ThinkOmni: A Reasoning-Driven Omni-Modal LLM Framework for Audio Forgery Detection and Localization
This work proposes ThinkOmni, a reasoning-driven omni-modal large language model that jointly performs explicit forensic reasoning, spoofing detection, and temporal manipulation localization and proposes Forensic-Consistent Multi-task Loss (FCML), which combines weighted cross-entropy with an adaptive localization loss...