About

I am a Ph.D. student in Computer Science at the University of Illinois Chicago, advised by Dr. Abolfazl Asudeh. I completed my B.Sc. in Computer Engineering, with a minor in Mathematics, at Sharif University of Technology.

My research primarily focuses on algorithm design and data science with an emphasize on developing algorithms to optimize various stages of machine learning and data science pipelines. I am also exploring algorithmic approaches to improve the efficiency of LLMs.

In addition, I have a strong interest in geometric algorithms and computational geometry, particularly in their applications to data science and database problems.

Publications

• HENN: A Hierarchical Epsilon Net Navigation Graph for Approximate Nearest Neighbor Search
  Mohsen Dehghankar, Abolfazl Asudeh
  Preprint (2025)
  [PDF] | [Code]

• An Efficient Matrix Multiplication Algorithm for Accelerating Inference in Binary and Ternary Neural Networks
  Mohsen Dehghankar, Mahdi Erfanian, Abolfazl Asudeh
  ICML 2025
  [PDF] | [Code]

• Rank It, Then Ask It: Input Reranking for Maximizing the Performance of LLMs on Symmetric Tasks
  Mohsen Dehghankar, Abolfazl Asudeh
  KDD 2025
  [PDF] | [Code]

• Mining the Minoria: Unknown, Under-represented, and Under-performing Minority Groups
  Mohsen Dehghankar, Abolfazl Asudeh
  VLDB 2025
  [PDF] | [Code]

• Fair Set Cover
  Mohsen Dehghankar, Rahul Raychaudhury, Stavros Sintos, Abolfazl Asudeh
  KDD 2025
  [PDF] | [Code] | [Video]

• Needle: A Generative-AI Powered Monte Carlo Method for Answering Complex Natural Language Queries on Multi-modal Data
  Mahdi Erfanian, Mohsen Dehghankar, Abolfazl Asudeh
  Preprint (2025)
  [PDF] | [Code]

Contact

You can reach me by email at mdehgh2@uic.edu. You can also connect with me on LinkedIn, GitHub, and X.