profile picture

Ya-Qi Yu

(Archie Yu)
余亚奇
Technical Expert
Huawei Technologies
Shanghai

Education

M.Sc. in Computer Science and Technology

Nanjing University
2018 - 2021

B.Sc. in Computer Science and Technology

Nanjing University
2014 - 2018

Languages

  • Chinese (Native)
  • English

Interests

Biography

I am a Technical Expert at Huawei Technologies, where I lead the multimodal foundation model post-training team for Celia. Our current research focuses on:

  • Reinforcement Learning and On-Policy Distillation
  • Streaming, Omni, and Vision-Language Models
  • Multi-Agent Systems

I received my M.Sc. in Computer Science and Technology from Nanjing University in 2021, where I was a member of the LAMDA group, advised by Professor Wu-Jun Li. I earned my B.Sc. from the same department in 2018 and graduated from Yali Middle School in 2014.

Publications

Google Scholar Profile

  • Reinforcement Learning with Robust Rubric Rewards
    • Ya-Qi Yu, Hao Wang, Fangyu Hong, Xiangyang Qu, Gaojie Wu, Qiaoyu Luo, Nuo Xu, Huixin Wang, Wuheng Xu, Yongxin Liao, Zihao Chen, Haonan Li, Ziming Li, Dezhi Peng, Minghui Liao, Jihao Wu, Haoyu Ren, Dandan Tu
    Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP), Budapest, Hungary, 2026
  • Visual preference optimization with rubric rewards
    • Ya-Qi Yu, Fangyu Hong, Xiangyang Qu, Hao Wang, Gaojie Wu, Qiaoyu Luo, Nuo Xu, Huixin Wang, Wuheng Xu, Yongxin Liao, Zihao Chen, Haonan Li, Ziming Li, Dezhi Peng, Minghui Liao, Jihao Wu, Haoyu Ren, Dandan Tu
    Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP), Budapest, Hungary, 2026
  • UniCAR-RL: Seeing Better before Thinking Deeper in Visual Mathematics
    • Yuzhe Li, Hao Yan, Hao Wang, Xingchen Liu, Ya-Qi Yu, Jihao Wu, Minghui Liao, Wei Chen, Yuliang Liu
    Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP), Budapest, Hungary, 2026
  • UI-hawk: Unleashing the Screen Stream Understanding for Mobile GUI Agents
    • Jiwen Zhang, Ya-Qi Yu, Minghui Liao, Wentao Li, Jihao Wu, Zhongyu Wei
    Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), Suzhou, China, 2025
  • TextHawk2: A Large Vision-Language Model Excels in Bilingual OCR and Grounding with 16x Fewer Tokens
    • Ya-Qi Yu, Minghui Liao, Jiwen Zhang, Jihao Wu
    Technical Report, 2024
  • Cross-Lingual Text-Rich Visual Comprehension: An Information Theory Perspective
    • Xinmiao Yu, Xiaocheng Feng, Yun Li, Minghui Liao, Ya-Qi Yu, Xiachong Feng, Weihong Zhong, Ruihan Chen, Mengkang Hu, Jihao Wu, Dandan Tu, Duyu Tang, Bing Qin
    Proceedings of the 39th Annual AAAI Conference on Artificial Intelligence (AAAI), Pennsylvania, USA, 2025
  • TextHawk: Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models
    • Ya-Qi Yu, Minghui Liao, Jihao Wu, Yongxin Liao, Xiaoyu Zheng and Wei Zeng
    Under Review, 2024
  • CAM: Context-Aware Masking for Robust Speaker Verification
    • Ya-Qi Yu, Siqi Zheng, Hongbin Suo, Yun Lei and Wu-Jun Li
    Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, Canada, 2021
  • Densely Connected Time Delay Neural Network for Speaker Verification
    • Ya-Qi Yu and Wu-Jun Li
    Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH), Shanghai, China, 2020
  • Deep Hashing for Speaker Identification and Retrieval
    • Lei Fan, Qing-Yuan Jiang, Ya-Qi Yu and Wu-Jun Li
    Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH), Graz, Austria, 2019
  • Ensemble Additive Margin Softmax for Speaker Verification
    • Ya-Qi Yu, Lei Fan and Wu-Jun Li
    Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK, 2019

    Experiences

    Technical Expert

    Augest 2026 - Now
    Huawei Technologies, Shanghai, China

    Chief Engineer

    October 2024 - Augest 2026
    Huawei Technologies, Shanghai, China

    Senior Engineer

    July 2021 - October 2024
    Huawei Technologies, Shanghai, China

    Algorithm Engineer Intern

    June 2020 - August 2020
    Speech Lab, Alibaba DAMO Academy, Alibaba Group, Hangzhou, China

    Work at speaker recognition group:

    • Deep hashing-based large-scale speaker retrieval
    • Noise robust speaker verification (Paper accpeted by ICASSP 2021)

    Awards & Honors

    Graduation with Distinction
    April 2021
    Nanjing University, Nanjing, China
    Excellent Graduate Student
    December 2020
    Nanjing University, Nanjing, China
    Excellence Scholarship
    November 2020
    Nanjing University, Nanjing, China
    HUAWEI Scholarship
    December 2019
    Nanjing University, Nanjing, China
    Speaker Verification Competition (2/345, ¥50,000)
    October 2018
    Tongdun, Hangzhou, China

    Projects

    R1-Vision - Let's first take a look at the image
    TextHawk - Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models
    D-TDNN - PyTorch implementation of densely connected time delay neural networks
    KaldiFeat - A light-weight Python library for computing Kaldi-style acoustic features based on NumPy

    Skills

    PyTorch

    Kaldi

    Python

    C & C++