Yan Zhou | 周䶮

I am a third-year Ph.D. student at Institute of Computing Technology, Chinese Academy of Sciences (ICT/CAS), advised by Prof. Yang Feng at ICT Natural Language Processing (ICTNLP) group.

Email   |   Github   |   Google Scholar

profile photo
Research

My research interests focus on Speech Language Models (Speech LLMs). I am actively exploring how to leverage Large Language Models (LLMs) to enhance instruction-following capabilities and emotional expressiveness in speech language models. Prior to this, I developed a solid research background in neural machine translation, speech-text translation and speech-to-speech translation, which provides a core foundation for my ongoing explorations in cross-modal speech processing and speech generation tasks.

News

[2026/4] Two papers, CSLM (1st author) and FreezeEmpath (2nd author), are accepted to ACL 2026 Findings.

[2025/7] Our paper LLaMA-Omni 2 is accepted to ACL 2025 main conference. Read our paper.

[2025/6] Our preprint Stream-Omni is released. Check our paper .

[2024/11] Our preprint Bayling 2 is released. Check our paper.

[2024/9] Our speech-language model LLaMA-Omni is released and then accepted to ICLR 2025. Check our paper, code, and model.

[2024/5] A paper about speech-to-speech translation that I participated in is accepted to ACL2024. Read our paper.

[2023/9] A paper about speech-to-speech translation (DASpeech) that I participated in is accepted to NeurIPS2023. Read our paper.

[2023/9] I start my Ph.D. life at University of Chinese Academy of Sciences (UCAS), and ICT/CAS.

[2023/6] I obtain my B.E. degree from Tsinghua University.

[2023/6] Our LLM BayLing (百聆) is released. BayLing is an instruction-following LLM with advanced language alignment and multi-turn interaction capability. Read our paper.

[2023/5] A long paper about speech translation (CMOT) is accepted to ACL 2023 main conference.

Publications

FreezeEmpath: Efficient Training for Empathetic Spoken Chatbots with Frozen LLMs
Yun Hong, Yan Zhou, Yang Feng
Findings of ACL 2026
Paper / Code

Efficient Training for Cross-lingual Speech Language Models
Yan Zhou, Qingkai Fang, Yun Hong, Yang Feng
Findings of ACL 2026
Paper / Code / Model

LLaMA-Omni 2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis
Qingkai Fang, Yan Zhou, Shoutao Guo, Shaolei Zhang, Yang Feng
ACL 2025
Paper / Code / Model

LLaMA-Omni: Seamless Speech Interaction with Large Language Models
Qingkai Fang, Shoutao Guo, Yan Zhou, Zhengrui Ma, Shaolei Zhang, Yang Feng
ICLR 2025
Paper / Code / Model

CTC-based Non-autoregressive Textless Speech-to-Speech Translation
Qingkai Fang, Zhengrui Ma, Yan Zhou, Min Zhang, Yang Feng
Findings of ACL 2024
Paper / Code

DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation
Qingkai Fang, Yan Zhou, Yang Feng
NeurIPS 2023
Paper / Code

CMOT: Cross-modal Mixup via Optimal Transport for Speech Translation
Yan Zhou, Qingkai Fang, Yang Feng
ACL 2023
Paper / Code
Preprints

Stream-Omni: Simultaneous Multimodal Interactions with Large Language-Vision-Speech Model
Shaolei Zhang, Shoutao Guo, Qingkai Fang, Yan Zhou, Yang Feng

Paper / Code / Model

BayLing 2: A Multilingual Large Language Model with Efficient Language Alignment
Shaolei Zhang, Kehao Zhang, Qingkai Fang, Shoutao Guo, Yan Zhou, Xiaodong Liu, Yang Feng

Paper

BayLing: Bridging Cross-lingual Alignment and Instruction Following through Interactive Translation for Large Language Models
Shaolei Zhang, Qingkai Fang, Zhuocheng Zhang, Zhengrui Ma, Yan Zhou, Langlin Huang, Mengyu Bu, Shangtong Gui, Yunji Chen, Xilin Chen, Yang Feng

Paper / Code
Experience
Tsinghua University , China
2019.08 - 2023.6
Undergraduate Student
Institute of Computing Technology, Chinese Academy of Sciences , China
2023.09 - now
Ph.D. student
Selected Awards

  • 2019: Second-class scholarship for freshmen, Tsinghua University

    		•



    Updated at April 2026