{"total":658,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863,"area":"diffusion"},{"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":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305,"area":"diffusion"},{"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":"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":"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":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864,"area":"wm"},{"id":"2409.18869","title":"Emu3: Next-Token Prediction is All You Need","created":"2024-09-27","cited_by_count":781,"area":"diffusion"},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747,"area":"wm"},{"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":"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":"2401.03048","title":"Latte: Latent Diffusion Transformer for Video Generation","created":"2024-01-05","cited_by_count":546,"area":"diffusion"},{"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":"2111.15640","title":"Diffusion Autoencoders: Toward a Meaningful and Decodable Representation","created":"2021-11-30","cited_by_count":449,"area":"diffusion"},{"id":"2412.07772","title":"From Slow Bidirectional to Fast Autoregressive Video Diffusion Models","created":"2024-12-10","cited_by_count":433,"area":"diffusion"},{"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":"2410.05954","title":"Pyramidal Flow Matching for Efficient Video Generative Modeling","created":"2024-10-08","cited_by_count":366,"area":"diffusion"},{"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":"2309.15103","title":"LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models","created":"2023-09-26","cited_by_count":349,"area":"diffusion"},{"id":"2405.17398","title":"Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability","created":"2024-05-27","cited_by_count":347,"area":"wm"},{"id":"2212.05199","title":"MAGVIT: Masked Generative Video Transformer","created":"2022-12-10","cited_by_count":346,"area":"wm"},{"id":"2303.08320","title":"VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation","created":"2023-03-15","cited_by_count":331,"area":"diffusion"},{"id":"2209.00588","title":"Transformers are Sample-Efficient World Models","created":"2022-09-01","cited_by_count":328,"area":"wm"},{"id":"2311.17918","title":"Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving","created":"2023-11-29","cited_by_count":319,"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":"2312.06662","title":"Photorealistic Video Generation with Diffusion Models","created":"2023-12-11","cited_by_count":306,"area":"diffusion"},{"id":"2309.15818","title":"Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation","created":"2023-09-27","cited_by_count":302,"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":"2405.12399","title":"Diffusion for World Modeling: Visual Details Matter in Atari","created":"2024-05-20","cited_by_count":300,"area":"wm"},{"id":"2408.14837","title":"Diffusion Models Are Real-Time Game Engines","created":"2024-08-27","cited_by_count":296,"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":"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":"2203.09481","title":"Diffusion Probabilistic Modeling for Video Generation","created":"2022-03-16","cited_by_count":238,"area":"diffusion"},{"id":"2509.25161","title":"Rolling Forcing: Autoregressive Long Video Diffusion in Real Time","created":"2025-09-29","cited_by_count":234,"area":"wm"},{"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":"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":"2310.10647","title":"A Survey on Video Diffusion Models","created":"2023-10-16","cited_by_count":206,"area":"diffusion"},{"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":"2312.04433","title":"DreamVideo: Composing Your Dream Videos with Customized Subject and Motion","created":"2023-12-07","cited_by_count":188,"area":"diffusion"},{"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":"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":"2602.02214","title":"Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation","created":"2026-02-02","cited_by_count":184,"area":"diffusion"},{"id":"2205.09911","title":"Can Foundation Models Wrangle Your Data?","created":"2022-05-20","cited_by_count":175,"area":null},{"id":"2310.08465","title":"MotionDirector: Motion Customization of Text-to-Video Diffusion Models","created":"2023-10-12","cited_by_count":173,"area":"diffusion"},{"id":"2302.07685","title":"Video Probabilistic Diffusion Models in Projected Latent Space","created":"2023-02-15","cited_by_count":171,"area":"diffusion"},{"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":"2406.02509","title":"CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation","created":"2024-06-04","cited_by_count":166,"area":"diffusion"},{"id":"2411.14499","title":"Understanding World or Predicting Future? A Comprehensive Survey of World Models","created":"2024-11-21","cited_by_count":166,"area":"wm"},{"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":"2405.15223","title":"iVideoGPT: Interactive VideoGPTs are Scalable World Models","created":"2024-05-24","cited_by_count":146,"area":"wm"},{"id":"2202.09481","title":"TransDreamer: Reinforcement Learning with Transformer World Models","created":"2022-02-19","cited_by_count":143,"area":"wm"},{"id":"2311.10982","title":"Make Pixels Dance: High-Dynamic Video Generation","created":"2023-11-18","cited_by_count":140,"area":null},{"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":"2110.08791","title":"Taming Visually Guided Sound Generation","created":"2021-10-17","cited_by_count":136,"area":null},{"id":"2506.05284","title":"Video World Models with Long-term Spatial Memory","created":"2025-06-05","cited_by_count":136,"area":"wm"},{"id":"2206.07696","title":"Diffusion Models for Video Prediction and Infilling","created":"2022-06-15","cited_by_count":135,"area":"diffusion"},{"id":"2209.09002","title":"MoVQ: Modulating Quantized Vectors for High-Fidelity Image Generation","created":"2022-09-19","cited_by_count":125,"area":null},{"id":"2410.13571","title":"DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation","created":"2024-10-17","cited_by_count":123,"area":"wm"},{"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":"2405.03520","title":"Is Sora a World Simulator? A Comprehensive Survey on General World Models and Beyond","created":"2024-05-06","cited_by_count":111,"area":"wm"},{"id":"2203.13880","title":"Reinforcement Learning with Action-Free Pre-Training from Videos","created":"2022-03-25","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":"2402.14797","title":"Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis","created":"2024-02-22","cited_by_count":105,"area":null},{"id":"2402.09470","title":"Rolling Diffusion Models","created":"2024-02-12","cited_by_count":104,"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":"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":"2307.10422","title":"PreDiff: Precipitation Nowcasting with Latent Diffusion Models","created":"2023-07-19","cited_by_count":98,"area":"diffusion"},{"id":"2412.18607","title":"DrivingGPT: Unifying Driving World Modeling and Planning with Multi-modal Autoregressive Transformers","created":"2024-12-24","cited_by_count":96,"area":"wm"},{"id":"2307.06940","title":"Animate-A-Story: Storytelling with Retrieval-Augmented Video Generation","created":"2023-07-13","cited_by_count":90,"area":null},{"id":"2401.09985","title":"WorldDreamer: Towards General World Models for Video Generation via Predicting Masked Tokens","created":"2024-01-18","cited_by_count":89,"area":"wm"},{"id":"2411.19548","title":"ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration","created":"2024-11-29","cited_by_count":89,"area":"wm"},{"id":"2503.07314","title":"Automated Movie Generation via Multi-Agent CoT Planning","created":"2025-03-10","cited_by_count":89,"area":"agents"},{"id":"2411.17697","title":"StableAnimator: High-Quality Identity-Preserving Human Image Animation","created":"2024-11-26","cited_by_count":88,"area":"diffusion"},{"id":"2106.13195","title":"FitVid: Overfitting in Pixel-Level Video Prediction","created":"2021-06-24","cited_by_count":87,"area":null},{"id":"2312.12490","title":"InstructVideo: Instructing Video Diffusion Models with Human Feedback","created":"2023-12-19","cited_by_count":86,"area":"diffusion"},{"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":"2601.03782","title":"PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation","created":"2026-01-07","cited_by_count":82,"area":"wm"},{"id":"2212.00235","title":"VIDM: Video Implicit Diffusion Models","created":"2022-12-01","cited_by_count":78,"area":"diffusion"},{"id":"2305.14343","title":"Video Prediction Models as Rewards for Reinforcement Learning","created":"2023-05-23","cited_by_count":78,"area":null}],"next_cursor":"100"}