CV

Chenhui Gou's Curriculum Vitae.

Contact Information

Name Chenhui Gou
Professional Title PhD Student
Email Chenhui.Gou@monash.edu

Professional Summary

PhD student at Monash University researching AI Agents, LLMs, VLMs, and Generative AI. Also working with ByteDance Seed Edge.

Experience

  • 2025 -

    Research Intern
    ByteDance Seed Edge
    Research on Agentic and Self-Evolving AI.
  • 2024 - 2025

    Research Intern
    ByteDance Seed VLM-BAGEL Group
    Supervised by Haoqi Fan
    • Researched on Unified Model BAGEL-series
    • Researching on VLM
  • 2023 - 2024

    Research Intern
    Vision-CAIR Group, KAUST
    Supervised by Deyao Zhu and Mohamed Elhoseiny (MiniGPT Group)
    • Researched on Large Language-based Multi-modality Models
    • Researching on Long Video Understanding
  • 2022 - 2023

    ShenZhen, China

    Research Intern
    Sensetime Inc
    • Researched on Partial Person Re-Identification
    • Developed novel transformer-based model for Partial Person Re-Identification
  • 2022 - 2023

    Canberra, Australia

    Research Project
    Australian National University
    Supervised by Dr. Liang Zheng
    • Researched plugable general performance improvement module for semantic segmentation
  • 2022 - 2022

    Sydney, Australia

    Research Project
    University of Technology Sydney
    Supervised by Dr. Wenguang Wang
    • Researched transformation equivalent and deformable transformer
  • 2021 - 2022

    Beijing, China

    Research Intern
    Baidu, Vision Technology Department
    Supervised by Wuqi Man and Jiang Wang (leader: Jingdong Wang)
    • Published RTFormer at NeurIPS 2022 (Spotlight), achieving SOTA accuracy-speed trade-off
    • Researched fast and efficient Transformer and hybrid CNN-Transformer models
  • 2021 - 2021

    Beijing, China

    Research Intern
    NIO Inc, Autonomous Driving
    Supervised by Ziwei Chen (leader: Shaoqing Ren)
    • Developed end-to-end car lane detection method based on Transformer
    • Increased model performance using 2x input image without affecting model size and speed
  • 2020 - 2021

    Beijing, China

    Research Intern
    Aibee Inc
    Supervised by JiangFan Deng, Feng Zhou
    • Researched on video completion and object removal
    • Optimised code running time from 0.25 fps to 2 fps, deployed in VR indoor map system

Education

  • 2023 - 2027

    Melbourne, Australia

    Doctor of Philosophy
    Monash University
    Data Science and AI
    • Supervisors: Hamid Rezatofighi, Jianfei Cai
  • 2020 - 2023

    Canberra, Australia

    Master
    Australian National University
    Machine Learning and Computer Vision
    • With COMMENDATION (Best scale)
  • 2016 - 2020

    Beijing, China

    B.E.
    Beijing University of Posts and Telecommunications (BUPT)
    Telecommunications Engineering with Management
  • 2016 - 2020

    London, United Kingdom

    Bachelor of Science with Honours
    Queen Mary University of London (QMUL)
    Engineering
    • First Class Honours

Academic Services

Skills

Research Areas (Expert): AI Agents, Large Language Models, Vision-Language Models, Generative AI, Semantic Segmentation, Video Understanding
Deep Learning (Expert): Transformers, CNNs, Diffusion Models, Multimodal Models, Reinforcement Learning

Languages

Chinese : Native speaker
English : Fluent

Interests

AI Research: Agentic AI, Self-Evolving AI, Unified Multimodal Models, Video Understanding, Efficient Models