About

I am an Applied Scientist at Amazon (Rufus team), where I focus on leveraging large language models (LLMs) to improve customer experiences and support innovative solutions across Amazon. I received my Ph.D. in Computer Science from University of California, Irvine. My advisor is Prof. Pierre Baldi. My research was focusing on computer vision, deep learning, and its applications in physical science. [Link to my CV]

In particular, my PhD projects include:

• LLMs for neutrino classification
• generative models for calorimeter simulation
• reconstruction of neutrino features using deep learning
• machine learning in high energy physics
• computational methods for bioimaging and biomedical informatics

Before joining UCI, I graduated with a M.Eng. from University of Illinois at Urbana-Champaign, working closely with Prof. Ruoyu Sun and Prof. Benjamin Hooberman.

Selected Publications

Journals

• Generalizing to new geometries with Geometry-Aware Autoregressive Models (GAAMs) for fast calorimeter simulation
  Junze Liu, Aishik Ghosh, Dylan Smith, Pierre Baldi, Daniel Whiteson
  Journal of Instrumentation, 2023
  [journal] [arXiv]
• Vitreoretinal Surgical Instrument Tracking in Three Dimensions Using Deep Learning
  (* indicates equal contribution)
  Pierre Baldi*, Sherif Abdelkarim*, Junze Liu*, Josiah To*, Marialejandra Ibarra, Andrew Browne
  Translational Vision Science & Technology, 2023
  [journal]
• Calorimetry with deep learning: particle simulation and reconstruction for collider physics
  (Primary contribution - authors are listed in alphabetical order as per the standard in particle physics)
  Dawit Belayneh, Federico Carminati, Amir Farbin, Benjamin Hooberman, Gulrukh Khattak, Miaoyuan Liu, Junze Liu, Dominick Olivito, Vitória Barin Pacela, Maurizio Pierini, Alexander Schwing, Maria Spiropulu, Sofia Vallecorsa, Jean-Roch Vlimant, Wei Wei, Matt Zhang
  The European Physical Journal C, 2020
  [journal] [arXiv] [code]

Conference/Workshop Papers

• Domain-Adaptive ML for Surface Roughness Predictions in Nuclear Fusion
  Shashank Galla, Antonios Alexos, Jay Phil Yoo, Junze Liu, Kshitij Bhardwaj, Sean Hayes, Monika Biener, Pierre Baldi, Satish Bukkapatnam, Suhas Bhandarkar
  NeurIPS Workshop on Machine Learning and the Physical Sciences, Vancouver, B.C., Canada, Dec 10, 2024
  [paper] [poster]
• Nuclear Fusion Diamond Polishing Dataset
  Antonios Alexos, Junze Liu, Shashank Galla, Sean Hayes, Kshitij Bhardwaj, Alexander Schwartz, Monika Biener, Pierre Baldi, Satish Bukkapatnam, Suhas Bhandarkar
  NeurIPS, Vancouver, B.C., Canada, Dec 10, 2024
  [paper] [poster] [dataset]
• Machine Learning-Enhanced Prediction of Surface Smoothness for Inertial Confinement Fusion Target Polishing Using Limited Data
  Antonios Alexos, Junze Liu, Akash Tiwari, Kshitij Bhardwaj, Sean Hayes, Pierre Baldi, Satish Bukkapatnam, Suhas Bhandarkar
  AIM 2024: Machine Learning Simulations, Cleveland, OH, United States, June 20, 2024
  [arXiv]
• Geometry-aware Autoregressive Models for Calorimeter Shower Simulations
  (* indicates equal contribution)
  Junze Liu*, Aishik Ghosh*, Dylan Smith*, Pierre Baldi, Daniel Whiteson
  NeurIPS Workshop on Machine Learning and the Physical Sciences, New Orleans, LA, United States, Dec 3, 2022
  [pdf] [poster] [arXiv]
• Automated detection of the spatial location of vitreoretinal instruments from retinal images using Deep Learning methods
  Marialejandra Ibarra, Josiah To, Junze Liu, Sherif Abdelkarim, Anjali Herekar, Baruch Kuppermann, Pierre Baldi, Andrew Browne
  ARVO Anual Meeting, Denver, CO, United States, May 1, 2022
  [abstract]
• Deep-Learning-Based Kinematic Reconstruction for DUNE
  Junze Liu, Jordan Ott, Julian Collado, Benjamin Jargowsky, Wenjie Wu, Jianming Bian, Pierre Baldi
  NeurIPS Workshop on Machine Learning and the Physical Sciences, Vancouver, Canada, Dec 11, 2020
  [pdf] [poster] [arXiv]

Selected Talks

• Deep-learning Event Reconstruction in DUNE Far Detector
  The Second Wire-Cell Reconstruction Summit at Brookhaven National Laboratory, Upton, NY, United States, April 12, 2024
  
• AI in Ophthalmology
  Vision Research Mixer at University of California Irvine, Irvine, CA, United States, Feb 7, 2024
  
• Deep-learning-based Kinematic Reconstruction for DUNE
  CFPU SMLI Seminar at Brown University, Providence, RI, United States, March 16, 2021
  

Academic Service

Program Committee:

• ECML-PKDD: The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2024
• Machine Learning and the Physical Sciences Workshop at NeurIPS, 2021, 2022, 2023, 2024

Reviewer:

• Synthetic Data for Computer Vision Workshop at CVPR, 2024
• ECML PKDD: The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2023
• KDD: ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2023

Teaching

• Teaching Assistant: COMPSCI 274P Neural Networks and Deep Learning, 2020 Spring
• Teaching Assistant: COMPSCI 178 Machine Learning and Data Mining, 2020 Winter
• Reader: COMPSCI 112 Computer Graphic, 2019 Fall

Awards

• CS Travel Grants from Donald Bren School of Information and Computer Sciences, 2024
• CS Travel Grants from Donald Bren School of Information and Computer Sciences, 2023
• CS Travel Grants from Donald Bren School of Information and Computer Sciences, 2022
• Dean's Awards from Donald Bren School of Information and Computer Sciences, 2019