Efficient Streaming Audio-Visual Target Speaker Extraction for Real-World Acoustic Scenes Paper • 2610.32749 • Published 28 days ago • 27
Harnessing CLIP and DINO: An Uncertainty-Aware Cascaded Fusion Network for Generalizable Deepfake Image Detection Paper • 2609.07670 • Published Sep 7 • 12
Multi-Agent Forensic Reasoning for Generalizable Deepfake Video Detection Paper • 2608.06865 • Published Aug 7 • 11
Efficient Audio-Visual Speech Separation with Discrete Lip Semantics and Multi-Scale Global-Local Attention Paper • 2509.23610 • Published Sep 28, 2025 • 15