{"total":137,"rows":[{"id":"2603.04379","title":"Helios: Real Real-Time Long Video Generation Model","created":"2026-03-04","cited_by_count":65,"area":null},{"id":"2602.08794","title":"MOVA: Towards Scalable and Synchronized Video-Audio Generation","created":"2026-02-09","cited_by_count":43,"area":null},{"id":"2601.15282","title":"Rethinking Video Generation Model for the Embodied World","created":"2026-01-21","cited_by_count":33,"area":null},{"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":"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":"2602.14941","title":"AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories","created":"2026-02-16","cited_by_count":15,"area":null},{"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":"2605.12496","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":"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":"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":"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":"2605.30073","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":"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":"2606.21661","title":"UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating","created":"2026-06-19","cited_by_count":6,"area":null},{"id":"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":"2605.18467","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":"2603.17989","title":"Versatile Editing of Video Content, Actions, and Dynamics without Training","created":"2026-03-18","cited_by_count":4,"area":null},{"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":"2605.28035","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":"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":"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":"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":"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":"2604.11788","title":"HDR Video Generation via Latent Alignment with Logarithmic Encoding","created":"2026-04-13","cited_by_count":2,"area":null},{"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":"2605.13565","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":"2605.20476","title":"Goodbye Drift: Anchored Tree Sampling for Long-Horizon Video-to-Video Generation","created":"2026-05-19","cited_by_count":2,"area":null},{"id":"2605.25801","title":"PixelWizard: Towards Efficient High-Fidelity Video Generation at Ultra-Large Spatial Resolution","created":"2026-05-25","cited_by_count":2,"area":null},{"id":"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":"2608.20534","title":"Grounded-Exo2Ego: Structured Semantic Grounding for Robust Exocentric-to-Egocentric Video Generation","created":"2026-08-20","cited_by_count":2,"area":null},{"id":"2608.21424","title":"EditStream: A Unified Autoregressive Framework for Interactive Video Generation and Editing","created":"2026-08-16","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":"2603.12118","title":"Cornserve: A Distributed Serving System for Any-to-Any Multimodal Models","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2603.17889","title":"Identity as Presence: Towards Appearance and Voice Personalized Joint Audio-Video Generation","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2603.23132","title":"InterDyad: Interactive Dyadic Speech-to-Video Generation by Querying Intermediate Visual Guidance","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2603.23462","title":"RealMaster: Lifting Rendered Scenes into Photorealistic Video","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2604.13793","title":"From Synchrony to Sequence: Exo-to-Ego Generation via Interpolation","created":"2026-04-15","cited_by_count":1,"area":null},{"id":"2604.22554","title":"Video Analysis and Generation via a Semantic Progress Function","created":"2026-04-24","cited_by_count":1,"area":null},{"id":"2605.14815","title":"Probing into Camera Control of Video Models","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2605.30045","title":"DualEraser: Joint Video Object and Effect Removal via Balanced Text-Mask Guidance and Decoupled Locator-Preserver","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.07508","title":"Streaming Video Generation with Streaming Force Control","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2606.20891","title":"Go-with-the-Track: Video Compositing and Motion Control with Point Tracking","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2606.24829","title":"GeoT2V-Bench: Benchmarking 3D Consistency in Text-to-Video Models via 3D Reconstruction","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2606.27192","title":"LISA: Likelihood Score Alignment for Visual-condition Controllable Generation","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2607.02317","title":"NEvo: Neural-Guided Evolutionary Video Synthesis for Dynamic Visual Selectivity","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.09091","title":"Beyond Time Shifts: Adapting Omni-LLM as a Reference-Free Evaluator for Generative Audio-Visual Models","created":"2026-07-10","cited_by_count":1,"area":null},{"id":"2607.13527","title":"VGIF-Score: Interpretable and Diagnostic Evaluation of Spatio-Temporal Instruction Following in Video Generation","created":"2026-07-15","cited_by_count":1,"area":null},{"id":"2607.22830","title":"ID-V2V: