{"total":236,"rows":[{"id":"2606.02800","title":"Cosmos 3: Omnimodal World Models for Physical AI","created":"2026-06-01","cited_by_count":165,"area":"wm"},{"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":"2603.04379","title":"Helios: Real Real-Time Long Video Generation Model","created":"2026-03-04","cited_by_count":65,"area":null},{"id":"2605.15178","title":"SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer","created":"2026-05-14","cited_by_count":55,"area":"wm"},{"id":"2602.08794","title":"MOVA: Towards Scalable and Synchronized Video-Audio Generation","created":"2026-02-09","cited_by_count":43,"area":null},{"id":"2602.20159","title":"A Very Big Video Reasoning Suite","created":"2026-02-23","cited_by_count":34,"area":"lr"},{"id":"2601.15282","title":"Rethinking Video Generation Model for the Embodied World","created":"2026-01-21","cited_by_count":33,"area":null},{"id":"2603.07145","title":"LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models","created":"2026-03-07","cited_by_count":28,"area":"wm"},{"id":"2602.19163","title":"JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation","created":"2026-02-22","cited_by_count":25,"area":null},{"id":"2603.21986","title":"Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model","created":"2026-03-23","cited_by_count":25,"area":null},{"id":"2603.26599","title":"VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward","created":"2026-03-27","cited_by_count":24,"area":"diffusion"},{"id":"2605.05204","title":"D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models","created":"2026-05-06","cited_by_count":22,"area":"diffusion"},{"id":"2604.08540","title":"AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation","created":"2026-04-09","cited_by_count":21,"area":null},{"id":"2602.12160","title":"DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation","created":"2026-02-12","cited_by_count":20,"area":null},{"id":"2603.11647","title":"OmniForcing: Unleashing Real-time Joint Audio-Visual Generation","created":"2026-03-12","cited_by_count":16,"area":"diffusion"},{"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":"2607.26037","title":"Wonder: Video World Model Done Better","created":"2026-07-28","cited_by_count":15,"area":"wm"},{"id":"2603.16870","title":"Demystifying Video Reasoning","created":"2026-03-17","cited_by_count":14,"area":"lr"},{"id":"2607.08766","title":"OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators","created":"2026-07-09","cited_by_count":14,"area":"diffusion"},{"id":"2603.23497","title":"WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG","created":"2026-03-24","cited_by_count":13,"area":"wm"},{"id":"2604.23632","title":"Hallo-Live: Real-Time Streaming Joint Audio-Video Avatar Generation with Asynchronous Dual-Stream and Human-Centric Preference Distillation","created":"2026-04-26","cited_by_count":13,"area":"diffusion"},{"id":"2608.23189","title":"EchoWM: Open and Enterable Omnimodal World Models","created":"2026-08-24","cited_by_count":13,"area":"wm"},{"id":"2601.21282","title":"WorldBench: Benchmarking Physical Understanding of World Models by Isolating Physics Concepts","created":"2026-01-29","cited_by_count":12,"area":"wm"},{"id":"2602.21818","title":"SkyReels-V4: Multi-modal Video-Audio Generation, Inpainting and Editing model","created":"2026-02-25","cited_by_count":12,"area":null},{"id":"2605.10806","title":"PhyGround: Benchmarking Physical Reasoning in Generative World Models","created":"2026-05-11","cited_by_count":12,"area":"wm"},{"id":"2609.02886","title":"SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models","created":"2026-09-02","cited_by_count":12,"area":"wm"},{"id":"2605.30409","title":"SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion Transformer","created":"2026-05-28","cited_by_count":11,"area":"diffusion"},{"id":"2602.08277","title":"PISCO: Precise Video Instance Insertion with Sparse Control","created":"2026-02-09","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":"2606.28128","title":"PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation","created":"2026-06-26","cited_by_count":10,"area":null},{"id":"2607.26004","title":"Parallel Decoding Distillation for Fast Image and Video Generation","created":"2026-07-28","cited_by_count":10,"area":"diffusion"},{"id":"2604.02296","title":"VOID: Video Object and Interaction Deletion","created":"2026-04-02","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":"2603.14375","title":"The Pulse of Motion: Measuring Physical Frame Rate from Visual Dynamics","created":"2026-03-15","cited_by_count":8,"area":"wm"},{"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":"2604.11804","title":"OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation","created":"2026-04-13","cited_by_count":8,"area":null},{"id":"2605.07061","title":"Do