Naren Sivakumar
he/him/his
University of Maryland, Baltimore County
Computer Science
Biography
I am Naren Sivakumar, a PhD student at the University of Maryland, Baltimore County. My research focuses on robust multimodal retrieval, context understanding from real-world and synthetic footage, and intelligent event-driven decision-making in real-world environments. I have built multimodal (audio + video, video only, audio only) systems to make decisions based on object and event detection, in both real-world (toll camera footage) and synthetic (video game) environments. For my master's degree, I worked on developing context-aware decision-making systems powered by a rich case history to be deployed in high-stakes negotiations. Language models, acting as agents, retrieve historical context and use it to simulate the governance of a country and formulate policies on the fly based on their counterparts' actions. As part of my applied work, I have also created several award-winning working prototypes as a part of hackathons for assistive technologies, such as voice-powered video game players and touchless phone navigation. My research is complemented by my industry experience at IBM, where I developed an AI-powered calorie-tracking application.
Academic Information
Status: PhD Student
Year in Program: 1st
Major/Specialty: Computer Science
Degrees: PhD in Computer Science / Computer Science /2025 - Ongoing Master's in Computer Science / Computer Science / 2023 - 2025 Bachelor's of Engineering in Computer Science / Computer Science / 2019 - 2023
Research Areas
Computer Science; Machine Learning/AI
Research Interests
My research interests lie in robust multimodal retrieval, assessment, and context understanding for factually correct vision and language models. I have built multimodal systems that involve taking actions based on event detection in a frame-by-frame analysis in real-world and synthetic data environments. My research focuses on identifying, tracking, and understanding events in video footage to then make intelligent decisions based on the events. I am also contributing to a DARPA project on retrieval and claim assessment, where I am building a multimodal system that retrieves relevant information about a claim and uses that information to intelligently make decisions about feasibility. Additionally, I am excited to expand my research to the audio domain.
Topical Areas
Artificial Intelligence and Intelligent Systems; Computer Science; Performance Evaluation and Benchmarking
Relevant Coursework
Design and Analysis of Algorithms, Principles of Artificial Intelligence, Introduction to Natural Language Processing, Reasoning with GenAI, Advanced Operating Systems, Robust Machine Learning, Computer Vision
Publications & Research Projects
Sivakumar, N., Chen, L. K., Papasani, P., Majmundar, V., Feng, J. H., Yarnall, L., & Gong, J. (2024, October). Show and Tell: Exploring Large Language Models' Potential in Formative Educational Assessment of Data Stories. In 2024 IEEE VIS Workshop on Data Storytelling in an Era of Generative AI (GEN4DS) (pp. 13-19). IEEE. Pravinkrishnan, K., Sivakumar, N., Jebaraj, A., Pooja, C. P., Sridhar, S., Balasundaram, P., & Kalinathan, L. (2022). Classification of Plant Species Using AlexNet Architecture. In CLEF (Working Notes) (pp. 2087-2093). Sivakumar, N. (2025). Emulating Rational Decisions With Traditional And Contemporary AI [Unpublished master's thesis]. University of Maryland, Baltimore County.