Ramneet Kaur

Advanced Computer Scientist II

Computer Science Lab, SRI

Menlo Park, California

LinkedIn Google Scholar

Ramneet Kaur Profile Picture

Research Interests

Core Areas:
  • Artificial Intelligence, Trustworthy Machine Learning, Interpretability and Fairness
  • GenAI Alignment, Resilient Deep Learning, Open World Learning
  • Reinforcement Learning, Formal Methods
Application Areas:
  • Cyber-Physical Systems (CPS)
  • Internet of Medical Things (IoMT)

Education

Ph.D. in Computer & Information Science

University of Pennsylvania, Philadelphia, PA | Dec 2023

Thesis: Screening Out-of-Distribution Inputs for Reliable AI Predictions

M.S. in Computer & Information Science

University of Pennsylvania, Philadelphia, PA | Dec 2021

M.S. in Computer Science & Engineering

Indian Institute of Technology Kharagpur, India | May 2014

Thesis: Applications of Lovász local lemma: Existence and Computation of Combinatorial Structures

B.S. in Computer Science & Engineering

College of Engineering Roorkee, India | May 2012

News

Publications

Conference Publications

Journal Publications

Workshop Publications

Dissertation and Technical Reports

Student Mentoring

Vivian Lin (University of Pennsylvania)

External Committee Member for PhD Research on OOD-Resilient Safety Monitoring for Safety-Critical Cyber-Physical Systems.

2024 – present
Ayush Gupta (Johns Hopkins University)

PhD Research on Out-of-Distribution Detection for Specialized LLMs.

2024 – present
Trilok Padhi (Georgia State University)

PhD Research on Uncertainty Quantification and Temporal Interpretability of LLMs.

2024 – present
Aurelien Ghiglino (Stanford University)

PhD Research on Interpretability of Diffusion Models.

2025 – present
Essa Jan (Brown University)

Masters Research on Reducing Potemkin Rate of LLMs.

2025 – present
Yahan Yang (University of Pennsylvania)

PhD Research on Interpretable Out-of-Distribution Detection.

2022 – 2024
Xiayan Li (University of Pennsylvania)

Mentor for her PhD Thesis.

2024
Chandra Kanth Nagesh (University of Colorado Boulder)

PhD Research on Kolmogorov-Arnold Networks.

2024
Felipe Toledo (University of Virginia)

PhD Research on Monitoring Safety properties of VLMs.

2024
Krishiv Agarwal (University of Florida)

Undergrad Research on Applying Interpretability Techniques for Jailbreaking LLMs.

2025 – present
Abhinav Khanna (Indian Institute of Technology (IIT), Delhi)

Undergrad Research on Agentic AI.

2025 – present

Industry and Research Experience

Advanced Computer Scientist II, AI

SRI (Computer Science Lab), Menlo Park, CA | Jan 2024 – Present

Working with the Neuro-Symbolic Computing and Intelligence (NuSCI) Research Group, focusing on trustworthy machine learning, AI alignment, resilient deep learning, and open-world learning, specifically for Cyber-Physical Systems and IoMT applications.

Research and Development Intern

SRI (CSL), Menlo Park, CA | Summer 2022

Developed an approach to predict the accuracy of deep learning models in novel environments for autonomous driving systems.

Member of Technical Staff-2

VMware Software India Private Limited, Maharashtra, India | Aug 2014 – Sep 2016

Worked on providing network virtualization solutions in VMware's hypervisor vSphere and deploying solutions to embedded systems.