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…

This study demonstrates that the tone of a prompt significantly affects the accuracy of various LLMs, requiring users to exercise caution regarding tone-robust reliability.

The paper introduces three new Korean speech benchmarks (KVoiceBench, KOpenAudioBench, and KMMAU) to evaluate SpeechLMs, demonstrating that English-centric evaluation fails to capture performance gaps…

MOSS-Audio is a unified audio-language model designed for comprehensive understanding of speech, environmental sounds, and music, achieving strong performance across various audio-grounded tasks.

The paper proposes an inference-time activation steering framework, utilizing orthogonalization, to achieve fine-grained, deterministic control over discrete musical attributes like Pitch and Duration…