About me

Hi, I'm Shaan Pakala.

I am a 2nd year Computer Science Ph.D. student at the University of California, Riverside, advised by Professor Vagelis Papalexakis. Here I work on AI4Science research, mainly focused on surrogate modeling for expensive experiments/simulations, alongside domain-experts in material science and physics. Most of my work involves learning from multi-dimensional data (i.e., tensors) by using tensor decomposition to understand and accelerate various scientific problems. Some key examples are designing a material with optimal properties or efficiently generating expensive physics simulations.

I also intern/collaborate with the predictive healthcare group at Lawrence Livermore National Laboratory with Dr. Priyadip Ray. Here we use machine learning methods to address important challenges in the healthcare space, alongside clinicians and biomedical researchers.

Peer-reviewed Publications

Conference

• Tensor Methods: A Unified and Interpretable Approach for Material Design
  Shaan Pakala, Aldair Gongora, Brian Giera, Evangelos Papalexakis
  ACM SIGKDD (AI for Sciences track) 2026 [pdf] [code]
• Automating Data Science Pipelines with Tensor Completion
  Shaan Pakala, Bryce Graw, Dawon Ahn, Tam Dinh, Mehnaz Tabassum Mahin, Vassilis Tsotras, Jia Chen, Evangelos Papalexakis
  IEEE International Conference on Big Data 2024 [pdf] [code]

Workshop

• Surrogate Modeling for the Design of Optimal Lattice Structures using Tensor Completion
  Shaan Pakala, Aldair Gongora, Brian Giera, Evangelos Papalexakis
  NeurIPS AI4Mat Workshop 2025 [pdf] [code]
• Efficiently Generating Multidimensional Calorimeter Data with Tensor Decomposition Parameterization
  Paimon Goulart*, Shaan Pakala*, Evangelos Papalexakis
  ICCV LIMIT Workshop 2025 [pdf] [code]
• Tensor Completion for Surrogate Modeling of Material Property Prediction
  Shaan Pakala, Dawon Ahn, Evangelos Papalexakis
  AAAI Bridge on Knowledge-Guided Machine Learning 2025 [pdf]