Xueyao Zhang

Covert AUV missions can achieve up to 30% greater task efficiency by leveraging a new framework that optimizes the value of sensed information under communication constraints.

Qwen-Music outperforms leading systems in musicality and audio quality, achieving state-of-the-art results across 13 of 16 metrics while generating songs from text and reinterpreting existing tracks.

Forget complex disentanglement architectures or low-quality synthetic targets: MimicLM achieves superior voice imitation by cleverly using synthetic speech as the *source* and real speech as the *target* in a pseudo-parallel training setup.

Speech LLMs struggle not just from a simple input distribution shift, but from the challenge of condensing redundant acoustic information into stable, high-level semantic representations.