{"list":"other","total":54,"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":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"2302.00111","title":"Learning Universal Policies via Text-Guided Video Generation","created":"2023-01-31","cited_by_count":522},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"1806.07011","title":"VirtualHome: Simulating Household Activities via Programs","created":"2018-06-19","cited_by_count":415},{"id":"2212.05199","title":"MAGVIT: Masked Generative Video Transformer","created":"2022-12-10","cited_by_count":346},{"id":"2312.06662","title":"Photorealistic Video Generation with Diffusion Models","created":"2023-12-11","cited_by_count":306},{"id":"2307.06304","title":"Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution","created":"2023-07-12","cited_by_count":229},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229},{"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":"2306.00983","title":"StyleDrop: Text-to-Image Generation in Any Style","created":"2023-06-01","cited_by_count":199},{"id":"2412.02700","title":"Motion Prompting: Controlling Video Generation with Motion Trajectories","created":"2024-12-03","cited_by_count":178},{"id":"2409.18964","title":"PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation","created":"2024-09-27","cited_by_count":174},{"id":"2410.05363","title":"Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation","created":"2024-10-07","cited_by_count":174},{"id":"2402.03162","title":"Direct-a-Video: Customized Video Generation with User-Directed Camera Movement and Object Motion","created":"2024-02-05","cited_by_count":167},{"id":"2106.08261","title":"Physion: Evaluating Physical Prediction from Vision in Humans and Machines","created":"2021-06-15","cited_by_count":153},{"id":"2112.10762","title":"StyleSwin: Transformer-based GAN for High-resolution Image Generation","created":"2021-12-20","cited_by_count":152},{"id":"2302.10893","title":"Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness","created":"2023-02-07","cited_by_count":151},{"id":"1812.02784","title":"StoryGAN: A Sequential Conditional GAN for Story Visualization","created":"2018-12-06","cited_by_count":138},{"id":"2206.03429","title":"Generating Long Videos of Dynamic Scenes","created":"2022-06-07","cited_by_count":113},{"id":"2502.02492","title":"VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models","created":"2025-02-04","cited_by_count":113},{"id":"2412.07760","title":"SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints","created":"2024-12-10","cited_by_count":93},{"id":"2401.09985","title":"WorldDreamer: Towards General World Models for Video Generation via Predicting Masked Tokens","created":"2024-01-18","cited_by_count":89},{"id":"2402.17139","title":"Video as the New Language for Real-World Decision Making","created":"2024-02-27","cited_by_count":87},{"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":"1903.01434","title":"VideoFlow: A Conditional Flow-Based Model for Stochastic Video Generation","created":"2019-03-04","cited_by_count":74},{"id":"2502.11831","title":"Intuitive physics understanding emerges from self-supervised pretraining on natural videos","created":"2025-02-17","cited_by_count":70},{"id":"2311.12631","title":"GPT4Motion: Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planning","created":"2023-11-21","cited_by_count":61},{"id":"2410.10815","title":"Depth Any Video with Scalable Synthetic Data","created":"2024-10-14","cited_by_count":57},{"id":"2312.07360","title":"Boosting Latent Diffusion with Flow Matching","created":"2023-12-12","cited_by_count":44},{"id":"2406.09386","title":"SimGen: Simulator-conditioned Driving Scene Generation","created":"2024-06-13","cited_by_count":34},{"id":"2501.06693","title":"Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation","created":"2025-01-12","cited_by_count":30},{"id":"2203.01914","title":"Playable Environments: Video Manipulation in Space and Time","created":"2022-03-03","cited_by_count":29},{"id":"2408.16090","title":"EPO: Hierarchical LLM Agents with Environment Preference Optimization","created":"2024-08-28","cited_by_count":28},{"id":"2407.11965","title":"UrbanWorld: An Urban World Model for 3D City Generation","created":"2024-07-16","cited_by_count":24},{"id":"2501.10928","title":"Generative Physical AI in Vision: A Survey","created":"2025-01-19","cited_by_count":24},{"id":"2303.16897","title":"Physics-Driven Diffusion Models for Impact Sound Synthesis from Videos","created":"2023-03-29","cited_by_count":22},{"id":"2312.04966","title":"NewMove: Customizing text-to-video models with novel motions","created":"2023-12-07","cited_by_count":18},{"id":"1910.00201","title":"Blending Diverse Physical Priors with Neural Networks","created":"2019-10-01","cited_by_count":11},{"id":"1911.11893","title":"Visual Physics: Discovering Physical Laws from Videos","created":"2019-11-27","cited_by_count":10}],"next_cursor":null}