{"list":"other","total":64,"rows":[{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"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},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"2303.13439","title":"Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators","created":"2023-03-23","cited_by_count":670},{"id":"2308.06571","title":"ModelScope Text-to-Video Technical Report","created":"2023-08-12","cited_by_count":658},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518},{"id":"2210.02399","title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","created":"2022-10-05","cited_by_count":484},{"id":"2211.11018","title":"MagicVideo: Efficient Video Generation With Latent Diffusion Models","created":"2022-11-20","cited_by_count":465},{"id":"2401.12945","title":"Lumiere: A Space-Time Diffusion Model for Video Generation","created":"2024-01-23","cited_by_count":455},{"id":"2402.19479","title":"Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers","created":"2024-02-29","cited_by_count":393},{"id":"2212.02500","title":"PhysDiff: Physics-Guided Human Motion Diffusion Model","created":"2022-12-05","cited_by_count":368},{"id":"2410.05954","title":"Pyramidal Flow Matching for Efficient Video Generative Modeling","created":"2024-10-08","cited_by_count":366},{"id":"2309.15103","title":"LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models","created":"2023-09-26","cited_by_count":349},{"id":"2405.17398","title":"Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability","created":"2024-05-27","cited_by_count":347},{"id":"2407.02371","title":"OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation","created":"2024-07-02","cited_by_count":341},{"id":"2104.14806","title":"GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions","created":"2021-04-30","cited_by_count":256},{"id":"2111.12417","title":"N\\\"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion","created":"2021-11-24","cited_by_count":253},{"id":"2406.03520","title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","created":"2024-06-05","cited_by_count":228},{"id":"2411.02385","title":"How Far is Video Generation from World Model: A Physical Law Perspective","created":"2024-11-04","cited_by_count":212},{"id":"2307.09702","title":"Efficient Guided Generation for Large Language Models","created":"2023-07-19","cited_by_count":200},{"id":"2409.18964","title":"PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation","created":"2024-09-27","cited_by_count":174},{"id":"1710.00421","title":"Video Generation From Text","created":"2017-10-01","cited_by_count":154},{"id":"2503.06800","title":"VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation","created":"2025-03-09","cited_by_count":149},{"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},{"id":"2501.08325","title":"GameFactory: Creating New Games with Generative Interactive Videos","created":"2025-01-14","cited_by_count":130},{"id":"2402.14797","title":"Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis","created":"2024-02-22","cited_by_count":105},{"id":"2505.23656","title":"VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models","created":"2025-05-29","cited_by_count":98},{"id":"2503.08153","title":"WISA: World Simulator Assistant for Physics-Aware Text-to-Video Generation","created":"2025-03-11","cited_by_count":90},{"id":"2412.00596","title":"PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation","created":"2024-11-30","cited_by_count":80},{"id":"2505.14357","title":"Vid2World: Crafting Video Diffusion Models to Interactive World Models","created":"2025-05-20","cited_by_count":76},{"id":"2412.18597","title":"DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation","created":"2024-12-24","cited_by_count":74},{"id":"2502.04896","title":"Goku: Flow Based Video Generative Foundation Models","created":"2025-02-07","cited_by_count":67},{"id":"2505.19386","title":"Force Prompting: Video Generation Models Can Learn and Generalize Physics-based Control Signals","created":"2025-05-26","cited_by_count":53},{"id":"2503.23368","title":"VLIPP: Towards Physically Plausible Video Generation with Vision and Language Informed Physical Prior","created":"2025-03-30","cited_by_count":52},{"id":"2404.05014","title":"MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators","created":"2024-04-07","cited_by_count":51},{"id":"2406.04277","title":"VideoTetris: Towards Compositional Text-to-Video Generation","created":"2024-06-06","cited_by_count":51},{"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},{"id":"2502.07825","title":"Pre-Trained Video Generative Models as World Simulators","created":"2025-02-10","cited_by_count":44},{"id":"2506.01380","title":"Playing with Transformer at 30+ FPS via Next-Frame Diffusion","created":"2025-06-02","cited_by_count":20},{"id":"2009.02018","title":"TiVGAN: Text to Image to Video Generation with Step-by-Step Evolutionary Generator","created":"2020-09-04","cited_by_count":19},{"id":"2408.08189","title":"FancyVideo: Towards Dynamic and Consistent Video Generation via Cross-frame Textual Guidance","created":"2024-08-15","cited_by_count":15},{"id":"2403.02332","title":"UniCtrl: Improving the Spatiotemporal Consistency of Text-to-Video Diffusion Models via Training-Free Unified Attention Control","created":"2024-03-04","cited_by_count":14},{"id":"2509.24702","title":"Enhancing Physical Plausibility in Video Generation by Reasoning the Implausibility","created":"2025-09-29","cited_by_count":13},{"id":"2412.01316","title":"Long Video Diffusion Generation with Segmented Cross-Attention and Content-Rich Video Data Curation","created":"2024-12-02","cited_by_count":12},{"id":"2502.00500","title":"Video Latent Flow Matching: Optimal Polynomial Projections for Video Interpolation and Extrapolation","created":"2025-02-01","cited_by_count":11},{"id":"2502.07508","title":"Enhance-A-Video: Better Generated Video for Free","created":"2025-02-11","cited_by_count":11},{"id":"2506.07177","title":"Frame Guidance: Training-Free Guidance for Frame-Level Control in Video Diffusion Models","created":"2025-06-08","cited_by_count":11},{"id":"2401.10404","title":"Inflation with Diffusion: Efficient Temporal Adaptation for Text-to-Video Super-Resolution","created":"2024-01-18","cited_by_count":9},{"id":"2408.12590","title":"xGen-VideoSyn-1: High-fidelity Text-to-Video Synthesis with Compressed Representations","created":"2024-08-22","cited_by_count":6},{"id":"2505.20827","title":"Frame-Level Captions for Long Video Generation with Complex Multi Scenes","created":"2025-05-27","cited_by_count":1}],"next_cursor":null}