{"total":18,"rows":[{"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":"2601.22143","title":"JUST-DUB-IT: Video Dubbing via Joint Audio-Visual Diffusion","created":"2026-01-29","cited_by_count":7,"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":"2512.00336","title":"MVAD: A Benchmark Dataset for Multimodal AI-Generated Video-Audio Detection","created":"2025-11-29","cited_by_count":3,"area":null},{"id":"2605.01638","title":"Omni-Fake: Benchmarking Unified Multimodal Social Media Deepfake Detection","created":"2026-05-02","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":"2605.04045","title":"Audio-Visual Intelligence in Large Foundation Models","created":"2026-05-05","cited_by_count":2,"area":null},{"id":"2510.22575","title":"MELDAE: A Framework for Micro-Expression Spotting, Detection, and Automatic Evaluation in In-the-Wild Conversational Scenes","created":"2025-10-26","cited_by_count":1,"area":null},{"id":"2603.14794","title":"Face-to-Face: A Video Dataset for Multi-Person Interaction Modeling","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2604.17211","title":"EmbodiedHead: Real-Time Listening and Speaking Avatar for Conversational Agents","created":"2026-04-19","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":"2602.03570","title":"Asymmetric Hierarchical Anchoring for Robust Audio-Visual Cross-Modal Generalization","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2604.23692","title":"Personalizing Causal Audio-Driven Facial Motion via Dynamic Multi-modal Retrieval","created":"2026-04-26","cited_by_count":0,"area":null},{"id":"2604.27918","title":"Generate Your Talking Avatar from Video Reference","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.02948","title":"AsymTalker: Identity-Consistent Long-Term Talking Head Generation via Asymmetric Distillation","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.24176","title":"Loki: Representation over Architecture for Diffusion-Based Portrait Animation","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2609.22264","title":"Hi-Singers: A Comprehensive High-Quality Dataset for Expressive Audio-Driven Singing Head Synthesis","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.29225","title":"ComplexSync: High-Fidelity and Real-Time Lip Sync in Complex Scenarios","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}