"2309.17080","title":"GAIA-1: A Generative World Model for Autonomous Driving","created":"2023-09-29","cited_by_count":637,"area":"wm"},{"id":"2406.04329","title":"Simplified and Generalized Masked Diffusion for Discrete Data","created":"2024-06-06","cited_by_count":626,"area":"diffusion"},{"id":"2506.08009","title":"Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion","created":"2025-06-09","cited_by_count":625,"area":"diffusion"},{"id":"2302.03011","title":"Structure and Content-Guided Video Synthesis with Diffusion Models","created":"2023-02-06","cited_by_count":590,"area":"wm"},{"id":"2401.09047","title":"VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models","created":"2024-01-17","cited_by_count":579,"area":"diffusion"},{"id":"2310.19512","title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation","created":"2023-10-30","cited_by_count":535,"area":"diffusion"},{"id":"2302.00111","title":"Learning Universal Policies via Text-Guided Video Generation","created":"2023-01-31","cited_by_count":522,"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":"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":"2310.12190","title":"DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors","created":"2023-10-18","cited_by_count":471,"area":"diffusion"},{"id":"2303.09535","title":"FateZero: Fusing Attentions for Zero-shot Text-based Video Editing","created":"2023-03-16","cited_by_count":466,"area":"diffusion"},{"id":"2401.12945","title":"Lumiere: A Space-Time Diffusion Model for Video Generation","created":"2024-01-23","cited_by_count":455,"area":"diffusion"},{"id":"2301.11325","title":"MusicLM: Generating Music From Text","created":"2023-01-26","cited_by_count":448,"area":null},{"id":"2309.15505","title":"Finite Scalar Quantization: VQ-VAE Made Simple","created":"2023-09-27","cited_by_count":440,"area":null},{"id":"2505.06111","title":"UniVLA: Learning to Act Anywhere with Task-centric Latent Actions","created":"2025-05-09","cited_by_count":410,"area":"vla"},{"id":"2212.05199","title":"MAGVIT: Masked Generative Video Transformer","created":"2022-12-10","cited_by_count":346,"area":"wm"},{"id":"2304.08466","title":"Synthetic Data from Diffusion Models Improves ImageNet Classification","created":"2023-04-17","cited_by_count":327,"area":"diffusion"},{"id":"2305.13077","title":"ControlVideo: Training-free Controllable Text-to-Video Generation","created":"2023-05-22","cited_by_count":327,"area":"diffusion"},{"id":"2410.11758","title":"Latent Action Pretraining from Videos","created":"2024-10-15","cited_by_count":321,"area":"vla"},{"id":"2303.12688","title":"Pix2Video: Video Editing using Image Diffusion","created":"2023-03-22","cited_by_count":320,"area":"diffusion"},{"id":"2303.04761","title":"Video-P2P: Video Editing with Cross-attention Control","created":"2023-03-08","cited_by_count":314,"area":null},{"id":"2303.16203","title":"Your Diffusion Model is Secretly a Zero-Shot Classifier","created":"2023-03-28","cited_by_count":306,"area":"diffusion"},{"id":"2312.06662","title":"Photorealistic Video Generation with Diffusion Models","created":"2023-12-11","cited_by_count":306,"area":"diffusion"},{"id":"2405.12399","title":"Diffusion for World Modeling: Visual Details Matter in Atari","created":"2024-05-20","cited_by_count":300,"area":"wm"},{"id":"2305.10474","title":"Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models","created":"2023-05-17","cited_by_count":285,"area":"diffusion"},{"id":"2405.14093","title":"A Survey on Vision-Language-Action Models for Embodied AI","created":"2024-05-23","cited_by_count":279,"area":"vla"},{"id":"2509.22622","title":"LongLive: Real-time Interactive Long Video Generation","created":"2025-09-26","cited_by_count":265,"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":"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":"2403.14773","title":"StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text","created":"2024-03-21","cited_by_count":251,"area":"wm"},{"id":"2307.01850","title":"Self-Consuming Generative Models Go MAD","created":"2023-07-04","cited_by_count":250,"area":null},{"id":"2303.09556","title":"Efficient Diffusion Training via Min-SNR Weighting Strategy","created":"2023-03-16","cited_by_count":246,"area":"diffusion"},{"id":"2303.11989","title":"Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models","created":"2023-03-21","cited_by_count":245,"area":null},{"id":"2310.20700","title":"SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction","created":"2023-10-31","cited_by_count":233,"area":"diffusion"},{"id":"2306.17115","title":"Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation","created":"2023-06-29","cited_by_count":228,"area":null},{"id":"2406.03520","title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","created":"2024-06-05","cited_by_count":228,"area":null},{"id":"2310.10647","title":"A Survey on Video Diffusion Models","created":"2023-10-16","cited_by_count":206,"area":"diffusion"},{"id":"2301.11280","title":"Text-To-4D Dynamic Scene Generation","created":"2023-01-26","cited_by_count":205,"area":null},{"id":"2503.00200","title":"Unified Video Action Model","created":"2025-02-28","cited_by_count":205,"area":null},{"id":"2306.00983","title":"StyleDrop: Text-to-Image Generation in Any Style","created":"2023-06-01","cited_by_count":199,"area":null},{"id":"2402.08268","title":"World Model on Million-Length Video And Language With Blockwise