{"list":"other","total":61,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897},{"id":"2305.14992","title":"Reasoning with Language Model is Planning with World Model","created":"2023-05-24","cited_by_count":861},{"id":"2409.18869","title":"Emu3: Next-Token Prediction is All You Need","created":"2024-09-27","cited_by_count":781},{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752},{"id":"2312.03641","title":"MotionCtrl: A Unified and Flexible Motion Controller for Video Generation","created":"2023-12-06","cited_by_count":580},{"id":"2408.11039","title":"Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model","created":"2024-08-20","cited_by_count":483},{"id":"2412.07772","title":"From Slow Bidirectional to Fast Autoregressive Video Diffusion Models","created":"2024-12-10","cited_by_count":433},{"id":"2411.04983","title":"DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning","created":"2024-11-07","cited_by_count":386},{"id":"2405.12399","title":"Diffusion for World Modeling: Visual Details Matter in Atari","created":"2024-05-20","cited_by_count":300},{"id":"2412.03572","title":"Navigation World Models","created":"2024-12-04","cited_by_count":272},{"id":"2601.03233","title":"LTX-2: Efficient Joint Audio-Visual Foundation Model","created":"2026-01-06","cited_by_count":236},{"id":"2509.20328","title":"Video models are zero-shot learners and reasoners","created":"2025-09-24","cited_by_count":220},{"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":"1507.08750","title":"Action-Conditional Video Prediction using Deep Networks in Atari Games","created":"2015-07-31","cited_by_count":172},{"id":"2406.02509","title":"CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation","created":"2024-06-04","cited_by_count":166},{"id":"2411.04996","title":"Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models","created":"2024-11-07","cited_by_count":163},{"id":"2411.07975","title":"JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation","created":"2024-11-12","cited_by_count":163},{"id":"2506.03141","title":"Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval","created":"2025-06-03","cited_by_count":163},{"id":"2405.15223","title":"iVideoGPT: Interactive VideoGPTs are Scalable World Models","created":"2024-05-24","cited_by_count":146},{"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},{"id":"2509.24527","title":"Training Agents Inside of Scalable World Models","created":"2025-09-29","cited_by_count":136},{"id":"2410.15957","title":"CamI2V: Camera-Controlled Image-to-Video Diffusion Model","created":"2024-10-21","cited_by_count":120},{"id":"2506.18903","title":"VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory","created":"2025-06-23","cited_by_count":109},{"id":"2507.10496","title":"Cameras as Relative Positional Encoding","created":"2025-07-14","cited_by_count":105},{"id":"2506.17201","title":"Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition","created":"2025-06-20","cited_by_count":98},{"id":"2508.21058","title":"Mixture of Contexts for Long Video Generation","created":"2025-08-28","cited_by_count":95},{"id":"2005.12126","title":"Learning to Simulate Dynamic Environments with GameGAN","created":"2020-05-25","cited_by_count":86},{"id":"2512.22096","title":"Yume-1.5: A Text-Controlled Interactive World Generation Model","created":"2025-12-26","cited_by_count":84},{"id":"2412.03568","title":"The Matrix: Infinite-Horizon World Generation with Real-Time Moving Control","created":"2024-12-04","cited_by_count":80},{"id":"1704.02254","title":"Recurrent Environment Simulators","created":"2017-04-07","cited_by_count":68},{"id":"2506.15675","title":"Sekai: A Video Dataset towards World Exploration","created":"2025-06-18","cited_by_count":67},{"id":"2101.12195","title":"Playable Video Generation","created":"2021-01-28","cited_by_count":64},{"id":"2605.15141","title":"Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation","created":"2026-05-14","cited_by_count":56},{"id":"2406.06485","title":"Can Language Models Serve as Text-Based World Simulators?","created":"2024-06-10","cited_by_count":52},{"id":"2512.15702","title":"End-to-End Training for Autoregressive Video Diffusion via Self-Resampling","created":"2025-12-17","cited_by_count":52},{"id":"2601.05230","title":"Learning Latent Action World Models In The Wild","created":"2026-01-08","cited_by_count":47},{"id":"2404.18202","title":"WorldGPT: Empowering LLM as Multimodal World Model","created":"2024-04-28","cited_by_count":42},{"id":"2512.04519","title":"VideoSSM: Autoregressive Long Video Generation with Hybrid State-Space Memory","created":"2025-12-04","cited_by_count":42},{"id":"2512.15716","title":"Spatia: Video Generation with Updatable Spatial Memory","created":"2025-12-17","cited_by_count":40},{"id":"2511.09057","title":"PAN: A World Model for General, Actionable, and Long-Horizon World Simulation","created":"2025-11-12","cited_by_count":36},{"id":"2203.01914","title":"Playable Environments: Video Manipulation in Space and Time","created":"2022-03-03","cited_by_count":29},{"id":"2504.21853","title":"A Survey of Interactive Generative Video","created":"2025-04-30","cited_by_count":23},{"id":"2303.13472","title":"Promptable Game Models: Text-Guided Game Simulation via Masked Diffusion Models","created":"2023-03-23","cited_by_count":22},{"id":"2603.09488","title":"Streaming Autoregressive Video Generation via Diagonal Distillation","created":"2026-03-10","cited_by_count":18},{"id":"2512.23851","title":"TinyHistory: Lightweight Video History Embeddings via Two-Stage Context Learning","created":"2025-12-29","cited_by_count":15},{"id":"2603.08703","title":"HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising","created":"2026-03-09","cited_by_count":15},{"id":"2603.17051","title":"Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models","created":"2026-03-17","cited_by_count":15},{"id":"2503.17359","title":"Position: Interactive Generative Video as Next-Generation Game Engine","created":"2025-03-21","cited_by_count":13},{"id":"2505.12707","title":"PLAICraft: Large-Scale Time-Aligned Vision-Speech-Action Dataset for Embodied AI","created":"2025-05-19","cited_by_count":10},{"id":"2602.10104","title":"Olaf-World: Orienting Latent Actions for Video World Modeling","created":"2026-02-10","cited_by_count":10},{"id":"2605.15725","title":"DiLA: Disentangled Latent Action World Models","created":"2026-05-15","cited_by_count":10},{"id":"2506.18901","title":"From Virtual Games to Real-World Play","created":"2025-06-23","cited_by_count":9},{"id":"2511.12940","title":"Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention","created":"2025-11-17","cited_by_count":9},{"id":"2504.01014","title":"AnimeGamer: Infinite Anime Life Simulation with Next Game State Prediction","created":"2025-04-01","cited_by_count":7},{"id":"2602.10480","title":"Neuro-Symbolic Synergy for World Modeling","created":"2026-02-11","cited_by_count":6},{"id":"2602.06130","title":"Self-Improving World Modelling with Latent Actions","created":"2026-02-05","cited_by_count":5}],"next_cursor":null}