{"total":230,"rows":[{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897,"area":null},{"id":"2509.22622","title":"LongLive: Real-time Interactive Long Video Generation","created":"2025-09-26","cited_by_count":265,"area":null},{"id":"2502.10248","title":"Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model","created":"2025-02-14","cited_by_count":168,"area":null},{"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":"2509.26328","title":"Fast-dLLM v2: Efficient Block-Diffusion LLM","created":"2025-09-30","cited_by_count":139,"area":null},{"id":"2503.19325","title":"Long-Context Autoregressive Video Modeling with Next-Frame Prediction","created":"2025-03-25","cited_by_count":123,"area":null},{"id":"2506.17201","title":"Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition","created":"2025-06-20","cited_by_count":98,"area":null},{"id":"2508.21058","title":"Mixture of Contexts for Long Video Generation","created":"2025-08-28","cited_by_count":95,"area":null},{"id":"2506.09350","title":"Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation","created":"2025-06-11","cited_by_count":90,"area":null},{"id":"2512.04678","title":"Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation","created":"2025-12-04","cited_by_count":86,"area":null},{"id":"2508.10893","title":"STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer","created":"2025-08-14","cited_by_count":82,"area":null},{"id":"2511.01266","title":"MotionStream: Real-Time Video Generation with Interactive Motion Controls","created":"2025-11-03","cited_by_count":76,"area":null},{"id":"2512.15840","title":"Large Video Planner Enables Generalizable Robot Control","created":"2025-12-17","cited_by_count":70,"area":null},{"id":"2603.04379","title":"Helios: Real Real-Time Long Video Generation Model","created":"2026-03-04","cited_by_count":65,"area":null},{"id":"2602.06028","title":"Context Forcing: Consistent Autoregressive Video Generation with Long Context","created":"2026-02-05","cited_by_count":59,"area":null},{"id":"2510.20822","title":"HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives","created":"2025-10-23","cited_by_count":54,"area":null},{"id":"2507.18634","title":"Captain Cinema: Towards Short Movie Generation","created":"2025-07-24","cited_by_count":48,"area":null},{"id":"2512.14699","title":"MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives","created":"2025-12-16","cited_by_count":45,"area":null},{"id":"2512.04519","title":"VideoSSM: Autoregressive Long Video Generation with Hybrid State-Space Memory","created":"2025-12-04","cited_by_count":42,"area":null},{"id":"2512.15716","title":"Spatia: Video Generation with Updatable Spatial Memory","created":"2025-12-17","cited_by_count":40,"area":null},{"id":"2512.03041","title":"MultiShotMaster: A Controllable Multi-Shot Video Generation Framework","created":"2025-12-02","cited_by_count":36,"area":null},{"id":"2607.08639","title":"Native Video-Action Pretraining for Generalizable Robot Control","created":"2026-07-09","cited_by_count":36,"area":null},{"id":"2601.16914","title":"LoL: Longer than Longer, Scaling Video Generation to Hour","created":"2026-01-23","cited_by_count":32,"area":null},{"id":"2501.12389","title":"Taming Teacher Forcing for Masked Autoregressive Video Generation","created":"2025-01-21","cited_by_count":30,"area":null},{"id":"2506.21552","title":"Whole-Body Conditioned Egocentric Video Prediction","created":"2025-06-26","cited_by_count":30,"area":null},{"id":"2504.01647","title":"FlowR: Flowing from Sparse to Dense 3D Reconstructions","created":"2025-04-02","cited_by_count":28,"area":null},{"id":"2410.03132","title":"Autoregressive Action Sequence Learning for Robotic Manipulation","created":"2024-10-04","cited_by_count":27,"area":null},{"id":"2603.12513","title":"MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens","created":"2026-03-12","cited_by_count":27,"area":null},{"id":"2412.00887","title":"Playable Game Generation","created":"2024-12-01","cited_by_count":26,"area":null},{"id":"2601.03193","title":"UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision","created":"2026-01-06","cited_by_count":26,"area":null},{"id":"2504.12540","title":"UniPhys: Unified Planner and Controller with Diffusion for Flexible Physics-Based Character Control","created":"2025-04-17","cited_by_count":25,"area":null},{"id":"2602.10825","title":"Flow caching for autoregressive video generation","created":"2026-02-11","cited_by_count":25,"area":null},{"id":"2504.21853","title":"A Survey of Interactive Generative Video","created":"2025-04-30","cited_by_count":23,"area":null},{"id":"2508.03694","title":"LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation","created":"2025-08-05","cited_by_count":22,"area":null},{"id":"2601.00664","title":"Avatar Forcing: Real-Time Interactive Head Avatar Generation for Natural Conversation","created":"2026-01-02","cited_by_count":19,"area":null},{"id":"2607.15275","title":"RoboTTT: Context Scaling for