{"list":"other","total":66,"rows":[{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"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":"1711.07280","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","created":"2017-11-20","cited_by_count":1027},{"id":"2311.18828","title":"One-step Diffusion with Distribution Matching Distillation","created":"2023-11-30","cited_by_count":1019},{"id":"2405.14867","title":"Improved Distribution Matching Distillation for Fast Image Synthesis","created":"2024-05-23","cited_by_count":684},{"id":"2407.01392","title":"Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion","created":"2024-07-01","cited_by_count":681},{"id":"2304.11277","title":"PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel","created":"2023-04-21","cited_by_count":660},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"2309.17080","title":"GAIA-1: A Generative World Model for Autonomous Driving","created":"2023-09-29","cited_by_count":637},{"id":"2506.08009","title":"Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion","created":"2025-06-09","cited_by_count":625},{"id":"2309.00071","title":"YaRN: Efficient Context Window Extension of Large Language Models","created":"2023-08-31","cited_by_count":601},{"id":"2505.13447","title":"Mean Flows for One-step Generative Modeling","created":"2025-05-19","cited_by_count":561},{"id":"2407.08608","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","created":"2024-07-11","cited_by_count":519},{"id":"2412.07772","title":"From Slow Bidirectional to Fast Autoregressive Video Diffusion Models","created":"2024-12-10","cited_by_count":433},{"id":"2410.05954","title":"Pyramidal Flow Matching for Efficient Video Generative Modeling","created":"2024-10-08","cited_by_count":366},{"id":"2503.03751","title":"GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control","created":"2025-03-05","cited_by_count":341},{"id":"2011.13922","title":"A Recurrent Vision-and-Language BERT for Navigation","created":"2020-11-26","cited_by_count":302},{"id":"2405.12399","title":"Diffusion for World Modeling: Visual Details Matter in Atari","created":"2024-05-20","cited_by_count":300},{"id":"2509.22622","title":"LongLive: Real-time Interactive Long Video Generation","created":"2025-09-26","cited_by_count":265},{"id":"2506.09113","title":"Seedance 1.0: Exploring the Boundaries of Video Generation Models","created":"2025-06-10","cited_by_count":259},{"id":"2504.13074","title":"SkyReels-V2: Infinite-length Film Generative Model","created":"2025-04-17","cited_by_count":229},{"id":"2509.20328","title":"Video models are zero-shot learners and reasoners","created":"2025-09-24","cited_by_count":220},{"id":"2406.09394","title":"WonderWorld: Interactive 3D Scene Generation from a Single Image","created":"2024-06-13","cited_by_count":202},{"id":"2510.02283","title":"Self-Forcing++: Towards Minute-Scale High-Quality Video Generation","created":"2025-10-02","cited_by_count":192},{"id":"2502.06764","title":"History-Guided Video Diffusion","created":"2025-02-10","cited_by_count":171},{"id":"2508.10934","title":"ViPE: Video Pose Engine for 3D Geometric Perception","created":"2025-08-12","cited_by_count":170},{"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":"2304.09151","title":"UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual Pretraining","created":"2023-04-18","cited_by_count":151},{"id":"2206.06360","title":"ARF: Artistic Radiance Fields","created":"2022-06-13","cited_by_count":147},{"id":"2405.11473","title":"FIFO-Diffusion: Generating Infinite Videos from Text without Training","created":"2024-05-19","cited_by_count":137},{"id":"2505.23884","title":"Test-Time Training Done Right","created":"2025-05-29","cited_by_count":130},{"id":"2105.13120","title":"Sequence Parallelism: Long Sequence Training from System Perspective","created":"2021-05-26","cited_by_count":126},{"id":"2402.09470","title":"Rolling Diffusion Models","created":"2024-02-12","cited_by_count":104},{"id":"2504.05298","title":"One-Minute Video Generation with Test-Time Training","created":"2025-04-07","cited_by_count":101},{"id":"2506.04225","title":"Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation","created":"2025-06-04","cited_by_count":101},{"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":"2507.21809","title":"HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels","created":"2025-07-29","cited_by_count":94},{"id":"2506.09350","title":"Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation","created":"2025-06-11","cited_by_count":90},{"id":"2501.07888","title":"Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding","created":"2025-01-14","cited_by_count":81},{"id":"2412.03568","title":"The Matrix: Infinite-Horizon World Generation with Real-Time Moving Control","created":"2024-12-04","cited_by_count":80},{"id":"2509.09676","title":"SpatialVID: A Large-Scale Video Dataset with Spatial Annotations","created":"2025-09-11","cited_by_count":77},{"id":"2511.01266","title":"MotionStream: Real-Time Video Generation with Interactive Motion Controls","created":"2025-11-03","cited_by_count":76},{"id":"2411.16375","title":"Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing","created":"2024-11-25","cited_by_count":74},{"id":"2410.08151","title":"Progressive Autoregressive Video Diffusion Models","created":"2024-10-10","cited_by_count":68},{"id":"2506.15675","title":"Sekai: A Video Dataset towards World Exploration","created":"2025-06-18","cited_by_count":67},{"id":"2412.01821","title":"World-consistent Video Diffusion with Explicit 3D Modeling","created":"2024-12-02","cited_by_count":65},{"id":"2412.06699","title":"You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale","created":"2024-12-09","cited_by_count":65},{"id":"2501.14729","title":"HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation","created":"2025-01-24","cited_by_count":56},{"id":"2503.07418","title":"AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion","created":"2025-03-10","cited_by_count":55},{"id":"2507.03745","title":"StreamDiT: Real-Time Streaming Text-to-Video Generation","created":"2025-07-04","cited_by_count":48},{"id":"2412.07720","title":"ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer","created":"2024-12-10","cited_by_count":45},{"id":"2501.12389","title":"Taming Teacher Forcing for Masked Autoregressive Video Generation","created":"2025-01-21","cited_by_count":30},{"id":"2502.10498","title":"The Role of World Models in Shaping Autonomous Driving: A Comprehensive Survey","created":"2025-02-14","cited_by_count":29},{"id":"2504.15278","title":"DRAWER: Digital Reconstruction and Articulation With Environment Realism","created":"2025-04-21","cited_by_count":29},{"id":"2408.13724","title":"PhysPart: Physically Plausible Part Completion for Interactable Objects","created":"2024-08-25","cited_by_count":25},{"id":"2507.05763","title":"DreamArt: Generating Interactable Articulated Objects from a Single Image","created":"2025-07-08","cited_by_count":25},{"id":"2503.10704","title":"Error Analyses of Auto-Regressive Video Diffusion Models: A Unified Framework","created":"2025-03-12","cited_by_count":20},{"id":"2504.19322","title":"Learned Perceptive Forward Dynamics Model for Safe and Platform-aware Robotic Navigation","created":"2025-04-27","cited_by_count":11},{"id":"2508.00558","title":"Guiding Diffusion-Based Articulated Object Generation by Partial Point Cloud Alignment and Physical Plausibility Constraints","created":"2025-08-01","cited_by_count":8},{"id":"2504.21332","title":"MagicCraft: Natural Language-Driven Generation of Dynamic and Interactive 3D Objects for Commercial Metaverse Platforms","created":"2025-04-30","cited_by_count":1}],"next_cursor":null}