RingAttention","created":"2024-02-13","cited_by_count":198,"area":"wm"},{"id":"2403.06845","title":"DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation","created":"2024-03-11","cited_by_count":191,"area":"wm"},{"id":"2404.13026","title":"PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation","created":"2024-04-19","cited_by_count":191,"area":"wm"},{"id":"2311.17984","title":"4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling","created":"2023-11-29","cited_by_count":185,"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":"2503.20523","title":"GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving","created":"2025-03-26","cited_by_count":185,"area":"wm"},{"id":"2310.15169","title":"FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling","created":"2023-10-23","cited_by_count":180,"area":"diffusion"},{"id":"2302.11550","title":"Scaling Robot Learning with Semantically Imagined Experience","created":"2023-02-22","cited_by_count":177,"area":null},{"id":"2409.18964","title":"PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation","created":"2024-09-27","cited_by_count":174,"area":null},{"id":"2303.12346","title":"NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation","created":"2023-03-22","cited_by_count":171,"area":"diffusion"},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164,"area":null},{"id":"2310.10625","title":"Video Language Planning","created":"2023-10-16","cited_by_count":162,"area":null},{"id":"2412.21059","title":"VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation","created":"2024-12-30","cited_by_count":156,"area":"alignment"},{"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":"2503.06800","title":"VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation","created":"2025-03-09","cited_by_count":149,"area":null},{"id":"2411.00816","title":"CycleResearcher: Improving Automated Research via Automated Review","created":"2024-10-28","cited_by_count":148,"area":null},{"id":"2504.12626","title":"Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models","created":"2025-04-17","cited_by_count":143,"area":"diffusion"},{"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":"2311.10982","title":"Make Pixels Dance: High-Dynamic Video Generation","created":"2023-11-18","cited_by_count":140,"area":null},{"id":"2305.18264","title":"Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising","created":"2023-05-29","cited_by_count":139,"area":"diffusion"},{"id":"2303.17599","title":"Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Models","created":"2023-03-30","cited_by_count":137,"area":"diffusion"},{"id":"2304.08477","title":"Latent-Shift: Latent Diffusion with Temporal Shift for Efficient Text-to-Video Generation","created":"2023-04-17","cited_by_count":137,"area":"diffusion"},{"id":"2405.11473","title":"FIFO-Diffusion: Generating Infinite Videos from Text without Training","created":"2024-05-19","cited_by_count":137,"area":"diffusion"},{"id":"2506.05284","title":"Video World Models with Long-term Spatial Memory","created":"2025-06-05","cited_by_count":136,"area":"wm"},{"id":"2410.10812","title":"HART: Efficient Visual Generation with Hybrid Autoregressive Transformer","created":"2024-10-14","cited_by_count":132,"area":"diffusion"},{"id":"2502.01061","title":"OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models","created":"2025-02-03","cited_by_count":129,"area":null},{"id":"2312.00777","title":"VideoBooth: Diffusion-based Video Generation with Image Prompts","created":"2023-12-01","cited_by_count":126,"area":"diffusion"},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"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":"2311.01813","title":"FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation","created":"2023-11-03","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":"2210.09263","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","created":"2022-10-17","cited_by_count":117,"area":"mllm"},{"id":"2312.17225","title":"4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency","created":"2023-12-28","cited_by_count":117,"area":"diffusion"},{"id":"2506.24113","title":"Epona: Autoregressive Diffusion World Model for Autonomous Driving","created":"2025-06-30","cited_by_count":117,"area":"wm"},{"id":"2304.10530","title":"Collaborative Diffusion for Multi-Modal Face Generation and Editing","created":"2023-04-20","cited_by_count":116,"area":"diffusion"},{"id":"2305.09636","title":"SoundStorm: Efficient Parallel Audio Generation","created":"2023-05-16","cited_by_count":114,"area":null},{"id":"2503.10589","title":"Long Context Tuning for Video Generation","created":"2025-03-13","cited_by_count":113,"area":"diffusion"},{"id":"2406.07548","title":"Image and Video Tokenization with Binary Spherical Quantization","created":"2024-06-11","cited_by_count":112,"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":"2411.02397","title":"Adaptive Caching for Faster Video Generation with Diffusion Transformers","created":"2024-11-04","cited_by_count":108,"area":"diffusion"},{"id":"2402.01566","title":"Boximator: Generating Rich and Controllable Motions for Video Synthesis","created":"2024-02-02","cited_by_count":107,"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":"2402.09470","title":"Rolling Diffusion Models","created":"2024-02-12","cited_by_count":104,"area":"diffusion"},{"id":"2409.02634","title":"Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency","created":"2024-09-04","cited_by_count":102,"area":"diffusion"},{"id":"2308.09710","title":"SimDA: Simple Diffusion Adapter for Efficient Video Generation","created":"2023-08-18","cited_by_count":101,"area":null},{"id":"2504.05298","title":"One-Minute Video Generation with Test-Time Training","created":"2025-04-07","cited_by_count":101,"area":"ssm"},{"id":"2402.03161","title":"Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization","created":"2024-02-05","cited_by_count":100,"area":"mllm"},{"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":"2312.07537","title":"FreeInit: Bridging Initialization Gap in Video Diffusion Models","created":"2023-12-12","cited_by_count":95,"area":"diffusion"}],"next_cursor":"100"}