collaborators

5 papers

eess.AS2025

Enhancing Speech Large Language Models with Prompt-Aware Mixture of Audio Encoders

Weiqiao Shan, Yuang Li, Yuhao Zhang +9

Connecting audio encoders with large language models (LLMs) allows the LLM to perform various audio understanding tasks, such as automatic speech recognition (ASR) and audio captio…

cs.CL2025

Why Not Transform Chat Large Language Models to Non-English?

Xiang Geng, Ming Zhu, Jiahuan Li +14

The scarcity of non-English data limits the development of non-English large language models (LLMs). Transforming English-centric LLMs to non-English has been identified as an effe…

cs.CL2025

Adapting Large Language Models to Log Analysis with Interpretable Domain Knowledge

Yuhe Ji, Yilun Liu, Feiyu Yao +10

Log analysis represents a critical sub-domain within AI applications that facilitates automatic approaches to fault and error management of large-scaled software systems, saving la…

cs.CL2025

DoCIA: An Online Document-Level Context Incorporation Agent for Speech Translation

Xinglin Lyu, Wei Tang, Yuang Li +7

Document-level context is crucial for handling discourse challenges in text-to-text document-level machine translation (MT). Despite the increased discourse challenges introduced b…

eess.AS2025

Optimizing Speech Multi-View Feature Fusion through Conditional Computation

Weiqiao Shan, Yuhao Zhang, Yuchen Han +7

Recent advancements have highlighted the efficacy of self-supervised learning (SSL) features in various speech-related tasks, providing lightweight and versatile multi-view speech…