Robot Policies","created":"2026-07-16","cited_by_count":19,"area":null},{"id":"2511.07222","title":"Omni-View: Unlocking How Generation Facilitates Understanding in Unified 3D Model based on Multiview images","created":"2025-11-10","cited_by_count":17,"area":null},{"id":"2506.14168","title":"VideoMAR: Autoregressive Video Generatio with Continuous Tokens","created":"2025-06-17","cited_by_count":16,"area":null},{"id":"2508.15720","title":"WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception","created":"2025-08-21","cited_by_count":16,"area":null},{"id":"2512.03520","title":"FloodDiffusion: Tailored Diffusion Forcing for Streaming Motion Generation","created":"2025-12-03","cited_by_count":16,"area":null},{"id":"2503.12929","title":"AR-1-to-3: Single Image to Consistent 3D Object Generation via Next-View Prediction","created":"2025-03-17","cited_by_count":15,"area":null},{"id":"2508.08601","title":"Yan: Foundational Interactive Video Generation","created":"2025-08-12","cited_by_count":15,"area":null},{"id":"2602.14941","title":"AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories","created":"2026-02-16","cited_by_count":15,"area":null},{"id":"2603.08703","title":"HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising","created":"2026-03-09","cited_by_count":15,"area":null},{"id":"2606.26740","title":"LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing","created":"2026-06-25","cited_by_count":15,"area":null},{"id":"2503.15855","title":"VideoRFSplat: Direct Scene-Level Text-to-3D Gaussian Splatting Generation with Flexible Pose and Multi-View Joint Modeling","created":"2025-03-20","cited_by_count":14,"area":null},{"id":"2503.17544","title":"PRIMAL: Physically Reactive and Interactive Motor Model for Avatar Learning","created":"2025-03-21","cited_by_count":14,"area":null},{"id":"2510.20888","title":"Video-As-Prompt: Unified Semantic Control for Video Generation","created":"2025-10-23","cited_by_count":14,"area":null},{"id":"2601.02204","title":"NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation","created":"2026-01-05","cited_by_count":14,"area":null},{"id":"2604.18933","title":"Gated Memory Policy: In-Context Memorization and Adaptation","created":"2026-04-21","cited_by_count":14,"area":null},{"id":"2410.11439","title":"A Simple Approach to Unifying Diffusion-based Conditional Generation","created":"2024-10-15","cited_by_count":13,"area":null},{"id":"2503.17359","title":"Position: Interactive Generative Video as Next-Generation Game Engine","created":"2025-03-21","cited_by_count":13,"area":null},{"id":"2502.11234","title":"MaskFlow: Discrete Flows For Flexible and Efficient Long Video Generation","created":"2025-02-16","cited_by_count":12,"area":null},{"id":"2504.10485","title":"Decoupled Diffusion Sparks Adaptive Scene Generation","created":"2025-04-14","cited_by_count":12,"area":null},{"id":"2512.05115","title":"Light-X: Generative 4D Video Rendering with Camera and Illumination Control","created":"2025-12-04","cited_by_count":12,"area":null},{"id":"2601.15281","title":"StableWorld: Towards Stable and Consistent Long Interactive Video Generation","created":"2026-01-21","cited_by_count":12,"area":null},{"id":"2601.10103","title":"FlowAct-R1: Towards Interactive Humanoid Video Generation","created":"2026-01-15","cited_by_count":11,"area":null},{"id":"2510.27688","title":"Continuous Autoregressive Language Models","created":"2025-10-31","cited_by_count":10,"area":null},{"id":"2512.11274","title":"FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive Diffusion","created":"2025-12-12","cited_by_count":10,"area":null},{"id":"2602.18882","title":"SceneTok: A Compressed, Diffusable Token Space for 3D Scenes","created":"2026-02-21","cited_by_count":10,"area":null},{"id":"2505.23660","title":"D-AR: Diffusion via Autoregressive Models","created":"2025-05-29","cited_by_count":9,"area":null},{"id":"2506.18901","title":"From Virtual Games to Real-World Play","created":"2025-06-23","cited_by_count":9,"area":null},{"id":"2511.12940","title":"Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention","created":"2025-11-17","cited_by_count":9,"area":null},{"id":"2511.20462","title":"STARFlow-V: End-to-End Video Generative Modeling with Normalizing Flows","created":"2025-11-25","cited_by_count":9,"area":null},{"id":"2512.11253","title":"PersonaLive! Expressive Portrait Image Animation for Live Streaming","created":"2025-12-12","cited_by_count":9,"area":null},{"id":"2601.05239","title":"Plenoptic Video Generation","created":"2026-01-08","cited_by_count":9,"area":null},{"id":"2606.04527","title":"Echo-Infinity: Learning Evolving Memory for Real-Time Infinite Video Generation","created":"2026-06-03","cited_by_count":9,"area":null},{"id":"2509.20251","title":"4D Driving Scene Generation With Stereo Forcing","created":"2025-09-24","cited_by_count":8,"area":null},{"id":"2510.00948","title":"InfVSR: Toward Consistency-Driven Streaming Generative Video