Image
Varshini Subhash
Download CV

Note: I am currently on the job market! I am open to machine learning and research roles such as Research Engineer, Applied Scientist, Machine Engineer, Data Scientist and alike. If you know a role that may be a good fit for me or anyone who is hiring, please feel free to reach out: varshinisubhash@alumni.harvard.edu

About

I am passionate about creating impact at the intersection of research and social good and have been working on intelligent e-commerce search at Tonita over the past year. Previously, I was a graduate student in Computer Science at Harvard, advised by Dr. Weiwei Pan and Prof. Finale Doshi-Velez. I was also nominated for the Forbes 30 Under 30 - Boston, named the Adobe Research Women-In-Technology Scholar and a Machine Learning Alignment Scholar by the Stanford Existential Risks Initiative. My research interests include AI safety, language models, interpretability and search. Prior to this, I was fortunate to be advised by Prof. Vijay Natarajan at the Indian Institute of Science, where I worked on developing parallel algorithms for computational topology and geometry.

I am generally interested in non-profit and social causes that make a positive difference. In particular, I find myself gravitating towards causes like AI safety, animal welfare and volunteering. In 2022, as part of MIT's Brave Behind Bars course, I taught Computer Science and mentored incarcerated individuals in New England prisons, which was featured in the Washington Post. I've enjoyed volunteering at the Harvard Square Homeless Shelter and volunteering backend help for the Humans of AI Podcast. In 2020, I founded a podcast to drive the conversation on gender inequity and why women belong at the table. During this time, I also led operations at Harvard’s Coronavirus Visualization Team, where my team visualized the increase in gender-based violence during COVID-19. Some of my work is listed below. Click on the links to see more details.

Outside of research, I love singing, writing and hiking. I am always open to conversation with like-minded people - feel free to reach out if anything resonates with you.

News

  • 2024: I am teaching CS 109A: Introduction to Data Science (Fall 2024) at Harvard.

  • 2024: I am serving as an Ethics Reviewer at NeurIPS 2024.

  • 2024: Our paper "Deep Learning Approach to Identify Diabetic Retinopathy Severity and Progression Using Ultra-Wide Field Retinal Images" was accepted for publication at AI for Health Equity and Fairness: Leveraging AI to Address Social Determinants of Health, 2024.

  • 2024: I am serving as an Ethics Reviewer at ICML 2024.

  • 2023: I have joined Tonita as a Research Engineer and will be working on intelligent e-commerce search.

  • 2023: I was nominated for the 2023 Forbes 30 Under 30 – Boston.

  • 2023: Our paper "Why do universal adversarial attacks work on large language models?: Geometry might be the answer" was accepted to the New Frontiers in Adversarial Machine Learning Workshop, ICML.

  • 2023: I defended my thesis at Harvard. [Slides]

  • 2023: Research Seminar on "GPU Parallel Computation of Morse-Smale Complexes" at Flagship Pioneering.

  • 2023: I was a course developer and Teaching Fellow for CS 181: Introduction to Machine Learning (Spring 2023) at Harvard.

  • 2023: Our paper "Tachyon: Efficient Shared Memory Parallel Computation of Extremum Graphs" was accepted for publication at the Computer Graphics Forum.

  • 2023: Lightning Talk, "What makes a good explanation?" at the Women in Data Science (WiDS) Conference, Cambridge.

  • 2023: My research was adapted as a graduate machine learning course CS6216: Advanced Topics in Machine Learning (Spring 2023) at the National University of Singapore (NUS).

  • 2022: Spotlight Talk, "What makes a good explanation?" at the Trustworthy Embodied AI Workshop, NeurIPS 2022.

  • 2022: I was selected as a Machine Learning Alignment Scholar and awarded $6000 by the Stanford Existential Risks Initiative to conduct research on adversarial attacks on large language models.

  • 2022: Our paper "What makes a good explanation?: A Harmonized View of Properties of Explanations" was accepted at the Trustworthy and Socially Responsible Machine Learning Workshop, NeurIPS 2022.

  • 2022: I interned with the Deep Learning Performance team at NVIDIA during the summer.

  • 2022: As part of MIT's Brave Behind Bars course, I taught Computer Science and mentored incarcerated individuals in New England prisons, which was featured in the Washington Post.

  • 2022: I was a Panelist at Harvard's IACS Research & Thesis Panel and IACS Graduate Admissions Information Panel.

  • 2022: I was selected as an Adobe Research Women-In-Technology Scholar (one among 16 across the United States awarded a prize of $10,000) and featured by Harvard University.

  • 2022: Our paper "GPU Parallel Computation of Morse-Smale Complexes", previously published and presented at the IEEE VIS Conference 2020, was accepted for publication at the IEEE Transactions on Visualization and Computer Graphics.

  • 2021: I was a Teaching Fellow for CS50: Introduction to Computer Science (Fall 2021) at Harvard.

  • 2021: Women in High Performance Computing (WHPC) Lightning Talk at the Supercomputing Conference.

  • 2021: Invited Speaker, "GPU Parallel Computation of Morse-Smale Complexes", ACM ARCS Symposium 2021. [Slides] [Poster]

  • 2020: Introducing the She Belongs Podcast, to drive conversation around gender inequality and why women belong at the table.


Publications

  • Varshini Subhash*, Zixi Chen*, Marton Havasi, Weiwei Pan, Finale Doshi-Velez, “What Makes a Good Explanation?: A Harmonized View of Properties of Explanations”, Trustworthy and Socially Responsible Machine Learning Workshop, NeurIPS 2022 | Submitted to Journal of Machine Learning Research (JMLR) | [arXiv]

  • Varshini Subhash*, Anna Bialas*, Weiwei Pan, Finale Doshi-Velez, “Why do universal adversarial attacks work on large language models?: Geometry might be the answer”, New Frontiers in Adversarial Machine Learning Workshop, ICML 2023. [arXiv]

  • Amber Nigam*, Jie Sun*, Varshini Subhash, Lloyd Paul Aiello, Paolo S Silva, Yixuan Huang, Guangze Luo, “Deep Learning Approach to Identify Diabetic Retinopathy Severity and Progression Using Ultra-Wide Field Retinal Images”, AI for Health Equity and Fairness: Leveraging AI to Address Social Determinants of Health 2024. [Springer]

  • Varshini Subhash , Karran Pandey, Vijay Natarajan, “GPU Parallel Algorithm for Computing Morse-Smale Complexes”, IEEE Transactions on Visualization and Computer Graphics | IEEE VIS Conference 2020. [IEEE Xplore]

  • Abhijath Ande, Varshini Subhash, Vijay Natarajan, “Tachyon: Efficient Shared Memory Parallel Computation of Extremum Graphs”. [Computer Graphics Forum, 2023]

  • Varshini Subhash, “Can Large Language Models Change User Preference Adversarially?”, [arXiv]