Hello!

I'm Neil Sharma

PhD Student in Computer Science

I am a first year PhD student at the University of Oregon (UO) advised by Prof. Suyash Gupta. I am studying Federated Learning and privacy-preserving techniques in federated learning, especially using Differential Privacy. Before joining UO, I worked at Cisco as a Production Engineer on the Webex team, and completed a research fellowship at ISRO (Indian Space Research Organisation).

Neil Sharma

About Me

I am a PhD student in Computer Science at the University of Oregon, working in the Distopia Lab. My research focuses on privacy-preserving federated learning and machine unlearning, with emphasis on developing computationally efficient methods for federated unlearning.

My academic journey has taken me through Manipal University (Bachelor's) and Stevens Institute of Technology (Master's) before joining University of Oregon for my PhD. I bring a unique combination of industry experience from Cisco and Chubb Insurance, along with research experience at ISRO and MNIT.

Research Interests

Federated Learning
Privacy-Preserving ML
Machine Unlearning
Natural Language Processing
Multimodal AI
Differential Privacy

Research

Current Research

Caffeine: Computationally Efficient Federated Unlearning

Machine unlearning—the ability to remove the influence of specific data from a trained model—is crucial for privacy compliance (GDPR's "right to be forgotten"). However, in federated learning settings, unlearning becomes particularly challenging due to the distributed nature of data and computation.

Caffeine addresses this challenge by developing computationally efficient methods for federated unlearning that avoid costly complete model retraining while maintaining model performance and providing formal privacy guarantees.

Federated Learning Machine Unlearning Privacy-Preserving ML

Past Research Projects

ISRO ChatBot

Developed a multimodal RAG-based chatbot using large language models for ISRO technical documentation.

LLMs RAG Multimodal AI

Video Surveillance Anomaly Detection

Built real-time anomaly detection models for video surveillance systems using computer vision.

Computer Vision Deep Learning

Sentiment Analysis

Developed NLP models for analyzing customer sentiment in cell phone reviews.

NLP Sentiment Analysis

Employee Attrition Prediction

Created ML models to predict employee turnover with interpretable insights for HR.

ML Data Analysis

Publications

2025

Caffeine: Computationally Efficient Federated Unlearning

Neil Sharma

Middleware 2025 - Doctoral Symposium

This work presents Caffeine, a novel approach to federated unlearning that addresses the computational challenges of removing data influence from distributed machine learning models without complete retraining.

2025

TheoremView: A Framework for Extracting Theorem-Like Environments from Raw PDFs

Shrey Mishra, Neil Sharma, Antoine Gauquier, Pierre Senellart

ECIR 2025 - European Conference on Information Retrieval

TheoremView introduces a novel approach to mathematical document search and retrieval, combining traditional information retrieval with mathematical formula understanding.

2025

MERIT: Multimodal Enhanced Retrieval and Integration of Text and Images

Neil Sharma, Namita Mittal, Munish Singh

ISAI 2025 - International Symposium on Artificial Intelligence

MERIT presents a unified framework for learning multimodal embeddings that excel at both retrieval and downstream information tasks across text, image, and structured data modalities.

2025

DIVERGEMENT: Domain-Tailored, Small-Model Natural Language to SQL Pipeline for Space Research Domain

Garvit Tibrewal, Neil Sharma, Naman Mittal

AusDM 2025 - Australasian Data Mining Conference Submitted

DIVERGEMENT introduces innovative methods for analyzing divergent data patterns in complex datasets with applications in anomaly detection and distribution shift analysis.

Experience

2023 - Present

Graduate Research Assistant

University of Oregon - Distopia Lab

Working on privacy-preserving federated learning and machine unlearning. Published paper at Middleware 2025 Doctoral Symposium on the Caffeine project.

Federated Learning Privacy-Preserving ML Python PyTorch
2024 - Present

Graduate Teaching Assistant

University of Oregon - CS Department

Teaching Introduction to Software Engineering. Topics: Git/GitHub, Docker, CI/CD, Agile methodologies, and software testing.

Git Docker CI/CD
2023

Research Fellow

Indian Space Research Organisation (ISRO)

Developed multimodal RAG-based chatbot using large language models for technical documentation and knowledge management.

LLMs RAG NLP
2021 - 2022

Production Engineer

Cisco Systems - Webex Team

Maintained production infrastructure for Webex services. Implemented monitoring systems, optimized microservices, and improved system reliability.

Kubernetes Docker Python Microservices
2020 - 2021

Data Analyst / ML Engineer

Chubb Insurance

Built machine learning models for employee attrition prediction and insurance risk assessment. Conducted data analytics for business insights.

Python Scikit-learn SQL

Teaching

Introduction to Software Engineering

University of Oregon | Fall 2024 - Present | Graduate Teaching Assistant

Conducting lab sessions and mentoring students on modern software development practices. Topics include version control, containerization, CI/CD pipelines, and Agile methodologies.

Topics Covered

Git & GitHub
Docker & Containers
CI/CD Pipelines
Software Testing
Agile & Scrum
Code Review

Office Hours

By appointment
Email to schedule

Teaching Philosophy

Hands-on learning with real-world projects and industry-relevant skills.

Get In Touch

Location

Department of Computer Science
University of Oregon
Eugene, OR 97403

Connect

Interested in collaboration?

I'm always open to discussing research collaborations, industry projects, or speaking opportunities related to privacy-preserving machine learning and federated learning.

Send Email