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 In-Context Visual Contrastive Optimization (IC-VCO) to rigorously mitigate multimodal hallucinations in Vision-Language Models by optimizing contrastive learning within a shared mul…

The paper introduces Partial Information Decomposition (PID) to quantitatively separate unique, redundant, and synergistic contributions of different modalities (e.g., vision, language) in multimodal…

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 introduces CERA, a novel contrastive retrieval framework that improves RAG factuality and interpretability by using subjectivity-based hard negative selection and an auxiliary attention alig…

Echo is a joint-embedding predictive architecture that uses a single, pretrained ViT encoder to simultaneously perform speaker diarization, speech recognition, and dynamic source separation in a share…

PolySpeech-100 introduces a massive, multi-lingual benchmark covering 110 linguistic variants to rigorously test Speech-LLMs, demonstrating that open-source models struggle with low-resource languages…

The paper demonstrates that audio-language models often ignore conflicting audio evidence in favor of text, and proposes a training-free decoding rule, GACL, that significantly improves faithfulness b…

The paper proposes Reasoning-Conditioned Direct Preference Optimization (RC-DPO) to effectively mitigate hallucinations in multimodal large reasoning models by explicitly conditioning the preference o…

UniAudio-Token is a framework that enhances existing semantic speech tokenizers with general audio perception, allowing them to handle diverse audio types while maintaining high-fidelity speech capabi…