{"total":79,"rows":[{"id":"2605.18678","title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","created":"2026-05-18","cited_by_count":12,"area":null},{"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":"2605.20183","title":"MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation","created":"2026-05-19","cited_by_count":10,"area":null},{"id":"2605.26244","title":"LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV","created":"2026-05-25","cited_by_count":9,"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":"2605.30073","title":"Native Audio-Visual Alignment for Generation","created":"2026-05-28","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":"2605.21028","title":"DySink: Dynamic Frame Sinks for Autoregressive Long Video Generation","created":"2026-05-20","cited_by_count":6,"area":null},{"id":"2606.06042","title":"LoomVideo: Unifying Multimodal Inputs into Video Generation and Editing","created":"2026-06-04","cited_by_count":6,"area":null},{"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":"2606.13432","title":"OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data","created":"2026-06-11","cited_by_count":6,"area":null},{"id":"2606.30534","title":"Orca: The World is in Your Mind","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2607.14189","title":"MultiRef-Compass: Towards Comprehensive Evaluation of Multi-Reference-to-Audio-Video Generation","created":"2026-07-15","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":"2606.14667","title":"Memento: Reconstruct to Remember for Consistent Long Video Generation","created":"2026-06-12","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":"2609.11638","title":"Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation","created":"2026-09-10","cited_by_count":5,"area":null},{"id":"2607.03118","title":"Vidu S1: A Real-Time Interactive Video Generation Model","created":"2026-07-03","cited_by_count":4,"area":null},{"id":"2607.17097","title":"HarmoHOI: Harmonizing Appearance and 3D Motion for Multi-view Hand-Object Interaction Synthesis","created":"2026-07-19","cited_by_count":4,"area":null},{"id":"2606.31946","title":"World Narrative Model for Highly Controllable Video Generation: A Paradigm Shift from Pixel Sampling to Physical World Orchestration","created":"2026-06-30","cited_by_count":3,"area":null},{"id":"2607.24241","title":"FilmBench: A Film-Grade Benchmark for Cinematic Video Generation","created":"2026-07-27","cited_by_count":3,"area":null},{"id":"2608.27168","title":"Magpie: Real-Time World Renderer for Interactive Games","created":"2026-08-27","cited_by_count":3,"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":"2605.20476","title":"Goodbye Drift: Anchored Tree Sampling for Long-Horizon Video-to-Video Generation","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2606.04098","title":"When Seeing Is Not Believing -- A Benchmark for Search-Grounded Video Misinformation Detection","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2608.01157","title":"InteracVid: Building a Real Interactive Audio-Visual Response Dataset from Live-Chat Videos","created":"2026-08-02","cited_by_count":2,"area":null},{"id":"2608.17566","title":"CoinVE-200K: A Large-Scale High-Quality Dataset for Compositional Instruction-Guided Video Editing","created":"2026-08-18","cited_by_count":2,"area":null},{"id":"2609.23407","title":"OmniEcho: Audio-Visual Spatial Understanding for Omni-Modal Embodied Agents","created":"2026-09-20","cited_by_count":2,"area":null},{"id":"2609.36995","title":"Salt++: Context-Aligned Post-Training for Few-Step Streaming Multimodal Generation","created":"2026-09-29","cited_by_count":2,"area":null},{"id":"2605.25569","title":"ControlLight: Towards Controllable, Consistent, and Generalizable Low-Light Enhancement","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2607.14202","title":"KeyFrame-Compass: Towards Comprehensive Evaluation of Keyframe-Conditioned Video Generation","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2607.23588","title":"JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents","created":"2026-07-26","cited_by_count":1,"area":null},{"id":"2607.26818","title":"Ripple: Real-Time Streaming Audio-Video Generation With Cross-Modal Recurrent Memory","created":"2026-07-29","cited_by_count":1,"area":null},{"id":"2607.28261","title":"TARS: Timestep-Aware Data Scaling for 3D-Free Video Re-Shooting","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2608.05049","title":"OmniEdit-Bench: A Comprehensive Benchmark for Instruction-based Video Editing","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2608.12314","title":"StateFlow: Building, Evolving, and Accessing 3D World States for Previsualization","created":"2026-08-12","cited_by_count":1,"area":null},{"id":"2608.14391","title":"Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination","created":"2026-08-14","cited_by_count":1,"area":null},{"id":"2609.08275","title":"Beyond Coherence: Benchmarking Professional Editing-Technique Execution in Multi-Shot Audio-Video Generation","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2609.20414","title":"TouchSight: Bare-Handed Tactile Prediction from Egocentric Video via Generative Visual Augmentation","created":"2026-09-17","cited_by_count":1,"area":null},{"id":"2610.03543","title":"DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation","created":"2026-10-02","cited_by_count":1,"area":null},{"id":"2605.02134","title":"Video Generation with Predictive Latents","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.03652","title":"AniMatrix: An Anime Video Generation Model that Thinks in Art, Not