Xuanjun Chen

This work training a LALM with reinforcement learning to reason over its own speech output generates a draft speech as a form of audio-token reasoning, critiques its own generation by reflecting on the acoustic realization in text, and produces a refined version conditioned on both the first-pass speech and the critique.

Targeting only the gaps in information, GDP-RAG achieves unprecedented accuracy in multi-hop question answering while slashing computational costs.

High-frequency details, often discarded, are actually crucial for spotting singing voice deepfakes, enabling significantly better detection.