5 papers
PEPS: Quantum-Inspired Reinforcement Learning for Coherent Reasoning Traces in LLMs
Venkat Margapuri, Garik Kazanjian, Naren Kosaraju
Large Language Models (LLMs) often struggle with maintaining coherent multi-step reasoning traces, particularly in tasks that require a structured logical flow. This work introduce…
Hybrid Safety Verification of Multi-Agent Systems using -Weighted CBFs and PAC Guarantees
Venkat Margapuri, Garik Kazanjian, Naren Kosaraju
This study proposes a hybrid safety verification framework for closed-loop multi-agent systems under bounded stochastic disturbances. The proposed approach augments control barrier…
Prompt Informed Reinforcement Learning for Visual Coverage Path Planning
Venkat Margapuri
Visual coverage path planning with unmanned aerial vehicles (UAVs) requires agents to strategically coordinate UAV motion and camera control to maximize coverage, minimize redundan…
Diagnosis and Severity Assessment of Ulcerative Colitis using Self Supervised Learning
Venkat Margapuri
Ulcerative Colitis (UC) is an incurable inflammatory bowel disease that leads to ulcers along the large intestine and rectum. The increase in the prevalence of UC coupled with gast…
Predicting Mortality and Functional Status Scores of Traumatic Brain Injury Patients using Supervised Machine Learning
Lucas Steinmetz, Shivam Maheshwari, Garik Kazanjian +4
Traumatic brain injury (TBI) presents a significant public health challenge, often resulting in mortality or lasting disability. Predicting outcomes such as mortality and Functiona…