AnchorSteer introduces a framework that achieves high-fidelity, structure-preserving music editing by decoupling semantic concept injection from structural constraints.

LoSATok proposes a low-dimensional semantic-acoustic tokenizer that efficiently compresses high-dimensional audio features into a compact latent space, significantly improving the performance and effi…

The paper proposes a novel multimodal framework for session-based music recommendation that jointly models audio, lyric, and semantic content signals within a unified LLM-based sequential reasoning sy…

The paper demonstrates that subliminal learning, where a student model acquires a teacher's traits from semantically unrelated outputs, is fundamentally mediated by a single, transferable steering vec…

The paper introduces MusTBENCH, a new benchmark, and MusT, an optimization recipe, to rigorously test and improve the ability of Large Audio-Language Models (LALMs) to accurately ground their musical…