Super-Resolution","created":"2025-10-01","cited_by_count":8,"area":null},{"id":"2512.06065","title":"EgoEdit: Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editing","created":"2025-12-05","cited_by_count":8,"area":null},{"id":"2602.21929","title":"Geometry-as-context: Modulating Explicit 3D in Scene-consistent Video Generation to Geometry Context","created":"2026-02-25","cited_by_count":8,"area":null},{"id":"2605.17019","title":"StreamingEffect: Real-Time Human-Centric Video Effect Generation","created":"2026-05-16","cited_by_count":8,"area":null},{"id":"2411.13549","title":"KFC-W: Generating 3D-Consistent Videos from Unposed Internet Photos","created":"2024-11-20","cited_by_count":7,"area":null},{"id":"2507.04285","title":"SeqTex: Generate Mesh Textures in Video Sequence","created":"2025-07-06","cited_by_count":7,"area":null},{"id":"2508.20505","title":"Describe, Don't Dictate: Semantic Image Editing with Natural Language Intent","created":"2025-08-28","cited_by_count":7,"area":null},{"id":"2509.21983","title":"Hybrid Diffusion for Simultaneous Symbolic and Continuous Planning","created":"2025-09-26","cited_by_count":7,"area":null},{"id":"2510.04961","title":"SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization","created":"2025-10-06","cited_by_count":7,"area":null},{"id":"2510.08994","title":"Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation","created":"2025-10-10","cited_by_count":7,"area":null},{"id":"2510.26412","title":"LoCoT2V-Bench: Benchmarking Long-Form and Complex Text-to-Video Generation","created":"2025-10-30","cited_by_count":7,"area":null},{"id":"2601.16192","title":"360Anything: Geometry-Free Lifting of Images and Videos to 360{\\deg}","created":"2026-01-22","cited_by_count":7,"area":null},{"id":"2601.20305","title":"Endogenous Reprompting: Self-Evolving Cognitive Alignment for Unified Multimodal Models","created":"2026-01-28","cited_by_count":7,"area":null},{"id":"2604.18215","title":"Memorize When Needed: Decoupled Memory Control for Spatially Consistent Long-Horizon Video Generation","created":"2026-04-20","cited_by_count":7,"area":null},{"id":"2605.06064","title":"PersonaGesture: Single-Reference Co-Speech Gesture Personalization for Unseen Speakers","created":"2026-05-07","cited_by_count":7,"area":null},{"id":"2605.18733","title":"Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memory","created":"2026-05-18","cited_by_count":7,"area":null},{"id":"2606.25041","title":"Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models","created":"2026-06-23","cited_by_count":7,"area":null},{"id":"2608.01771","title":"LiveLight: Real-time Streaming Video Relighting with Interactive Control","created":"2026-08-03","cited_by_count":7,"area":null},{"id":"2506.08456","title":"Improving Motion in Image-to-Video Models via Adaptive Low-Pass Guidance","created":"2025-06-10","cited_by_count":6,"area":null},{"id":"2511.20426","title":"Block Cascading: Training Free Acceleration of Block-Causal Video Models","created":"2025-11-25","cited_by_count":6,"area":null},{"id":"2601.16933","title":"Reward-Forcing: Autoregressive Video Generation with Reward Feedback","created":"2026-01-23","cited_by_count":6,"area":null},{"id":"2603.14331","title":"AvatarForcing: One-Step Streaming Talking Avatars via Local-Future Sliding-Window Denoising","created":"2026-03-15","cited_by_count":6,"area":null},{"id":"2603.25734","title":"Unleashing Guidance Without Classifiers for Human-Object Interaction Animation","created":"2026-03-26","cited_by_count":6,"area":null},{"id":"2604.06939","title":"Grounded Forcing: Bridging Time-Independent Semantics and Proximal Dynamics in Autoregressive Video Synthesis","created":"2026-04-08","cited_by_count":6,"area":null},{"id":"2605.01725","title":"Motion-Aware Caching for Efficient Autoregressive Video Generation","created":"2026-05-03","cited_by_count":6,"area":null},{"id":"2605.08729","title":"Unison: Harmonizing Motion, Speech, and Sound for Human-Centric Audio-Video Generation","created":"2026-05-09","cited_by_count":6,"area":null},{"id":"2608.03974","title":"JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion","created":"2026-08-04","cited_by_count":6,"area":null},{"id":"2508.21556","title":"ECHO: Ego-Centric modeling of Human-Object interactions","created":"2025-08-29","cited_by_count":5,"area":null},{"id":"2509.03348","title":"Generative Auto-Bidding in Large-Scale Competitive Auctions via Diffusion Completer-Aligner","created":"2025-09-03","cited_by_count":5,"area":null},{"id":"2603.13500","title":"ActionPlan: Future-Aware Streaming Motion Synthesis via Frame-Level Action Planning","created":"2026-03-13","cited_by_count":5,"area":null},{"id":"2604.19141","title":"Denoising, Fast and Slow: Difficulty-Aware Adaptive Sampling for Image Generation","created":"2026-04-21","cited_by_count":5,"area":null},{"id":"2605.15824","title":"FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization","created":"2026-05-15","cited_by_count":5,"area":null}],"next_cursor":"100"}