Identity-Preserving Video Restylization","created":"2026-07-24","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":"2608.04224","title":"OmniVR: Audio-Video Conditional Generation for Archival Footage Restoration","created":"2026-08-04","cited_by_count":1,"area":null},{"id":"2608.12107","title":"Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars","created":"2026-08-12","cited_by_count":1,"area":null},{"id":"2608.13602","title":"Omni-LiveAvatar: Minute-Level Real-Time Streaming Joint Audio-Video Avatar Generation","created":"2026-08-07","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":"2608.15522","title":"Efficient Audio-Visual Generation via Synchrony-Aware Cross-Modal Sparse Attention","created":"2026-08-16","cited_by_count":1,"area":null},{"id":"2608.15690","title":"Adding Voice Cloning to Text-to-Audio-Video Models with a Single Zero-Initialised Layer","created":"2026-08-16","cited_by_count":1,"area":null},{"id":"2608.17426","title":"SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation","created":"2026-08-18","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":"2609.30221","title":"WanPE: Towards Cinematic Prompt Enhancement for Modern Text-to-Video Generation","created":"2026-09-24","cited_by_count":1,"area":null},{"id":"2609.30770","title":"NavGen: Visual Generative Models as a Scalable Data Engine for Embodied 3D Navigation","created":"2026-09-25","cited_by_count":1,"area":null},{"id":"2609.37732","title":"The Camera Inside the Editor: Reading the Implicit Camera of Image Editors with Painted Calibration Patterns","created":"2026-09-29","cited_by_count":1,"area":null},{"id":"2610.01499","title":"VTR-Bench: A Systematic Benchmark for Evaluating Visual Text Rendering in Video Generation","created":"2026-10-01","cited_by_count":1,"area":null},{"id":"2603.09084","title":"SyncEdit: Rethinking Lip Synchronization as Editing with Audio-Driven Diffusion Models","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2604.01654","title":"Moir\\'e Video Authentication: A Physical Signature Against AI Video Generation","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.09057","title":"Tora3: Trajectory-Guided Audio-Video Generation with Physical Coherence","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2604.10385","title":"GTASA: Ground Truth Annotations for Spatiotemporal Analysis, Evaluation and Training of Video Models","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2604.16503","title":"Motif-Video 2B: Technical Report","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.06356","title":"SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.14843","title":"MechVerse: Evaluating Physical Motion Consistency in Video Generation Models","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.15307","title":"Sound Sparks Motion: Audio and Text Tuning for Video Editing","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.01362","title":"AlbedoEdit: Unified Instance-Level Video Editing with Albedo Guidance","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2606.02441","title":"Spatial-Temporal Decoupled Reference Conditioning for Identity-Preserving Text-to-Video Generation","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.07891","title":"C3VD-DEFCOL: A Deformable Colonoscopy Dataset with Time-Resolved 3D Ground Truth and Realistic Appearance","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.19325","title":"Reference-Driven Multi-Speaker Audio Scene Generation from In-the-Wild Priors","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2606.29473","title":"MAVIN: Multi-Shot Audio-Visual Generation with Customized Narrative Control","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2607.04553","title":"Lights, Camera, Carbon: Architectural Scaling Laws for Video Generation Energy Consumption","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2607.17985","title":"Keyframe-Anchored Identity Preservation for Sequential-Action Video Generation","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2607.23855","title":"OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2607.24359","title":"TaoMate: Anchor-Guided Memory Bridging Evolving and Reference States for Real-Time Audio-Video Digital Human Generation","created":"2026-07-27","cited_by_count":0,"area":null},{"id":"2608.03999","title":"Agogic: Performance-Timed Music Tokens for LLM-Native Text-to-Symbolic-Music Generation","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.05648","title":"Vorch-IR: Long-Form Unified Multimodal Identity Replacement Video Generation","created":"2026-08-06","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":"2608.11752","title":"UniSwap: Streaming Audio-Visual Identity Swapping for Talking Videos","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.16154","title":"KeyID: Decoupled Drafting and Keyframe Editing for Identity-Preserving Video Generation","created":"2026-08-17","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":"2608.24674","title":"TurboT2VA: Fast Large-Scale Text-to-Video-Audio Generation via Score-Regularized Consistency Distillation","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2608.26535","title":"Multi2AV-Safety: Benchmarking Safety in Multimodal-to-Audio-Video Generation","created":"2026-08-27","cited_by_count":0,"area":null}],"next_cursor":"100"}