{"total":95,"rows":[{"id":"2604.08995","title":"Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory","created":"2026-04-10","cited_by_count":100,"area":"wm"},{"id":"2510.09212","title":"Stable Video Infinity: Infinite-Length Video Generation with Error Recycling","created":"2025-10-10","cited_by_count":73,"area":"diffusion"},{"id":"2603.04379","title":"Helios: Real Real-Time Long Video Generation Model","created":"2026-03-04","cited_by_count":65,"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":"2512.15702","title":"End-to-End Training for Autoregressive Video Diffusion via Self-Resampling","created":"2025-12-17","cited_by_count":52,"area":"diffusion"},{"id":"2510.18135","title":"World-in-World: World Models in a Closed-Loop World","created":"2025-10-20","cited_by_count":47,"area":"wm"},{"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":"2512.19539","title":"StoryMem: Multi-shot Long Video Storytelling with Memory","created":"2025-12-22","cited_by_count":40,"area":"diffusion"},{"id":"2512.03041","title":"MultiShotMaster: A Controllable Multi-Shot Video Generation Framework","created":"2025-12-02","cited_by_count":36,"area":null},{"id":"2512.07802","title":"OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory","created":"2025-12-08","cited_by_count":35,"area":null},{"id":"2510.01784","title":"Pack and Force Your Memory: Long-form and Consistent Video Generation","created":"2025-10-02","cited_by_count":29,"area":null},{"id":"2603.25746","title":"ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling","created":"2026-03-26","cited_by_count":28,"area":null},{"id":"2602.12675","title":"SLA2: Sparse-Linear Attention with Learnable Routing and QAT","created":"2026-02-13","cited_by_count":22,"area":"diffusion"},{"id":"2509.01085","title":"Bidirectional Sparse Attention for Faster Video Diffusion Training","created":"2025-09-01","cited_by_count":19,"area":"diffusion"},{"id":"2509.21574","title":"X-Streamer: Unified Human World Modeling with Audiovisual Interaction","created":"2025-09-25","cited_by_count":18,"area":"wm"},{"id":"2510.18692","title":"MoGA: Mixture-of-Groups Attention for End-to-End Long Video Generation","created":"2025-10-21","cited_by_count":18,"area":"diffusion"},{"id":"2602.13515","title":"SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning","created":"2026-02-13","cited_by_count":18,"area":"diffusion"},{"id":"2512.12080","title":"BAgger: Backwards Aggregation for Mitigating Drift in Autoregressive Video Diffusion Models","created":"2025-12-12","cited_by_count":16,"area":"wm"},{"id":"2603.06679","title":"MultiGen: Level-Design for Editable Multiplayer Worlds in Diffusion Game Engines","created":"2026-03-03","cited_by_count":16,"area":"wm"},{"id":"2603.13405","title":"Anchor Forcing: Anchor Memory and Tri-Region RoPE for Interactive Streaming Video Diffusion","created":"2026-03-12","cited_by_count":16,"area":"diffusion"},{"id":"2602.05871","title":"Pathwise Test-Time Correction for Autoregressive Long Video Generation","created":"2026-02-05","cited_by_count":15,"area":"diffusion"},{"id":"2608.07408","title":"Addressable Memory for Video World Models","created":"2026-08-07","cited_by_count":15,"area":"wm"},{"id":"2608.13546","title":"Alaya-EVOKE: From Linear-Scaling Supervision to Endless World","created":"2026-08-13","cited_by_count":14,"area":"wm"},{"id":"2606.02436","title":"Geometry-Aware Implicit Memory for Video World Models","created":"2026-06-01","cited_by_count":13,"area":"wm"},{"id":"2602.04789","title":"Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention","created":"2026-02-04","cited_by_count":12,"area":"diffusion"},{"id":"2602.24289","title":"Mode Seeking meets Mean Seeking for Fast Long Video Generation","created":"2026-02-27","cited_by_count":12,"area":"diffusion"},{"id":"2603.08055","title":"Speed3R: Sparse Feed-forward 3D Reconstruction Models","created":"2026-03-09","cited_by_count":10,"area":null},{"id":"2603.08982","title":"SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing","created":"2026-03-09","cited_by_count":10,"area":"diffusion"},{"id":"2605.12496","title":"CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video Narratives","created":"2026-05-12","cited_by_count":10,"area":null},{"id":"2606.02753","title":"MetaWorld: Scaling Multi-Agent Video World Model from Single-view Video Data","created":"2026-06-01","cited_by_count":10,"area":"wm"},{"id":"2511.22973","title":"BIFE: Better Interaction, Fewer Errors for Minute-Long Video Generation","created":"2025-11-28","cited_by_count":9,"area":"wm"},{"id":"2512.13604","title":"LongVie 2: Multimodal Controllable Ultra-Long Video World Model","created":"2025-12-15","cited_by_count":9,"area":"wm"},{"id":"2601.05239","title":"Plenoptic Video