{"total":32,"rows":[{"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":"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":"2605.30073","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":"2605.18467","title":"InstructAV2AV: Instruction-Guided Audio-Video Joint Editing","created":"2026-05-18","cited_by_count":5,"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":"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":"2605.04045","title":"Audio-Visual Intelligence in Large Foundation Models","created":"2026-05-05","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":"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":"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":"2603.23132","title":"InterDyad: Interactive Dyadic Speech-to-Video Generation by Querying Intermediate Visual Guidance","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"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":"2607.26818","title":"Ripple: Real-Time Streaming Audio-Video Generation With Cross-Modal Recurrent Memory","created":"2026-07-29","cited_by_count":1,"area":null},{"id":"2608.15522","title":"Efficient Audio-Visual Generation via Synchrony-Aware Cross-Modal Sparse Attention","created":"2026-08-16","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":"2604.09057","title":"Tora3: Trajectory-Guided Audio-Video Generation with Physical Coherence","created":"2026-04-10","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":"2606.29473","title":"MAVIN: Multi-Shot Audio-Visual Generation with Customized Narrative Control","created":"2026-06-28","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":"2608.31106","title":"DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.04867","title":"PRISM-Bench: An Audio-Centric Diagnostic Benchmark for Text-to-Audio-Video Generation","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.27901","title":"All modalities are equal, but video is more equal: Closing the Cross-Attention Gap in Joint Video Generation","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.29816","title":"AV-GRPO: Modality-Anchored Decoupling Diffusion Reinforcement Learning for Joint Audio-Video Generation","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.34381","title":"Joint and Cross-Modal Video-Audio Generation and Editing: A Unified Formulation and Design Taxonomy","created":"2026-09-28","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":"2610.05416","title":"Prism: Dynamic Sparse Attention for Native 2K Joint Video-Audio Generation Model Training","created":"2026-10-04","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":"2610.15512","title":"Structured Stateful Relational Scripts with a High-Quality Dataset for Multi-Shot Audio-Visual Video Generation","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}