Applied Scientist at AmazonMy name is Kiran Kokilepersaud. I am an Applied Scientist at Amazon working on LLM Judge Systems. I completedPhD in the school of Electrical and Computer Engineering at the Georgia Institute of Technology.
My PhD research targeted understanding self supervised algorithms (SSL) from both a theoretical and application specific perspective.
Resume
Warning
Problem: The current name of your GitHub Pages repository ("Solution: Please consider renaming the repository to "
http://".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}" in index.html.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "Education
-
Georgia Institute of TechnologyDepartment of Electrical and Computer Engineering
Ph.D. StudentSep. 2020 - Apr. 2026 -
University of Maryland at College ParkB.S. in Electrical EngineeringSep. 2016 - May 2020
Experience
-
AmazonApplied ScientistJun. 2026 - Present
-
AppleCamera Algorithms Machine Learning InternMay 2025 - August 2025 -
Georgia Institute of TechnologyPhD Student ResearcherSep. 2020 - Apr. 2026
-
Johns Hopkins Applied Physics LabMission Systems Research InternMay 2020 - Aug. 2020 -
Maryland Cybersecurity CenterResearch InternJan. 2020 - Apr. 2020
-
Northrop GrummanHardware Engineering InternJun. 2019 - Aug. 2019 -
iD Tech Camps American UniversityLead InstructorJun. 2018 - Aug. 2018
Teaching
-
AI Foundations ECE 2806Course Developer and Teaching FellowJan. 2024 - May 2025
-
Intro to Signals Processing ECE 2026Graduate Teaching AssistantJan. 2021 - Aug. 2021
-
Intro to C Programming ENEE 140Undergraduate Teaching FellowSep. 2018 - Dec. 2019
Honors & Awards
-
ECE Outstanding Graduate Teaching Assistant Award2026
-
NextProf Workshop Acceptance2024
-
ICIP 2024 Student Travel Grant2024
-
CSIP Service Award2023
-
IEEE Big Data 2023 Student Travel Grant2023
-
Georgia Tech PhD President's Fellowship2020
News
Selected Publications (view all )
AdaDim: Dimensionality Adaptation for SSL Representational Dynamics
Kiran Kokilepersaud, Mohit Prabhushankar, Ghassan AlRegib
Under review at NeurIPS 2026
In this work, we study SSL training dynamics in terms of both mutual information between projection and representation spaces as well as in terms of overall dimensionality.
AdaDim: Dimensionality Adaptation for SSL Representational Dynamics
Kiran Kokilepersaud, Mohit Prabhushankar, Ghassan AlRegib
Under review at NeurIPS 2026
In this work, we study SSL training dynamics in terms of both mutual information between projection and representation spaces as well as in terms of overall dimensionality.
Countering Multi-modal Representation Collapse through Rank-targeted Fusion
Seulgi Kim, Kiran Kokilepersaud, Mohit Prabhushankar, Ghassan AlRegib
Winter Applications on Computer Vision (WACV) 2026
In this work, we introduce an adaptive representational alignment strategy for multi-modal learning based on the rank associated with an SVD matrix decomposition. The intuition behind this work is to ensure an equal contribution of information from both modalities. We show theoretical and empirical analyses across multi-modal fusion frameworks with a focus on time series video recognition tasks.
Countering Multi-modal Representation Collapse through Rank-targeted Fusion
Seulgi Kim, Kiran Kokilepersaud, Mohit Prabhushankar, Ghassan AlRegib
Winter Applications on Computer Vision (WACV) 2026
In this work, we introduce an adaptive representational alignment strategy for multi-modal learning based on the rank associated with an SVD matrix decomposition. The intuition behind this work is to ensure an equal contribution of information from both modalities. We show theoretical and empirical analyses across multi-modal fusion frameworks with a focus on time series video recognition tasks.
HEX: Hierarchical Emergence Exploitation in Self-Supervised Algorithms
Kiran Kokilepersaud, Seulgi Kim, Mohit Prabhushankar, Ghassan AlRegib
Winter Applications on Computer Vision (WACV) 2025 ORAL
In this work, we introduce an SSL regularization strategy based on localized hierarchical relationships. We show that this method can be added on to a wide variety of SSL approaches to improve performance.
HEX: Hierarchical Emergence Exploitation in Self-Supervised Algorithms
Kiran Kokilepersaud, Seulgi Kim, Mohit Prabhushankar, Ghassan AlRegib
Winter Applications on Computer Vision (WACV) 2025 ORAL
In this work, we introduce an SSL regularization strategy based on localized hierarchical relationships. We show that this method can be added on to a wide variety of SSL approaches to improve performance.
Clinically Labeled Contrastive Learning for OCT Biomarker Classification
Kiran Kokilepersaud, Stephanie Trejo Corona, Mohit Prabhushankar, Ghassan AlRegib, Charles Wykoff
IEEE Journal of Bio Health Informatics 2023
In this work, we demonstrate that clinical information can be used in SSL algorithms to inform the related task of biomarker detection. This shows that one modality can act as guiding information for a contrastive learning algorithm.
Clinically Labeled Contrastive Learning for OCT Biomarker Classification
Kiran Kokilepersaud, Stephanie Trejo Corona, Mohit Prabhushankar, Ghassan AlRegib, Charles Wykoff
IEEE Journal of Bio Health Informatics 2023
In this work, we demonstrate that clinical information can be used in SSL algorithms to inform the related task of biomarker detection. This shows that one modality can act as guiding information for a contrastive learning algorithm.
OLIVES Dataset: Ophthalmic Labels for Investigating Visual Eye Semantics
Mohit Prabhushankar, Kiran Kokilepersaud*, Yash-Yee Logan*, Stephanie Trejo Corona, Ghassan AlRegib, Charles Wykoff (* equal contribution)
Neural Information Processing Systems (NeurIPS) 2022
We collaborated with a medical institution to develop one of the first multimodal time series clinical trial datasets. We demonstrate its utility to the machine learning community across tasks such as multi-modal learning, time series prediction, and self supervised learning.
OLIVES Dataset: Ophthalmic Labels for Investigating Visual Eye Semantics
Mohit Prabhushankar, Kiran Kokilepersaud*, Yash-Yee Logan*, Stephanie Trejo Corona, Ghassan AlRegib, Charles Wykoff (* equal contribution)
Neural Information Processing Systems (NeurIPS) 2022
We collaborated with a medical institution to develop one of the first multimodal time series clinical trial datasets. We demonstrate its utility to the machine learning community across tasks such as multi-modal learning, time series prediction, and self supervised learning.