Yuan-Hong Liao

University of Toronto, Vector Institute

prof_pic.jpg

Toronto, Canada

:star: I’ll be on the job market for an industry role starting early 2025. If my research aligns with your needs, please feel free to reach out via email.

:sunny: I will be in Miami for EMNLP’24. Drop me an email if you’d like to have a chat or grad a coffee :coffee:

I am a final-year Ph.D. student at the University of Toronto and Vector Institute. I am fortunate to be supervised by Prof. Sanja Fidler. Previously, I was an CV/ML scientist intern at NVIDIA Toronto AI lab in 2022 - 2023 and Amazon Astros team in 2024.

I am interested in developing and analyzing large Vision-Language Models. Specifically, I focus on the application of building scalable & efficient data labeling pipeline. Check my papers in

Previous experiences Prior to my Ph.D., I was a visiting student at Vector Institute and USC in 2018 and 2017, respectively. I was fortunate to start by AI research at National Tsing Hua University, supervised by Prof. Min Sun.

news

Sep 20, 2024 :star: Our paper Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Models is accepted to EMNLP 2024
Jul 22, 2024 :star: Start my internship at Amazon Astro team at Seattle!
Apr 09, 2024 :star: New preprint out on arXiv Can Feedback Enhance Semantic Grounding in Large Vision-Language Models?!
Jan 15, 2024 :star: Our paper Transferring Labels to Solve Annotation Mismatches Across Object Detection Datasets is accepted to ICLR 2024
Oct 01, 2023 :star: Our paper Bridging the Sim2Real gap with CARE: Supervised Detection Adaptation with Conditional Alignment and Reweighting is accepted to TMLR 2023

selected publications

  1. spatial_prompt.pdf
    Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Models
    Yuan-Hong Liao, Rafid Mahmood , Sanja Fidler , and David Acuna
    In The 2024 Conference on Empirical Methods in Natural Language Processing , 2024
  2. vlm_feedback.png
    Can Feedback Enhance Semantic Grounding in Large Vision-Language Models?
    Yuan-Hong Liao, Rafid Mahmood , Sanja Fidler , and David Acuna
    2024
  3. label_transfer.png
    Translating Labels to Solve Annotation Mismatches Across Object Detection Datasets
    Yuan-Hong Liao, David Acuna , Rafid Mahmood , James Lucas , Viraj Uday Prabhu , and Sanja Fidler
    In The Twelfth International Conference on Learning Representations , 2024
  4. good_practices.png
    Towards Good Practices for Efficiently Annotating Large-Scale Image Classification Datasets
    Yuan-Hong Liao, Amlan Kar , and Sanja Fidler
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , Jun 2021