Wenbo (Gordon) Hu

whu at cs dot ucla dot edu

Hi! I am Wenbo. I'm a graduate student at University of California, Los Angeles Computer Science Program, working with Prof. Nanyun Peng and Prof. Kai-Wei Chang at UCLA. Before that, I worked at Machine Learning, Perception, and Cognition Lab (mlPC) advised by Prof. Zhuowen Tu. I graduated from University of California, San Diego majoring Data Science in March 2023.

My primary research interest lies in Multimodal Machine Learning and Vision-Language Models. Particularly, I have worked on 2D and 3D vision-language models in visual understanding and embodied tasks, and evaluation benchmarks for multimodal models.

CV  /  GitHub  /  Google Scholar /  LinkedIn  /  Email  /  Twitter (X)


News
  • 10/2024: We release MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models.
  • 09/2024: MQT-LLaVA: Matryoshka Query Transformer for Large Vision-Language Models is accepted at NeurIPS 2024!
  • 05/2024: Released Matryoshka Query Transformer for Large Vision-Language Models, check our new work here.
  • 05/2024: VALOR-EVAL is accepted by ACL 2024 Findings!
  • 12/2023: BLIVA is accepted by AAAI 2024!
  • 10/2023: Joined PLUS lab and UCLA NLP Group at UCLA.
  • 04/2023: Joined Machine Learning, Perception, and Cognition Lab (mlPC) at UCSD.
  • 02/2022: Joined Hao Su Lab at UCSD for computer vision and robotics research.

  • Publications

    Loading...

    Work Experience
    Synthesis Electronic Technology        06/2021 - 08/2021
    Research Intern at Computer Vision Group
    Inspur Groups        07/2020 - 09/2020
    Software Engineering Intern

    Teaching Experience
    Teaching Assistant: CSE151A: Intro to Machine Learning
    UCSD (Winter 2023)

    Service
    Reviewer for ICLR, NeurIPS, AAAI, EMNLP, ACL Rolling Review, and IEEE Transactions on Multimedia.



    Pageviews


    Inspired by this and this.