Joint Audio-Video Generation Models Understand Physics?","created":"2026-05-08","cited_by_count":8,"area":null},{"id":"2601.22143","title":"JUST-DUB-IT: Video Dubbing via Joint Audio-Visual Diffusion","created":"2026-01-29","cited_by_count":7,"area":null},{"id":"2602.02465","title":"MentisOculi: Revealing the Limits of Reasoning with Mental Imagery","created":"2026-02-02","cited_by_count":7,"area":"lr"},{"id":"2603.00466","title":"DreamWorld: Unified World Modeling in Video Generation","created":"2026-02-28","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":"2605.12480","title":"OmniNFT: Modality-wise Omni Diffusion Reinforcement for Joint Audio-Video Generation","created":"2026-05-12","cited_by_count":7,"area":null},{"id":"2605.15190","title":"RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO","created":"2026-05-14","cited_by_count":7,"area":"diffusion"},{"id":"2605.25343","title":"Toward Native Multimodal Modeling: A Roadmap","created":"2026-05-25","cited_by_count":7,"area":"wm"},{"id":"2605.30073","title":"Native Audio-Visual Alignment for Generation","created":"2026-05-28","cited_by_count":7,"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":"2605.19242","title":"PhyWorld: Physics-Faithful World Model for Video Generation","created":"2026-05-19","cited_by_count":6,"area":"wm"},{"id":"2606.09639","title":"CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generation","created":"2026-06-08","cited_by_count":6,"area":null},{"id":"2606.17800","title":"MaineCoon: Pursuing A Real-Time Audio-Visual Social World Model","created":"2026-06-16","cited_by_count":6,"area":"wm"},{"id":"2606.21661","title":"UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating","created":"2026-06-19","cited_by_count":6,"area":null},{"id":"2607.03509","title":"Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model","created":"2026-07-03","cited_by_count":6,"area":"diffusion"},{"id":"2608.26105","title":"VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning","created":"2026-08-26","cited_by_count":6,"area":"lr"},{"id":"2602.03826","title":"Continuous Control of Editing Models via Adaptive-Origin Guidance","created":"2026-02-03","cited_by_count":5,"area":null},{"id":"2603.24793","title":"AVControl: Efficient Framework for Training Audio-Visual Controls","created":"2026-03-25","cited_by_count":5,"area":null},{"id":"2604.09429","title":"Rays as Pixels: Learning A Joint Distribution of Videos and Camera Trajectories","created":"2026-04-10","cited_by_count":5,"area":null},{"id":"2605.11723","title":"CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating","created":"2026-05-12","cited_by_count":5,"area":"mllm"},{"id":"2605.18467","title":"InstructAV2AV: Instruction-Guided Audio-Video Joint Editing","created":"2026-05-18","cited_by_count":5,"area":null},{"id":"2607.13336","title":"Delving into the Temporal Challenges of Unified Video Protection Against Image-to-Video and Fine-Tuning-based Customization","created":"2026-07-14","cited_by_count":5,"area":null},{"id":"2608.18607","title":"VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generation","created":"2026-08-19","cited_by_count":5,"area":"alignment"},{"id":"2603.17989","title":"Versatile Editing of Video Content, Actions, and Dynamics without Training","created":"2026-03-18","cited_by_count":4,"area":null},{"id":"2603.18600","title":"Improving Joint Audio-Video Generation with Cross-Modal Context Learning","created":"2026-03-19","cited_by_count":4,"area":"diffusion"},{"id":"2604.19679","title":"MMControl: Unified Multi-Modal Control for Joint Audio-Video Generation","created":"2026-04-21","cited_by_count":4,"area":"diffusion"},{"id":"2605.10079","title":"SocialDirector: Training-Free Social Interaction Control for Multi-Person Video Generation","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2605.18984","title":"Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos","created":"2026-05-18","cited_by_count":4,"area":null},{"id":"2605.25195","title":"Baton: Explicit Semantic Blueprints for Joint Video-Audio Generation","created":"2026-05-24","cited_by_count":4,"area":"diffusion"},{"id":"2605.28035","title":"MTAVG-Bench 2.0: Diagnosing Failure Modes of Cinematic Expressiveness in Multi-Talker Audio-Video Generation","created":"2026-05-27","cited_by_count":4,"area":null},{"id":"2606.03183","title":"Inference-Time Scaling for Joint Audio-Video Generation","created":"2026-06-02","cited_by_count":4,"area":"lr"},{"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":"2608.13049","title":"H2R-Bench: Benchmarking Human-to-Robot Manipulation Video Generation in World Models","created":"2026-08-13","cited_by_count":4,"area":"wm"},{"id":"2608.16859","title":"HarnessEval-W: Agentifying the Evaluation of Visual