Arun Sharma

Arun Sharma

Ph.D., Computer Science

University of Minnesota, Twin Cities

CV Google Scholar GitHub Hugging Face LinkedIn Twitter Email

I build physics-informed AI systems that make spatial reasoning reliable for real-world deployment: detecting GPS spoofing for safer autonomous navigation, modeling energy-efficient vehicle routing, and downscaling climate data for coastal flood-risk assessment. My research fuses deep generative models, diffusion models, transformers, physics-informed learning, and geostatistical priors to address data incompleteness, distribution shift, and violations of physical laws in spatial machine learning. I build AI systems that back each output with checkable evidence, including a real-time maritime anomaly-detection platform on AWS (Harbormaster) and a spatial reasoning agent (Spatial Atlas).

I earned my Ph.D. in Computer Science from the University of Minnesota, Twin Cities, advised by Prof. Shashi Shekhar, with committee members Prof. Vipin Kumar, Prof. Ravi Janardan, and Prof. Ying Song. My dissertation is Distortion-Aware Spatial Data Science (Doctoral Dissertation Fellowship, 2022-2023).

Actively looking for full-time opportunities.

Research Statement Teaching Statement Diversity Statement Ph.D. Thesis

News

  1. [07/2026] Spatial Atlas, a compute-grounded spatial reasoning agent (Berkeley RDI) [arXiv] [video]
  2. [09/2026] Oral presentation accepted at AIAS+ 2026 in San Francisco, CA. [project page] [video]
  3. [07/2026] Oral presentation accepted at PyTorch Conference North America 2026. [project page] [video]
  4. [12/2025] One paper accepted in AAAI Workshop on AI to Accelerate Science and Engineering.
  5. [11/2025] Two oral presentations in ACM SIGSPATIAL 2025 in Minneapolis.
  6. [09/2025] Four papers accepted at ACM SIGSPATIAL 2025.
  7. [08/2025] One paper accepted in SSTD 2025.
  8. [07/2025] Successfully defended my Ph.D. dissertation.
  9. [02/2025] Two papers accepted at AAAI Bridge on Knowledge-Guided ML Workshop 2025.
  10. [12/2024] One paper accepted at SIAM Data Mining 2025.
  11. [11/2024] Oral presentation in ACM SIGSPATIAL 2024 in Atlanta, GA.
  12. [10/2024] NSF Travel Award for SIGSPATIAL 2024.
  13. [10/2024] One paper accepted at ACM Transactions on Spatial Algorithms and Systems.
  14. [09/2024] Two papers accepted at ACM SIGSPATIAL 2024.
  15. [08/2024] Invited poster presentation at Knowledge-Guided Machine Learning Workshop 2024.
  16. [06/2024] One paper accepted at COSIT 2024.
  17. [05/2024] Invited lightning talk and poster presentation in the AI-CLIMATE annual meeting.
  18. [12/2023] One paper accepted at SIAM Data Mining 2024.
  19. [08/2023] Completed my internship at Esri under Dr. Erik G. Hoel.
  20. [04/2023] Invited presentation at MIDAS Future Leader Summit at University of Michigan.
  21. [03/2023] One paper accepted in GIScience 2023.
  22. [11/2022] Oral presentation in ACM SIGSPATIAL 2022 in Seattle, WA.
  23. [10/2022] NSF Travel Award for SIGSPATIAL 2022.
  24. [09/2022] Oral presentation in COSIT 2022 in Kobe, Japan.
  25. [08/2022] One paper accepted in ACM SIGSPATIAL 2022.
  26. [05/2022] Received Doctoral Dissertation Fellowship 2022-2023.
  27. [04/2022] One paper accepted in COSIT 2022.
  28. [03/2022] One paper accepted in AGILE 2022.
  29. [09/2021] Oral presentation in GIScience 2021 online.
  30. [05/2021] One paper accepted at ACM Transactions in Intelligent System and Technology.
  31. [10/2020] Invited presentation at University of Maryland, College Park online.
  32. [06/2020] One paper accepted in GIScience 2021.

Publications

Complete list, also on Google Scholar. Click a title to open the paper.

Teaching

Teaching assistant at the University of Minnesota (600+ students).

Reading Resources

Papers and books I am reading, with short notes and a relevance rating (out of 5). Click a title for my notes; "source" links to the original.

How to Scale Your Model: A Systems View of LLMs on TPUs

Jacob Austin, Sholto Douglas, Roy Frostig, Anselm Levskaya, Charlie Chen, Reiner Pope, et al. (Google DeepMind) · Online book (jax-ml.github.io/scaling-book), Google DeepMind · ★★★★½4.5/5

A first-principles, roofline-driven playbook for scaling Transformer training and inference across thousands of TPUs (and GPUs).

notes · source

Reinforcement Learning: An Overview

Kevin P. Murphy · arXiv 2024 (v5, Dec 2025) · ★★★★½4.5/5

Kevin Murphy's 250-page modern RL monograph: value/policy/model-based, multi-agent, and a deep LLMs-and-RL chapter (RLHF, RLVR, PPO/GRPO/DPO).

notes · source

Contact

Email: arunshar at umn dot edu