EchoDistill:Alignment Noisy-to-Clean Self-Distillation for Robust Audio LLMs 事件

EchoDistill:Alignment Noisy-to-Clean Self-Distillation for Robust Audio LLMs arXiv:2605.23954v1 Announce Type: new Abstract: Audio Large Language Models (ALLMs) are highly vulnerable to real-world noise, which often induces severe semantic drift and hallucinations. Existing robustness methods primarily rely on waveform-level acoustic enhancement, answer-level supervision, or the internal suppression of noise representations. To address these issues, we propose echodistill, an alignment-based no