Ehsan Latif
AI Research Scientist
I am an AI researcher with 5+ years of experience specializing in natural language processing, large language models (LLMs), multi-agent/multi-robot systems, and autonomous and intelligent systems optimizations.
I conduct high-impact AI research in decision-making, AI orchestration, and trustworthy AI, with a focus on safe, robust, and sustainable AI applications. My expertise includes training and optimizing transformer-based models, efficient inference deployment, and integrating LLMs into multi-agent coordination.
Selected Publications
Unveiling Scoring Processes: Dissecting the Differences between LLMs and Human Graders in Automatic Scoring
Investigated the key challanges between making agreement between human and machine using machine explination over Large Language Models
Fine-tuning ChatGPT for Automatic Scoring
Implemented specialized fine-tuning techniques on ChatGPT for automating the scoring of educational assessments.
Latest News
Awarded CPS Rising Star 2025 Fellowship
Received a highly competitive fellowship (<0.17% acceptance rate) to attend the NSF Cyber Physical Systems Rising Star Workshop and PI meeting to establish scholarships and networks among the CPS community.
Read morePapers Accepted at IROS 2024
Two papers accepted at the 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS): "HGP-RL: Distributed Hierarchical Gaussian Processes for Wi-Fi-based Relative Localization in Multi-Robot Systems" and "Anchor-Oriented Localized Voronoi Partitioning for GPS-denied Multi-Robot Coverage."
Read moreEarned Machine Learning Specialization from Stanford University
Successfully completed the Machine Learning Specialization from Stanford University, deepening my expertise in advanced machine learning techniques and applications.
Read more