I am a Machine Learning Ph.D. student at Georgia Tech, fortunate to be advised by Prof. Xiaoming Huo. Before Georgia Tech I completed an M.S. in Industrial Engineering (Data Science) at West Virginia University and a B.S. in Industrial Engineering at Iran University of Science and Technology, Tehran, Iran.

My research focuses on developing statistical machine learning and reinforcement learning methods for evaluating, understanding, and improving AI systems, with an emphasis on large language models and sequential decision-making systems. I also spent 2025 at Tesla building production ML pipelines for large-scale modeling and evaluation.

I am always glad to talk about research or possible collaborations — feel free to reach out.

Research Interests

Statistical machine learning · Reinforcement learning · LLM evaluation and risk control · Reinforcement learning with verifiable rewards (RLVR) for LLMs · Human–AI teaming · Statistical evaluation of AI systems · Multi-armed and contextual bandits · Non-stationary and online learning · Sequential decision making · Conformal prediction and uncertainty quantification · Causal inference and experimental design

Latest News

  • 2026New paper preprint on choosing which LLM to use for which task when quality estimates are uncertain is now on arXiv.
  • 2026TEAM-Audit: A Two-Endpoint Audit of Margins accepted at HAT 2026 (HCOMP/CI).
  • 2026Received the Most Innovative Approach Award, NSF Future Manufacturing Data Challenge.
  • 2026Awarded the John Morris Fellowship.
  • 2026Two new preprints on non-stationary low-rank bandits and anytime-valid risk control for RLVR-trained LLMs.
  • 2025Started the Machine Learning Ph.D. at Georgia Tech with Prof. Xiaoming Huo.
  • 2025Completed a Machine Learning Engineer internship at Tesla (Cell Engineering, Analytics & Software).

Selected Publications

Full list on Google Scholar.

  1. Which LLM for Which Work? Budgeted Model Allocation under Uncertain Evaluation Hamed Khosravi, Xiaoming Huo arXiv preprint arXiv:2608.29560, 2026 Paper Code
  2. Catching a Moving Subspace: Low-Rank Bandits Beyond Stationarity Hamed Khosravi, Xiaoming Huo arXiv preprint arXiv:2605.20269, 2026 Paper Code
  3. Conformal Selective Acting: Anytime-Valid Risk Control for RLVR-Trained LLMs Hamed Khosravi, Xiaoming Huo arXiv preprint arXiv:2605.20270, 2026 Paper Code
  4. LLM-Observed Multi-Agent Maintenance with Amortized Reinforcement Learning Policies Hamed Khosravi, Xiaoming Huo SSRN preprint, 2026 Paper Code
  5. LNUCB-TA: Linear–Nonlinear Hybrid Bandit Learning with Temporal Attention Hamed Khosravi, Mohammad Reza Shafie, Ahmed Shoyeb Raihan, Srinjoy Das, Imtiaz Ahmed arXiv preprint arXiv:2503.00387, 2025 Paper
  6. KANGURA: Kolmogorov–Arnold Network-Based Geometry-Aware Learning with Unified Representation Attention for 3D Modeling of Complex Structures Mohammad Reza Shafie*, Morteza Hajiabadi*, Hamed Khosravi*, Mobina Noori, Imtiaz Ahmed Manufacturing Letters, 2026 * Equal contribution — co-first authors. Paper
  7. A Data-Driven Sequential Learning Framework to Accelerate and Optimize Multi-Objective Manufacturing Decisions Hamed Khosravi, Taofeeq Olajire, Ahmed Shoyeb Raihan, Imtiaz Ahmed Journal of Intelligent Manufacturing, vol. 35(8), 2024 Paper
  8. An Improved Group Teaching Optimization Algorithm Based on Local Search and Chaotic Map for Feature Selection in High-Dimensional Data Hamed Khosravi, Babak Amiri, Navid Yazdanjue, Vahide Babaiyan Expert Systems with Applications, vol. 204, 2022 Paper

Experience

  • Jan – Aug 2025 Machine Learning Engineer Intern, Tesla — Cell Engineering, Analytics & Software Built a modular Python ML framework and Kubeflow/Kubernetes pipelines for reproducible large-scale training and evaluation; applied conformal prediction and uncertainty-aware modeling to production workflows.

Honors & Awards

  • 2026Most Innovative Approach Award — NSF Future Manufacturing Data Challenge
  • 2026John Morris Fellowship, Georgia Institute of Technology
  • 2025Finalist, PG&E Energy Analytics Challenge Competition, IISE
  • 2025NSF Travel Award to attend the IISE Annual Conference
  • 20243rd Place, Manufacturing AI Competition, INFORMS QSR Section
  • 2024NSF Travel Award to attend the NAMRC 53 Conference
  • 2024Excellence in Research Award, West Virginia University
  • 2023Benjamin M. Statler College of Engineering and Mineral Resources Fellowship, West Virginia University
  • 2022Distinguished Student, B.Sc. degree, Iran University of Science and Technology

Academic Service

Conferences Reviewer, NeurIPS 2026.

Journals Reviewer for 10+ peer-reviewed journals, including Scientific Reports, Expert Systems with Applications, Artificial Intelligence Review, Signal, Image and Video Processing, Neural Processing Letters, Machine Learning Research, and Machine Learning with Applications.