Dr. Manas Gaur

Assistant Professor · Tenure-Track

Department of Computer Science and Electrical Engineering

College of Engineering and Information Technology

He/Him/His/Himself

About

Manas Gaur is an Assistant Professor of Computer Science at UMBC and Director of the KAI² Lab, where he pursues use-inspired basic research at the intersection of neurosymbolic AI, mechanistic interpretability, and clinical natural language processing. His overarching mission is to render large language models trustworthy for high-stakes applications, particularly in mental health and clinical decision support. Gaur holds the prestigious Ramanujan Fellowship from the Anusandhan National Research Foundation, recognizing his standing among early-career researchers in artificial intelligence. He serves as an Advisor AI Research Scientist for NeuralNest and Aidvance. He brings industry-academic experience from Samsung Research America and Dataminr, combined with sustained clinical partnerships spanning the Maryland Psychiatric Research Center and university-embedded clinical psychology. His research traces a coherent arc from foundational work in social media mining for mental health, through the development of Knowledge-Infused Learning as a neurosymbolic paradigm, to mechanistic interpretability and grounding fidelity for clinical AI systems. His innovation portfolio includes three patents that define core algorithmic advances for high-stakes applications: AQGPT, ISEEQ, and Virtual Court Room, each anchoring trustworthy AI deployment in clinical and legal contexts. Gaur is deeply committed to early-stage researcher development and academic leadership. Through mentorship of undergraduates and high school students to first-author publication, he has seeded cumulative research impact now flowing through Carnegie Mellon, Purdue, and leading technology companies. His current research frames Knowledge-Infused Neurosymbolic AI around three scientific pillars, Interpret, Ground, and Control, positioning mechanistic reasoning as the foundation for trustworthy clinical AI.

Research interests

Neurosymbolic AI, Knowledge-Infused Learning, Mechanistic Interpretability, Sparse Autoencoders and Circuit Analysis, Long-Form Reasoning and Attribution, Retrieval-Augmented Generation, Grounding Fidelity in LLMs, Clinical Natural Language Processing, Trustworthy AI for High-Stakes Applications (Cybersecurity, Scientific Discovery, Mental Health, Legal), Adversarial Robustness

Teaching interests

Neurosymbolic AI Systems, Knowledge-infused Learning, Machine Learning, Semantic Mechanistic Interpretability, Trustworthy AI, Knowledge Graph Representation and AI Reasoning, Large Language Models, Natural Language Processing

Education

  • Ph D, Computer Science — University of South Carolina (2022)
    Knowledge-infused Learning
  • MS, Software Engineering — Delhi Technological University (Formerly Delhi College of Engineering) (2015)
    BIOGEOGRAPHY BASED OPTIMIZATION FOR COMPLEX SYSTEM
  • BS, Computer Science — Netaji Subhas University of Technology (East Campus) (Formerly Ambedkar Institute of Technology) (2013)
    Meticulous study of firewall using security detection tools

Publications

Presentations

  • Process Knowledge-infused AI 2022 KGSWC · Springer · Lecture
  • Towards Effective Paraphrasing for Information Disguise 2022 ECIR · Springer · Oral Presentation Anmol Agarwal (Author & Presenter), Shrey Gupta (Author & Presenter), Vamshi Bonagiri (Author), Manas Gaur (Author), Joseph Reagle (Author), Ponnurangam Kumaraguru (Author)
  • Towards Process Knowledge-infused Learning for Explainable Mental Healthcare 2022 ICON · ACL · Lecture Manas Gaur (Author & Presenter), Kaushik Roy (Author & Presenter), Amit Sheth (Author)

Grants and Contracts

  • Collaborative Research: SCH: Towards Observable and Instructible AI Agents for Supporting Mental Health Professionals NSF · Grant · Currently Under Review Manas Gaur (Principal), Lira Yoon (Co-Principal)
  • Collaborative Research: VINES: Track 1: NSF-JST: Neuro-symbolic AI-Native Design of Semantic Communications NSF · Grant · Currently Under Review Manas Gaur (Co-Principal), Houbing Song (Principal)
  • SparqSSM: A Lightweight Hybrid State Space Framework for Fast SPARQL Query Generation and Conversation on Personal Lifelong Knowledge Graphs Samsung · Sponsored Research · Not Funded Timothy W Finin (Co-Principal), Manas Gaur (Principal), Rajasekhar Anguluri (Co-Principal)

Research in Progress

  • Human-Centered AI Advising Systems 2025 Scholarly · On-Going Sanorita Dey, Manas Gaur

Patents and Intellectual Property

  • AQ-GPT: Custom and Compact Foundation Model for Personalized Air Quality Advisories Small App, Personalized Advisor on the go 2025 Patent Manas Gaur, Ram Rustagi, Vaidyanathan A
  • Dynamic question generation for information-gathering 2022 Patent · No. US20230061906A1 Manas Gaur, Kalpa Gunaratna, Vijay Srinivasan, Hongxia Jin

Courses Taught

  • Spec Topics In Comp Science : Knowledge-powered NeuroSymbolic AI for Explainability, Interpretability, and Safety CMSC 691 · Fall 2024
  • Master's Thesis Research CMSC 799 · Spring 2024
  • Independent Study in Computer Science CMSC 699 · Spring 2024
  • Independent Study Computer Science CMSC 499 · Spring 2024
  • Introduction to Machine Learning CMSC 478 · Spring 2024
  • Intro Machine Learning CMSC 678 · Fall 2022