Biblio Discovery — Demo Discovery Service

3 hasil untuk "Cheng, Xize"

Menampilkan 1–3 · 0,33 detik · RSS

  1. Preprint Teks lengkap

    Character Beyond Speech: Leveraging Role-Playing Evaluation in Audio Large Language Models via Reinforcement Learning

    Fu, Dongjie; Feng, Fangming; Cheng, Xize dkk.

    arXiv · 2026 · Inggris · arXiv

    The rapid evolution of multimodal large models has revolutionized the simulation of diverse characters in speech dialogue systems, enabling a novel interactive paradigm. Character attributes are manifested not only in textual responses but also through vocal features, as speech conveys rich…

  2. Preprint Teks lengkap

    MARS-Sep: Multimodal-Aligned Reinforced Sound Separation

    Zhang, Zihan; Cheng, Xize; Jiang, Zhennan dkk.

    arXiv · 2025 · Inggris · arXiv

    Universal sound separation faces a fundamental misalignment: models optimized for low-level signal metrics often produce semantically contaminated outputs, failing to suppress perceptually salient interference from acoustically similar sources. We introduce a preference alignment perspective…

  3. Preprint Teks lengkap

    Modeling and Benchmarking Spoken Dialogue Rewards with Modality and Colloquialness

    Lu, Jingyu; Wang, Yuhan; Zhuo, Fan dkk.

    arXiv · 2026 · Inggris · arXiv

    The rapid evolution of end-to-end spoken dialogue systems demands transcending mere textual semantics to incorporate paralinguistic nuances and the spontaneous nature of human conversation. However, current methods struggle with two critical gaps: the modality gap, involving prosody and emotion…