Generation","created":"2026-01-08","cited_by_count":9,"area":null},{"id":"2604.23789","title":"MuSS: A Large-Scale Dataset and Cinematic Narrative Benchmark for Multi-Shot Subject-to-Video Generation","created":"2026-04-26","cited_by_count":9,"area":null},{"id":"2606.31734","title":"MemLearner: Learning to Query Context memory for Video World Models","created":"2026-06-30","cited_by_count":9,"area":"wm"},{"id":"2511.20714","title":"Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation","created":"2025-11-25","cited_by_count":8,"area":"wm"},{"id":"2512.21338","title":"HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming","created":"2025-12-24","cited_by_count":8,"area":"diffusion"},{"id":"2604.11244","title":"Script-a-Video: Deep Structured Audio-visual Captions via Factorized Streams and Relational Grounding","created":"2026-04-13","cited_by_count":8,"area":"mllm"},{"id":"2602.06959","title":"CineScene: Implicit 3D as Effective Scene Representation for Cinematic Video Generation","created":"2026-02-06","cited_by_count":7,"area":null},{"id":"2603.11421","title":"ShotVerse: Advancing Cinematic Camera Control for Text-Driven Multi-Shot Video Creation","created":"2026-03-12","cited_by_count":7,"area":null},{"id":"2604.06339","title":"Evolution of Video Generative Foundations","created":"2026-04-07","cited_by_count":7,"area":"wm"},{"id":"2604.15911","title":"Efficient Video Diffusion Models: Advancements and Challenges","created":"2026-04-17","cited_by_count":7,"area":"diffusion"},{"id":"2606.10671","title":"FadeMem: Distance-Aware Memory Consolidation for Autoregressive Video Diffusion","created":"2026-06-09","cited_by_count":7,"area":"diffusion"},{"id":"2601.17067","title":"A Mechanistic View on Video Generation as World Models: State and Dynamics","created":"2026-01-22","cited_by_count":6,"area":"wm"},{"id":"2604.10030","title":"Prompt Relay: Inference-Time Temporal Control for Multi-Event Video Generation","created":"2026-04-11","cited_by_count":6,"area":"diffusion"},{"id":"2605.15199","title":"EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation","created":"2026-05-14","cited_by_count":6,"area":null},{"id":"2605.26525","title":"ReCA: Multi-Shot Long Video Extrapolation via Recursive Context Allocation","created":"2026-05-26","cited_by_count":6,"area":null},{"id":"2606.09803","title":"Echo-Memory: A Controlled Study of Memory in Action World Models","created":"2026-06-08","cited_by_count":6,"area":"wm"},{"id":"2510.20668","title":"From Masks to Worlds: A Hitchhiker's Guide to World Models","created":"2025-10-23","cited_by_count":5,"area":"wm"},{"id":"2603.28489","title":"Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms","created":"2026-03-30","cited_by_count":5,"area":"wm"},{"id":"2605.14487","title":"Head Forcing: Long Autoregressive Video Generation via Head Heterogeneity","created":"2026-05-14","cited_by_count":5,"area":"diffusion"},{"id":"2606.14667","title":"Memento: Reconstruct to Remember for Consistent Long Video Generation","created":"2026-06-12","cited_by_count":5,"area":null},{"id":"2608.26794","title":"Ring Forcing: Towards Precise Long-Term Memory for Autoregressive Video Diffusion","created":"2026-08-27","cited_by_count":5,"area":"diffusion"},{"id":"2510.24718","title":"Generative View Stitching","created":"2025-10-28","cited_by_count":4,"area":"diffusion"},{"id":"2603.25319","title":"MACRO: Advancing Multi-Reference Image Generation with Structured Long-Context Data","created":"2026-03-26","cited_by_count":4,"area":null},{"id":"2605.11596","title":"HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulation","created":"2026-05-12","cited_by_count":4,"area":"wm"},{"id":"2606.09056","title":"MilliVid: Hierarchical Latents for Long-Range Consistency in Video Generation","created":"2026-06-08","cited_by_count":4,"area":null},{"id":"2607.14076","title":"From Pixels to States: Rethinking Interactive World Models as Game Engines","created":"2026-07-15","cited_by_count":4,"area":"wm"},{"id":"2512.03040","title":"Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generation","created":"2025-12-02","cited_by_count":3,"area":null},{"id":"2601.16296","title":"Memory-V2V: Memory-Augmented Video-to-Video Diffusion for Consistent Multi-Turn Editing","created":"2026-01-22","cited_by_count":3,"area":"diffusion"},{"id":"2604.03738","title":"Rethinking Position Embedding as a Context Controller for Multi-Reference and Multi-Shot Video Generation","created":"2026-04-04","cited_by_count":3,"area":null},{"id":"2604.24842","title":"Co-Director: Agentic Generative Video Storytelling","created":"2026-04-27","cited_by_count":3,"area":"diffusion"},{"id":"2605.09442","title":"SWIFT: Prompt-Adaptive Memory for Efficient Interactive Long Video Generation","created":"2026-05-10","cited_by_count":3,"area":null},{"id":"2607.18436","title":"Surprise