Sahil Verma

I'm a Senior Research Scientist at Voyage AI , an embedding model company now acquired by MongoDB. Previously, I completed my PhD in the Department of Computer Science at the University of Washington in Seatte.

In my PhD, I focused on ML Robustness and AI Safety research. Before that, I graduated from Indian Institute of Technology Kanpur (IIT Kanpur) in 2019 with a B.Tech in Electrical Engineering and a minor in Computer Science. I have been fortunate to work with several amazing researchers in my career. I have interned as an Applied Scientist at Microsoft Research, Amazon, and Arthur AI. During my undergrad years, I also interned at ETH Zurich, MIT, and National University of Singapore (NUS).

Email / CV / Scholar / Twitter / LinkedIn / Blog / Fun

Experiences

2026 - Senior Research Scientist, Voyage AI (acquired by MongoDB)
2019 - 2025 PhD in Computer Science and Engineering, University of Washington, Seattle
Summer, 2024 Research Intern, Deep Learning Group at Microsoft Research
Summer, 2023 Applied Scientist Intern, Amazon
Summer, 2022 Applied Scientist Intern, Amazon
Summer, 2021 Research Scientist Intern, Arthur AI
Summer, 2019 Research Intern, ETH Zurich
Summer, 2018 Research Intern, MIT
Summer, 2017 Research Intern, National University of Singapore
2015 - 2019 B.Tech in Electrical Engineering, IIT Kanpur

If you have any questions or want to collaborate, please reach out via email or Twitter! Always happy to chat.

Research

	OMNIGUARD: An Efficient Approach for AI Safety Moderation Across Modalities Sahil Verma, Keegan Hines, Jeff Bilmes, Charlotte Siska, Luke Zettlemoyer, Hila Gonen, Chandan Singh Accepted as Oral at EMNLP 2025 Main Conference We develop an method that can detect harmful prompts across multiple languages and modalities just using the same approach. Omniguard leverages the universal shared embeddings produced by models internally and builds a classifier that achieves SOTA performance in text, image, and audio jailbreak detection.
	How Many Van Goghs Does It Take to Van Gogh? Finding the Imitation Threshold Sahil Verma, Royi Rassin, Arnav Das, Gantavya Bhatt, Preethi Seshadri, Chirag Shah, Jeff Bilmes, Hannaneh Hajishirzi, Yanai Elazar Accepted at TMLR and as the Best Oral Paper Award at BUGS Workshop at NeurIPS 2023 We ask "how many images of a concept does a text-to-image model need for its imitation?". We posit this question as a new problem: Finding the Imitation Threshold (FIT) and propose an efficient approach (MIMETIC²) that estimates the imitation threshold without incurring the colossal cost of training multiple models from scratch.
	Effective Backdoor Mitigation Depends on the Pre-training Objective Sahil Verma, Gantavya Bhatt, Avi Schwarzschild, Soumye Singhal, Arnav Das, Chirag Shah, John P Dickerson, Jeff Bilmes Accepted at TMLR and Best Oral Paper Award at BUGS Workshop at NeurIPS 2023 We demonstrate that the effectiveness of backdoor removal techniques is highly dependent on the pre-training objective of the model. Based on the empirical findings, we suggest practitioners to train multimodal models using the simple constrastive loss owing to its amenability to be cleaned of backdoors.
	RecRec: Algorithmic Recourse for Recommender Systems Sahil Verma, Ashudeep Singh, Varich Boonsanong, John P Dickerson, Chirag Shah Accepted as a short paper at CIKM 2023 We propose RecRec that provides recourse for content creators of a recommender system, an often ignored community in the recommender system interpretability research.
	Post-Hoc Attribute-Based Explanations for Recommender Systems Sahil Verma, Chirag Shah, John P. Dickerson, Anurag Beniwal, Narayanan Sadagopan, Arjun Seshadri Best Student Paper Award at TEA Workshop at NeurIPS 2022 We propose RecXplainer that provide attribute based explanations for recommendations.
	Amortized Generation of Sequential Counterfactual Explanations for Black-box Models Sahil Verma, Keegan Hines, John P Dickerson Accepted at AAAI 2022 We propose FastAR, a novel stochastic-control-based approach that generates sequential recourses. FastAR is model agnostic and black box.
	Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review Sahil Verma, Varich Boonsanong, Minh Hoang, Keegan Hines, John P. Dickerson, Chirag Shah Best Paper Award at the ML-RSA Workshop at NeurIPS 2020 We survey close to 200 recently published papers about counterfactual explanations in ML.
	Removing biased data to improve fairness and accuracy Sahil Verma, Michael Ernst, Rene Just We propose a black-box approach to identify and remove biased training data to improve model fairness.
	Fairness Definitions Explained Sahil Verma and Julia Rubin We consolidate, define, and delineate over a dozen ML fairness definitions.

Teaching Experience and Community Services

	Teaching Assitant, Introduction to Software Engineering (CSE403), Fall 2023 Teaching Assitant, Introduction to Machine Learning (CSE416), Fall 2021
	Student Volunteer at ACM ESEC/FSE 2017, Paderborn, Germany Reviewer for EAAMO, XAIF, NeurIPS, AAAI, ICML, AIES, FAccT, IEEE Transactions on Artificial Intelligence, Data Mining and Knowledge Discovery, International Journal of Data Science and Analytics, and several workshops.

Template adapted from Jon Barron's website . Special thanks to our friendly AGI (in making) for assistance in customization.