Physics","created":"2026-05-05","cited_by_count":0,"area":null},{"id":"2606.01285","title":"Knowledge-Intensive Video Generation","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2606.04811","title":"Dream.exe: Can Video Generation Models Dream Executable Robot Manipulation?","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.23643","title":"TailorMind: Towards Preference-Aligned Multimodal Content Generation","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2606.24196","title":"Navigating User Behavior toward Personalized Multimodal Generation","created":"2026-06-23","cited_by_count":0,"area":null},{"id":"2608.01628","title":"Motion Beyond Morphology: Bootstrapping Cross-Category Motion Transfer from Abstract Motion Representations","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.04956","title":"ContextMaster: Interactive Multi-Shot Video Creation via Fixed-Budget Sparse Context Routing","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.05663","title":"Vorch-Streamer: Extending Human Audio-Visual Generation to Real-Time Long-Form Streaming","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.09111","title":"RAVEN-Eval: Rubric-Guided Automatic Evaluation for AI Video Generation Models Based on LMM Preference Judgement","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.16717","title":"PersonaShot: Benchmarking Person-Centric Narrative Continuity in Multi-Shot Video Generation","created":"2026-08-17","cited_by_count":0,"area":null},{"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":"2609.06652","title":"VidaForge: Open Research Infrastructure for Video Pretraining Data Recipes","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.15562","title":"PIVOT: Physics-Grounded Verification for AI-Generated Audio-Video Detection","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.18323","title":"Can MiniMax-H3 Reason About the Physical World? An Evaluation of Omni-Modal Generative Model","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.19137","title":"Dreaming the Sound of Contact: Leveraging Video and Audio Generation for Zero-Shot Force-Aware Manipulation and Data Generation","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.21465","title":"OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.25864","title":"TV-AudioRemover: Joint Text-Visual Guided Sound Removal with Multi-Task Hard-Mixture Curriculum","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.34178","title":"Enhanced Video Text Editing with Trajectory-Aligned Glyph Rendering","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.34335","title":"SkillPE: Creativity-Oriented Cinematic Skill Evolution for Text-to-Video Prompt Engineering","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.34722","title":"Geometry as Address: Routing Attention to Visual Memory for Long-Horizon Camera-Controlled Video Generation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.37030","title":"MotionInsight: Diagnosing Object Motion Deficiencies in Generated Videos","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38172","title":"Counterfactual Video Generation Enables Scalable Humanoid Loco-Manipulation","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38748","title":"Hear the World in Stereo: Learning Dynamic Spatial Correspondence for Immersive Joint Video-Audio Generation","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.40129","title":"VR-JEPA: Learning Contrastive-State Latent Guidance for Generation-based Video Reasoning","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.01092","title":"Ego2Act: Evaluating Goal-Directed Manipulation in Egocentric Video Generation","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.05135","title":"How Does Geometry Enter Generated Motion?","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.05779","title":"A Spatiotemporal Semantic Importance-Guided Unified Compression and Editing Framework for AI-Generated Videos","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.10047","title":"AdSpark: A Large-Scale Dataset and Benchmark for Product-Centric Advertisement Video Generation","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.11770","title":"From Video Clips to Creation Trajectory: Sora100K for AI-Native Video Creation","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.12104","title":"VINCIE-NExT: Unlocking Video Editing from Images via In-Context Modeling","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.12156","title":"Connected Self Forcing: Beyond Local Learning in Video Autoregression","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.12963","title":"MotionCoach: Constructing Multimodal Guidance for Video Professional Motion Editing","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.13470","title":"GraftOOD: Grafting Out-of-Distribution Exemplars into Advantage-Weighted Rectification for Video Reward Optimization","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.13733","title":"KVeil: First-Place Solution to ECCV 2026 LifeGenIP Challenge on Unlearnable Videos","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.15900","title":"Gen Through the Lens: Camera-Controllable Video Generation via Cross-Coordinate Conditioning Fusion","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.16204","title":"VGGA: Geometry-Grounded Autoencoder for Video Generation","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.19726","title":"Generative World Simulation with DAO and JING","created":"2026-10-14","cited_by_count":0,"area":null},{"id":"2610.19823","title":"PhyMetric: Diagnosing Physical Plausibility in Text-to-Video Generation via Scene-Level QA","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}