Honglin Mu

Harbin Institute of Technology · pklmu@outlook.com

I am a Ph.D. student in Computer Science and Technology at Harbin Institute of Technology, focusing on Natural Language Processing, supervised by Prof. Wanxiang Che. My expertise lies in Dialogue Assistants and Audio Processing. Currently my research interests includes LLM Agents and Evaluation. Skilled in Python, C/C++, and Java, I also have professional experience as a Test Development Engineer at Tencent Technology. Passionate about AI, I am committed to advancing the field of NLP through rigorous research and practical applications.

Currently I work as an intern in Huawei Technologies Co., Ltd. under the supervision of Dr. Yutai Hou and Dr. Yitong Li

Socialization

Publications

Conference - Improving Domain Generalization for Sound Classification with Sparse Frequency-Regularized Transformer

Honglin Mu, Wentian Xia, Wanxiang Che
ICME 2023 (Oral) | IEEE International Conference on Multimedia and Expo

July 2023

Arxiv - MixPro: Simple yet Effective Data Augmentation for Prompt-based Learning

Bohan Li, Longxu Dou, Yutai Hou, Yunlong Feng, Honglin Mu, Wanxiang Che
arXiv preprint | arXiv:2304.09402

April 2023

Projects

Huawei-HIT Joint Laboratory - Multimodal Voice Assistant Rejection Project

  • Developed models to distinguish interference (like non-targeted voice assistant speech or background noise) during continuous multi-round dialogue listening by voice assistants.
  • Responsible for building a dual-tower rejection model of voice (Wav2vec2) + text (BERT), and adopting various approaches (like data augmentation, MoE) to improve model generalization (OOD) across domains.

    • October 2021 - November 2022

    Undergraduate Thesis - Contextual Spoken Language Understanding based on Heterogeneous Graph Networks

  • Improved the contextual spoken language understanding system by using Heterogeneous Attention Networks (HAN) to jointly model the semantic information and domain transitions of dialogue, and disambiguate semantic frame parsing by explicitly modeling domain transition phenomena.
  • Experiments on the SGD dataset showed that the proposed method achieved SOTA results, leading previous best models by 2.18% in semantic frame accuracy and 1.1% in intent accuracy.
  • Explored the performance of pre-trained models in the system, achieving an improvement of 1.02% in semantic frame accuracy on top of the proposed model.
  • Supervised by Prof. Libo Qin.

    • June 2021

    Tencent Technology (Shenzhen) Co., Ltd. - Software Defect Prediction Plugin

  • Predict the vulnerability risk on the code repository based on information like code hotspots and developer count using machine learning methods.

    • June 2020 - August 2020

    Education

    Harbin Institute of Technology

    Ph.D. in Computer Science and Technology
    Research Center for Social Computing and Information Retrieval

    Supervised by Prof. Wanxiang Che

    2021 - Present

    National University of Singapore

    Visiting Student
    NUS Summer Workshop project

    Studied computer vision and deep learning, and engaged in related Raspberry Pi programming

    July 2019

    Harbin Institute of Technology

    Bachelor's in Computer Science and Technology
    School of Computing

    Honors/Awards: Excellent League Member at the University Level 2018, Second Class People's Scholarship 2019

    2017 - 2021

    Experience

    Huawei Technologies Co., Ltd.

    Intern

    Work on context compression and evaluation of Tool-assisted LLMs. Supervised by Dr. Yutai Hou and Dr. Yitong Li.

    May 2023 - Present

    Huozi LLM Project

    Developer

    Responsible for the front-end of the Huozi(活字) LLM, a Chinese LLM developed by HIT-SCIR.

    April 2023 - Present

    Tencent Technology (Shenzhen) Co., Ltd.

    Intern

    Participated in code vulnerability prediction DevOps Plugin development.

    July 2020 - September 2020

    Harbin Institute of Technology ACM Training Team

    Team Member

    As a member (and small team leader) of the HIT ACM Training Team, participated in the ACM-ICPC Asia Regional Contest 2018 in Zhengzhou and Beijing (Silver Medal).

    July 2018 - July 2019

    Certifications

    CCF Outstanding College Student Award

    China Computer Federation Outstanding College Student Award 2020

    ACM-ICPC Asia Regional

    ACM-ICPC Asia Regional Contest 2018 Beijing (Silver Medal)

    Skills

    Deep Learning
    • PyTorch
    • Megatron
    • Hugging Face
    • Fairseq
    Languages, Operating Systems & Tools
    • Python
    • C++
    • Java
    • javascript
    • LaTeX
    • git
    • linux
    • Docker
    Nifty tech tag lists from Wouter Beeftink