5 papers
UniAE-MoE: A Unified Audio Encoder via Mixture of Experts
Shengbo Cai, Zhisheng Zhang, Zichao Nie +3
Large Audio Language Models (LALMs) rely on effective audio encoders for multi-task performance. We introduce UniAE-MoE, a unified audio encoder designed to model cross-domain audi…
Thinking in Depth, Speaking Directly: Recurrent Latent Reasoning for Paralinguistically Grounded Spoken Dialogue
Shengbo Cai, Yuxiang Wang, Jingran Xie +5
Empathetic spoken dialogue requires models to use both what is said and how it is said to decide how to respond. Explicit CoT can improve paralinguistic perception and make acousti…
ParaBridge: Bridging Paralinguistic Perception and Dialogue Behavior in Speech Language Models
Yuxiang Wang, Qinke Ni, Shengbo Cai +3
Speech carries more information than just words: a child's voice, a fearful tone, or a noisy background should all lead a sufficiently competent spoken-dialogue assistant to differ…
WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents
Sicheng Fan, Qingyun Shi, Shengze Xu +5
Current paradigms for training GUI agents are fundamentally limited by a reliance on either unsafe, non-reproducible live web interactions or costly, scarce human-crafted data and…
UniSRCodec: Unified and Low-Bitrate Single Codebook Codec with Sub-Band Reconstruction
Zhisheng Zhang, Xiang Li, Yixuan Zhou +4
Neural Audio Codecs (NACs) can reduce transmission overhead by performing compact compression and reconstruction, which also aim to bridge the gap between continuous and discrete s…