Forcing: What to Remember, When to Skip in Long Video Generation","created":"2026-07-20","cited_by_count":3,"area":null},{"id":"2608.26671","title":"RECAP-Forcing: Retaining Content Appearances for Long Video Generation","created":"2026-08-27","cited_by_count":3,"area":null},{"id":"2609.16679","title":"AI for Games in the Foundation Model Era","created":"2026-09-15","cited_by_count":3,"area":"wm"},{"id":"2512.11438","title":"Flowception: Temporally Expansive Flow Matching for Video Generation","created":"2025-12-12","cited_by_count":2,"area":"diffusion"},{"id":"2602.01219","title":"Mixture-of-Top-k Attention: Efficient Attention via Scalable Fast Weights","created":"2026-02-01","cited_by_count":2,"area":"moe"},{"id":"2603.06688","title":"Narrative Weaver: Towards Controllable Long-Range Visual Consistency with Multi-Modal Conditioning","created":"2026-03-04","cited_by_count":2,"area":null},{"id":"2605.12957","title":"GTA: Advancing Image-to-3D World Generation via Geometry Then Appearance Video Diffusion","created":"2026-05-13","cited_by_count":2,"area":"diffusion"},{"id":"2605.18365","title":"GeoFlow: Enforcing Implicit Geometric Consistency in Video Generation","created":"2026-05-18","cited_by_count":2,"area":"diffusion"},{"id":"2606.02479","title":"Retrieve What's Missing: Coverage-Maximizing Retrieval for Consistent Long Video Generation","created":"2026-06-01","cited_by_count":2,"area":null},{"id":"2606.16184","title":"EvoState: Closed-Loop Visual State Management for Long-Form Video Generation","created":"2026-06-15","cited_by_count":2,"area":null},{"id":"2606.22370","title":"Towards Error-Free Long Video Generation","created":"2026-06-21","cited_by_count":2,"area":"diffusion"},{"id":"2607.15772","title":"SlotMem: Character-Addressable Internal Memory for Narrative Long Video Generation","created":"2026-07-17","cited_by_count":2,"area":null},{"id":"2511.16783","title":"Generative Augmented Reality: Paradigms, Technologies, and Future Applications","created":"2025-11-20","cited_by_count":1,"area":null},{"id":"2603.17944","title":"TransText: Alpha-as-RGB Representation for Transparent Text Animation","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2604.19741","title":"CityRAG: Stepping Into a City via Spatially-Grounded Video Generation","created":"2026-04-21","cited_by_count":1,"area":null},{"id":"2604.27443","title":"ABC: Any-Subset Autoregression via Non-Markovian Diffusion Bridges in Continuous Time and Space","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.18233","title":"Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2607.03012","title":"HyperVAttention: Efficient Sparse Attention with Spatio-Temporal Clustering for Video Diffusion","created":"2026-07-03","cited_by_count":1,"area":"diffusion"},{"id":"2608.17559","title":"MSEditor: Toward Consistent Multi-Shot Video Editing","created":"2026-08-18","cited_by_count":1,"area":null},{"id":"2609.34502","title":"SubjectAnchor: Subject-Aware Memory-to-Video for Multi-Shot Storytelling","created":"2026-09-28","cited_by_count":1,"area":null},{"id":"2604.17428","title":"Long-CODE: Isolating Pure Long-Context as an Orthogonal Dimension in Video Evaluation","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2605.13080","title":"Learning to See What You Need: Gaze Attention for Multimodal Large Language Models","created":"2026-05-13","cited_by_count":0,"area":"mllm"},{"id":"2608.20910","title":"InfinityEdit: Infinite Video Editing with a Lightweight Edit-Ignition Adapter","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.13830","title":"DiVA: Enabling Interactive Digital Life Simulation via Video Models","created":"2026-09-12","cited_by_count":0,"area":null},{"id":"2609.32882","title":"Improving Video Sparse Attention with Fine-grained Router and Sparse Rebasing","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.34606","title":"WorldAttention: An Efficient Attention Architecture for Interactive Video World Models","created":"2026-09-28","cited_by_count":0,"area":"wm"},{"id":"2609.34677","title":"Learning What to Recall: Adaptive Multi-Cue Episodic Memory for World Models","created":"2026-09-28","cited_by_count":0,"area":"wm"},{"id":"2610.00544","title":"Memorizon: Training World Models Beyond Their Context Window","created":"2026-09-30","cited_by_count":0,"area":"wm"},{"id":"2610.02153","title":"MosaiChunk: Compositing Spatio-Temporal Memory for Autoregressive Video Generation","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.02521","title":"Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory","created":"2026-10-01","cited_by_count":0,"area":"wm"},{"id":"2610.19795","title":"StateCraft: Augmenting Video World Models with Abstract-State Reasoning","created":"2026-10-14","cited_by_count":0,"area":"wm"}],"next_cursor":null}