Worlds","created":"2026-08-17","cited_by_count":4,"area":"wm"},{"id":"2608.23383","title":"Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds","created":"2026-08-24","cited_by_count":4,"area":"wm"},{"id":"2604.18326","title":"OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation","created":"2026-04-20","cited_by_count":3,"area":null},{"id":"2604.24351","title":"Diffusion Templates: A Unified Plugin Framework for Controllable Diffusion","created":"2026-04-27","cited_by_count":3,"area":"diffusion"},{"id":"2605.25659","title":"StreamChar: Long-Horizon Streaming Character Audio-Video Generation with Decoupled Orchestration","created":"2026-05-25","cited_by_count":3,"area":null},{"id":"2606.09150","title":"Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutions","created":"2026-06-08","cited_by_count":3,"area":"diffusion"},{"id":"2607.09185","title":"Causally Debiased Latent Action Model for Embodied Action Conditioned World Models","created":"2026-07-10","cited_by_count":3,"area":"wm"},{"id":"2607.14088","title":"VideoRAE: Taming Video Foundation Models for Generative Modeling via Representation Autoencoders","created":"2026-07-15","cited_by_count":3,"area":null},{"id":"2607.14681","title":"ReBind: Multi-Reference Video Editing via Structured Instructions with Explicit Reference Relationships","created":"2026-07-16","cited_by_count":3,"area":"diffusion"},{"id":"2608.27168","title":"Magpie: Real-Time World Renderer for Interactive Games","created":"2026-08-27","cited_by_count":3,"area":null},{"id":"2609.07720","title":"Better Call CineCrew: Consistent Ultra-Long Narrative-to-Film Generation","created":"2026-09-07","cited_by_count":3,"area":null},{"id":"2609.20034","title":"Astronex-World 1.0: Real-Time Interactive World Model Foundation","created":"2026-09-17","cited_by_count":3,"area":"wm"},{"id":"2603.17825","title":"Steering Video Diffusion Transformers with Massive Activations","created":"2026-03-18","cited_by_count":2,"area":"diffusion"},{"id":"2604.11788","title":"HDR Video Generation via Latent Alignment with Logarithmic Encoding","created":"2026-04-13","cited_by_count":2,"area":null},{"id":"2604.19193","title":"How Far Are Video Models from True Multimodal Reasoning?","created":"2026-04-21","cited_by_count":2,"area":"lr"},{"id":"2604.20816","title":"ParetoSlider: Diffusion Models Post-Training for Continuous Reward Control","created":"2026-04-22","cited_by_count":2,"area":"diffusion"},{"id":"2604.23586","title":"Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling","created":"2026-04-26","cited_by_count":2,"area":"diffusion"},{"id":"2605.01809","title":"TMD-Bench: A Multi-Level Evaluation Paradigm for Music-Dance Co-Generation","created":"2026-05-03","cited_by_count":2,"area":null},{"id":"2605.04045","title":"Audio-Visual Intelligence in Large Foundation Models","created":"2026-05-05","cited_by_count":2,"area":null},{"id":"2605.12179","title":"SyncDPO: Enhancing Temporal Synchronization in Video-Audio Joint Generation via Preference Learning","created":"2026-05-12","cited_by_count":2,"area":"alignment"},{"id":"2605.13565","title":"Qwen-Image-VAE-2.0 Technical Report","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2605.17488","title":"Omni-Customizer: End-to-End MultiModal Customization for Joint Audio-Video Generation","created":"2026-05-17","cited_by_count":2,"area":null},{"id":"2605.18346","title":"Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion","created":"2026-05-18","cited_by_count":2,"area":"diffusion"},{"id":"2605.20476","title":"Goodbye Drift: Anchored Tree Sampling for Long-Horizon Video-to-Video Generation","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2605.20708","title":"Rethinking Cross-Layer Information Routing in Diffusion Transformers","created":"2026-05-20","cited_by_count":2,"area":"diffusion"},{"id":"2605.25801","title":"PixelWizard: Towards Efficient High-Fidelity Video Generation at Ultra-Large Spatial Resolution","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"2605.30542","title":"Physically Viable World Models: A Case for Query-Conditioned Embodied AI","created":"2026-05-28","cited_by_count":2,"area":"wm"},{"id":"2606.32033","title":"SpheRoPE: Zero-Shot Optimization-Free 360 Panorama Generation with Spherical RoPE","created":"2026-06-30","cited_by_count":2,"area":"diffusion"},{"id":"2607.20940","title":"Ms. Forcing: Efficient Streaming Video Generation with Multi-Scale Patchification and Attention","created":"2026-07-23","cited_by_count":2,"area":"diffusion"},{"id":"2607.28624","title":"PhiZero: A World Model Built Around Physical Language","created":"2026-07-30","cited_by_count":2,"area":"wm"},{"id":"2608.09873","title":"Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains","created":"2026-08-10","cited_by_count":2,"area":"lr"}],"next_cursor":"100"}