5 papers
Dynamic Minimax Regret Optimization for Robust LLM Post-Training
Chengbo Zang, Haoyu Dong, Mehmet Kerem Turkcan +3
Modern LLM training increasingly relies on heterogeneous data sources spanning different domains, tasks, preference distributions, and difficulty levels. We study dynamic minimax r…
Reinforcement Learning of Communication in a Mesh of Small Language Models
Mehmet Kerem Turkcan
Language models gain accuracy from more compute at test time, but majority voting over independent samples saturates: as samples grow, the vote converges to the model's most freque…
Harnessing Floating Car Data, Traffic Camera Observations, and Network Flow Analysis for Traffic Volume Estimation
Antonina Kosikova, Mehmet Kerem Turkcan, Ahmed Darrat +1
Cities increasingly rely on vehicle trajectory data to monitor traffic conditions; however, such data offer only a partial and spatially heterogeneous view of network dynamics and…
Data-Driven Traffic Simulation for an Intersection in a Metropolis
Chengbo Zang, Mehmet Kerem Turkcan, Gil Zussman +2
We present a novel data-driven simulation environment for modeling traffic in metropolitan street intersections. Using real-world tracking data collected over an extended period of…
Examining the Influence of Varied Levels of Domain Knowledge Base Inclusion in GPT-based Intelligent Tutors
Blake Castleman, Mehmet Kerem Turkcan
Recent advancements in large language models (LLMs) have facilitated the development of chatbots with sophisticated conversational capabilities. However, LLMs exhibit frequent inac…