{"total":18,"rows":[{"id":"2411.17698","title":"Video-Guided Foley Sound Generation with Multimodal Controls","created":"2024-11-26","cited_by_count":49,"area":null},{"id":"2411.05679","title":"Tell What You Hear From What You See -- Video to Audio Generation Through Text","created":"2024-11-08","cited_by_count":34,"area":null},{"id":"2503.10522","title":"AudioX: A Unified Framework for Anything-to-Audio Generation","created":"2025-03-13","cited_by_count":27,"area":null},{"id":"2505.01237","title":"CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained Alignment","created":"2025-05-02","cited_by_count":16,"area":null},{"id":"2504.10746","title":"Hearing Anywhere in Any Environment","created":"2025-04-14","cited_by_count":8,"area":null},{"id":"2508.08237","title":"VGGSounder: Audio-Visual Evaluations for Foundation Models","created":"2025-08-11","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":"2509.23727","title":"AudioMoG: Guiding Audio Generation with Mixture-of-Guidance","created":"2025-09-28","cited_by_count":5,"area":null},{"id":"2503.09205","title":"Quality Over Quantity? LLM-Based Curation for a Data-Efficient Audio-Video Foundation Model","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2509.26604","title":"Video Object Segmentation-Aware Audio Generation","created":"2025-09-30","cited_by_count":2,"area":null},{"id":"2603.11042","title":"V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2605.30339","title":"Benchmarking Single-Factor Physical Video-to-Audio Generation","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2603.08126","title":"Foley-Flow: Coordinated Video-to-Audio Generation with Masked Audio-Visual Alignment and Dynamic Conditional Flows","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2608.04902","title":"Visual Representation Matters: Exploiting Temporal Differences in Video-to-Audio Generation","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2601.17085","title":"Recovering Performance in Speech Emotion Recognition from Discrete Tokens via Multi-Layer Fusion and Paralinguistic Feature Integration","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2601.19606","title":"GMS-CAVP: Improving Audio-Video Correspondence with Multi-Scale Contrastive and Generative Pretraining","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2604.08147","title":"Semantic Noise Reduction via Teacher-Guided Dual-Path Audio-Visual Representation Learning","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.27944","title":"From Talking to Singing: A New Challenge for Audio-Visual Deepfake Detection","created":"2026-05-27","cited_by_count":0,"area":null}],"next_cursor":null}