Vinayak Gupta

ML Researcher
Lawrence Livermore National Lab
Download CV

Research Interests

AI for Time Series and Health: Algorithms and benchmarks (including language models) for time series derived from medical records, health devices, and recommender systems. Also training foundational models for sequential biological data such as amino acids and nucleic acids.

Education

Ph.D. in Machine Learning.

Indian Institute of Technology (IIT), Delhi

B.Tech. in Computer Science.

Indian Inst. of Info. Tech. (IIIT), Jabalpur

About Me

I am a Researcher in the AI research group (AIRG) at the Lawrence Livermore National Lab. Previously, I was a Postdoctoral Scholar at the Paul G. Allen School of Computer Science, University of Washington, where I worked with Tim Althoff, an AI Scientist at IBM Research, and also held positions as an Applied Scientist Intern at Amazon and an R&D Intern at Siemens.

My research advances methods for modeling medical and temporal data, combining techniques from machine learning and LLMs to drive progress in genomics, drug discovery, and personalized recommendations. My work has been featured in multiple media outlets, including IBM blogs, and recognized as "One of the biggest revelations of 2024". I was IIT Delhi's nominee for the ACM SIGKDD and ACM Doctoral Dissertation Awards, featured on IndiaAI by the Ministry of IT, Government of India, was a runner-up in NASSCOM's AI Gamechangers of India, and received the Outstanding Doctoral Paper Award at the conference on AI-ML Systems.

Selected Publications (View All )

Differentiable Adversarial Attacks for Marked Temporal Point Processes.
Pritish Chakraborty*, Vinayak Gupta*, Rahul R, Srikanta Bedathur, and Abir De.
AAAI Conference on Artificial Intelligence (AAAI), 2025.
Cost-Effective Biological Data Analysis via a Benchmark and Ensemble of LLMs.
Vinayak Gupta, B. Bartoldson, J. Wakim, J. Allen, J. M. Marti, Tianlong Chen, and Bhavya Kailkhura.
U.S. Office of Scientific and Technical Information (OSTI), 2025. (Limited Release)
Are Language Models Actually Useful for Time Series Forecasting?
Mingtian Tan, Mike A. Merrill, Vinayak Gupta, Tim Althoff, and Tom Hartvigsen.
Neural Information Processing Systems (NeurIPS), 2024. (Spotlight Paper)
Language Models Still Struggle to Zero-shot Reason about Time Series.
Mike A. Merrill, Mingtian Tan, Vinayak Gupta, Tom Hartvigsen, and Tim Althoff.
Emperical Methods in Natural Langauge Processing (EMNLP), 2024.
SPML: A DSL for Defending Language Models Against Prompt Attacks.
Reshabh K Sharma, Vinayak Gupta, and Dan Grossman.
Dataset Paper, 2024. (7k+ downloads/month on Hugging Face)
Learning Temporal Point Processes for Efficient Retrieval of Continuous Time Event Sequences.
Vinayak Gupta, Srikanta Bedathur, and Abir De.
AAAI Conference on Artificial Intelligence (AAAI), 2022.
ProActive: Self-Attentive Temporal Point Process Flows for Activity Sequences.
Vinayak Gupta and Srikanta Bedathur.
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2022.
Learning Temporal Point Processes with Intermittent Observations.
Vinayak Gupta, Srikanta Bedathur, Sourangshu Bhattacharya, and Abir De.
International Conference on Artificial Intelligence and Statistics (AISTATS), 2021.