20 citations · 23 across the 7 of their papers we have counts for
7 papers
Tools in the Loop: Quantifying Uncertainty of LLM Question Answering Systems That Use Tools
Panagiotis Lymperopoulos, Vasanth Sarathy
Modern Large Language Models (LLMs) often require external tools, such as machine learning classifiers or knowledge retrieval systems, to provide accurate answers in domains where…
Graph Pruning for Enumeration of Minimal Unsatisfiable Subsets
Panagiotis Lymperopoulos, Liping Liu
Finding Minimal Unsatisfiable Subsets (MUSes) of binary constraints is a common problem in infeasibility analysis of over-constrained systems. However, because of the exponential s…
NovelGym: A Flexible Ecosystem for Hybrid Planning and Learning Agents Designed for Open Worlds
Shivam Goel, Yichen Wei, Panagiotis Lymperopoulos +3
As AI agents leave the lab and venture into the real world as autonomous vehicles, delivery robots, and cooking robots, it is increasingly necessary to design and comprehensively e…
NovelCraft: A Dataset for Novelty Detection and Discovery in Open Worlds
Patrick Feeney, Sarah Schneider, Panagiotis Lymperopoulos +3
In order for artificial agents to successfully perform tasks in changing environments, they must be able to both detect and adapt to novelty. However, visual novelty detection rese…
Integrating Planning, Execution and Monitoring in the presence of Open World Novelties: Case Study of an Open World Monopoly Solver
Sriram Gopalakrishnan, Utkarsh Soni, Tung Thai +3
The game of monopoly is an adversarial multi-agent domain where there is no fixed goal other than to be the last player solvent, There are useful subgoals like monopolizing sets of…
Forecasting COVID-19 Counts At A Single Hospital: A Hierarchical Bayesian Approach
Alexandra Hope Lee, Panagiotis Lymperopoulos, Joshua T. Cohen +2
We consider the problem of forecasting the daily number of hospitalized COVID-19 patients at a single hospital site, in order to help administrators with logistics and planning. We…
Branching principles of animal and plant networks identified by combining extensive data, machine learning, and modeling
Alexander B Brummer, Panagiotis Lymperopoulos, Jocelyn Shen +7
Branching in vascular networks and in overall organismic form is one of the most common and ancient features of multicellular plants, fungi, and animals. By combining machine-learn…