Akshita Kamsali

185, BHEE

465 Northwestern Ave

West Lafayette, IN

I am a PhD Candidate in Electrical and Computer Engineering at Purdue University and a member of the Robot Vision Lab, advised by Dr. Avi Kak. My research is in deep learning, focusing on interpretabilty solutions for deep learning models. I have had the opportunity to work with various industry collaborators for real-life problem solving throughout my PhD. Proficient in Python, PyTorch, and Deep Learning, I also bring strong skills in scientific communication, public speaking, and presentations, enabling me to effectively bridge research and impactful real-world applications.

I have also interned at Lawrence Livermore National Lab, was a Top-presenter featured in LLNL newsletter and Purdue ECE top news.

For a detailed overview of my academic and professional journey, you can view my resume.

Let’s connect and explore how technology can transform the way we perceive and solve problems!

News

May 19, 2026	Podcast on my PhD and internship experiences YouTube, Spotify, Apple Podcasts, LinkedIn
May 19, 2026	Returning as a Research Intern in CASC/MED @LLNL mentored by Aldair Gongora and Kowshik Thopalli.
Mar 28, 2026	Successfully defended my PhD preliminary examination. Officially, a PhD Candidate in Electrical and Computer Engineering at Purdue University.
Oct 18, 2025	Attending NeurIPS 2025 and organizing Women in Machine Learning Workshop
Aug 18, 2025	GTA for ECE20875 Python for DataScience
May 20, 2025	Starting as a Research Intern at Data Science Institute @LLNL mentored by Aldair Gongora
Mar 11, 2025	Awarded Outstanding Service Award 2025 by College of Engineering for service to ECE

Selected Publications

Digital Discovery

Benchmarking Deep Learning Models for Raman Spectroscopy Across Open-Source Datasets

Sineesh, Adithya, and Kamsali, Akshita Ramya

Digital Discovery 2026
NeurIPS-Workshop

From Sensing to Reasoning: Multi-Modal Large Language Models Guiding Robotic Intelligence in Autonomous Labs

Kamsali, Akshita Ramya, Hallas, Kristen, and Gongora, Aldair E.

In Women in Machine Learning Workshop @ NeurIPS 2025 2025
NeurIPS-Workshop

Speak, Start, See, Sense: How NLP, Robotics, and Computer Vision can Improve Automated Experimentation in Self-driving Labs

Hallas, Kristen, Allaparti, Tarun, Kamsali, Akshita Ramya, and Gongora, Aldair E.

In Women in Machine Learning Workshop @ NeurIPS 2025 2025
NeurIPS-Workshop

Graph-based Change Detection for Natural Language

Kamsali, Akshita Ramya

In Women in Machine Learning Workshop @ NeurIPS 2024 Dec 2024

Abs HTML

Computational models such as machine learning (ML) and deep learning (DL) excel at processing structured data, including numbers, images, audio signals, and spectral data. These types of data can be easily converted into numerical patterns, which models can analyze to extract meaningful insights. In contrast, processing text is significantly more complex. Language is inherently rich, intricate, and nuanced. Techniques like tokenization and word embeddings, which transform text into numerical representations, often struggle to fully capture the subtle context and deeper meaning within the text. Challenges such as context dependency, disambiguation, and diverse writing styles can lead to multiple interpretations of the same text, even for humans. This complexity is further magnified in specialized domains, such as legal or medical documents. In this work we present LLM-based solution to build consistent knowledge graphs for change detection.