I am a final year Ph.D student at ICME at Stanford University where I am part of the Medical AI and ComputeR Vision Lab (MARVL). I am fortunate to be advised by Prof. Serena Yeung. Previously, I received a BS in Mathematics from Caltech. I have a broad range of research interests, including 3D computer vision, implicit neural representations, multimodal large language models, geometric deep learning, and AI for science applications (such as structural biology/cryo-EM)! You can reach me at jeffgu[at]stanford.edu.

I am currently on job market! I am looking for both industry opportunities and postdocs. Feel free to reach out!

News

• Jan 2025: Our paper “Foundation Models Secretly Understand Neural Network Weights: Enhancing Hypernetwork Architectures with Foundation Models” is accepted to ICLR 2025!
• Feb 2024: Our survey “Hyperbolic Deep Learning in Computer Vision: A Survey” is accepted to IJCV 2024! Big thanks to my coauthors and Pascal for organizing!
• Oct 2023: Presented our work “Generalizable Neural Fields as Partially Observed Neural Processes” at ICCV 2023!
• Oct 2022: Gave a talk as part of the Hyperbolic Representation Learning for Computer Vision tutorial at ECCV 2022! The tutorial webiste can be found here and videos of the talks can be found here!
• Feb 2022: Gave a talk at the MedAI Group Exchange Sessions at Stanford! The website for MedAI can be found here and a video of the talk can be found at this channel

Publications and Preprints

• CryoHype: Transformer-based hypernetwork for heterogeneous Cryo-EM reconstruction (In submission) Jeffrey Gu, Minkyu Jeon, Ambri Ma, Serena Yeung, Ellen D. Zhong

• BIOMEDICA: An Open Biomedical Image-Caption Archive with Vision-Language Models derived from Scientific Literature (In submission) Alejandro Lozano, Min Woo Sun, James Burgess, Liangyu Chen, Jeffrey J Nirschl, Jeffrey Gu, Ivan Lopez, Josiah Aklilu, Austin Wolfgang Katzer, Collin Chiu, Anita Rau, Xiaohan Wang, Yuhui Zhang, Alfred Seunghoon Song, Robert Tibshirani, Serena Yeung-Levy

• Foundation Models Secretly Understand Neural Network Weights: Enhancing Hypernetwork Architectures with Foundation Models (ICLR 2025) Jeffrey Gu, Serena Yeung

• Hyperbolic Deep Learning in Computer Vision: A Survey (IJCV 2024) [Paper][Tutorial][Sample code] Pascal Mettes, Mina Ghadimi Atigh, Martin Keller-Ressler, Jeffrey Gu, Serena Yeung

• Generalizable Neural Fields as Partially Observed Neural Processes (ICCV 2023) [Project page][Paper][Code] Jeffrey Gu, Kuan-Chieh Wang, Serena Yeung

• NeMo: 3D Neural Motion Fields from Multiple Video Instances of the Same Action (CVPR 2023 Highlight) [Project page][Paper][Code] Kuan-Chieh Wang, Zhenzhen Weng, Maria Xenochristou, Joao Pedro Araujo, Jeffrey Gu, C Karen Liu, Serena Yeung

• Capturing implicit hierarchical structure in 3D biomedical images with self-supervised hyperbolic representations (NeurIPS 2021) [Paper][Code] Joy Hsu*, Jeffrey Gu*, Gong-Her Wu, Wah Chiu, Serena Yeung

• Staying in Shape: Learning Invariant Shape Representations using Contrastive Learning (UAI 2021) [Paper][Code] Jeffrey Gu, Serena Yeung

• Learning Hyperbolic Representations for Unsupervised 3D Segmentation (NeurIPS Differential Geometry meets Deep Learning (DiffGeo4DL) Workshop 2020, Top paper/Contributed talk) [Paper]
  Joy Hsu*, Jeffrey Gu*, Serena Yeung

Service

• Reviewer: NeurIPS 2021 Datasets & Benchmarks, CVPR 2024, NeurIPS 2024 (Top Reviewer), AAAI 2025, ICLR 2025, AISTATS 2025, CVPR 2025

Teaching

• BIODS 220/CS 271/BIOMEDIN 220: Artificial Intelligence in Healthcare: Fall ‘22, Stanford University
• CME 241: Reinforcement Learning for Stochastic Control Problems in Finance: Winter ‘19, Stanford University