Stephanie Fu

phd student | EECS @ UC Berkeley

prof_pic.jpg

I am a PhD student at BAIR advised by Trevor Darrell.

Previously, I graduated from MIT with an MEng in computer science (advised by Phillip Isola) and bachelors degrees in computer science and music. During my undergrad, I was fortunate to work on exciting research under Bill Freeman, Yoel Fink, and Phillip Isola.

I am broadly interested in the science behind deep learning and representation learning, especially in the realm of computer vision. Most recently, I have been interested in developing and understanding models with visual intelligence.


In 2019, I co-founded TEDxMIT and helped launch the inaugural conference at MIT CSAIL. Since then, TEDxMIT has brought communities across the Greater Boston area together with three more conferences and adapted to the COVID-19 pandemic by holding a virtual event. Check out the highlight reels from past events and details about the upcoming conference here!


news

Jun 2023 We just released DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data!
Jun 2023 I will be attending UC Berkeley for my PhD in Computer Science, supported by the NSF GRFP and Chancellor’s Fellowship!
May 2023 I was offered Stanford’s Knight-Hennessy Scholarship!

selected publications

  1. DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data
    Stephanie Fu*, Netanel Tamir*, Shobhita Sundaram*, Lucy Chai, Richard Zhang, Tali Dekel, and Phillip Isola
    arXiv:2306.09344 2023
  2. Axiomatic Explanations for Visual Search, Retrieval, and Similarity Learning
    Mark Hamilton, Scott Lundberg, Lei Zhang, Stephanie Fu, and William T Freeman
    International Conference on Learning Representations (ICLR) 2021
  3. MosAIc: Finding Artistic Connections across Culture with Conditional Image Retrieval
    Mark Hamilton, Stephanie Fu, Mindren Lu, Johnny Bui, Darius Bopp, Zhenbang Chen, Felix Tran, Margaret Wang, Marina Rogers, Lei Zhang, Chris Hoder, and William T. Freeman
    In Proceedings of the NeurIPS 2020 Competition and Demonstration Track 06–12 dec 2021
  4. Digital electronics in fibres enable fabric-based machine-learning inference
    Gabriel Loke, Tural Khudiyev, Brian Wang, Stephanie Fu, Syamantak Payra, Yorai Shaoul, Johnny Fung, Ioannis Chatziveroglou, Pin-Wen Chou, Itamar Chinn, Wei Yan, Anna Gitelson-Kahn, John Joannopoulos, and Yoel Fink
    Nature Communications Jun 2021