Arvind Pillai

Arvind Pillai

Machine Learning  ·  Healthcare

I am a senior PhD student at Dartmouth College, advised by Prof. Andrew Campbell. My research develops machine learning techniques to study health in real-world settings, drawing on data from wearable devices and mobile phone sensors. I am currently focused on Health Foundation Models. To this end, I have developed PaPaGei, the first open-source foundation model for Photoplethysmography (PPG) [ICLR’25], and proposed Time2Lang, a framework to integrate time-series foundation models with LLMs [CHIL’25]; LENS, a system that aligns multimodal sensing with LLMs for mental health narrative synthesis [ACL’26]; and SLIP, a method for learning transferable sensor models via language-informed pretraining [ICLR’26 Workshop].

Previously I was a Student Researcher at Google (Cambridge, MA) and a Research Intern at Nokia Bell Labs (Cambridge, UK). Before my PhD I spent two years as an AI & Data Graduate Scientist at AstraZeneca.

News

April 2026 LENS accepted to ACL 2026 (Main)!
Oct 2025 College Experience Study wins Distinguished Paper Award at UbiComp 2025. 🏆 Award
Jun 2025 Starting as a Student Researcher at Google, Cambridge, MA.
Apr 2025 Time2Lang accepted to CHIL 2025.
Jan 2025 PaPaGei accepted to ICLR 2025.
Dec 2024 PaPaGei wins Best Paper Award at the NeurIPS Time Series in the Age of Large Models Workshop. 🏆 Award
Oct 2024 PaPaGei foundation model released with paper, models, and code.
Jun 2024 Interning at Nokia Bell Labs, Cambridge, UK.
May 2024 Presented MoodCapture at CHI 2024 in Honolulu.

Selected Publications

See all →
2026

LENS: LLM-Enabled Narrative Synthesis for Mental Health by Aligning Multimodal Sensing with Language Models

Wenxuan Xu*, Arvind Pillai*, Tess Griffin, Amanda C Collins, Michael Heinz, Damien Lekkas, Shayan Mirjafari, Matthew Nemesure, George Price, Nicholas Jacobson, Andrew Campbell (*equal contribution)

ACL 2026 — Annual Meeting of the Association for Computational Linguistics

2025

Time2Lang: Bridging Time-Series Foundation Models and Large Language Models for Health Sensing Beyond Prompting

Arvind Pillai, Dimitris Spathis, Subigya Nepal, Amanda C Collins, Daniel M Mackin, Michael V Heinz, Tess Z Griffin, Nicholas C Jacobson, Andrew Campbell

CHIL 2025 — Conference on Health, Inference, and Learning

2025

PaPaGei: Open Foundation Models for Optical Physiological Signals

Arvind Pillai, Dimitris Spathis, Fahim Kawsar, Mohammad Malekzadeh

ICLR 2025 — International Conference on Learning Representations

🏆 Best Paper Award — NeurIPS Time Series Workshop 2024
2024

MoodCapture: Depression Detection Using In-the-Wild Smartphone Images

Subigya Nepal*, Arvind Pillai*, Weichen Wang, Tess Griffin, Amanda C Collins, Michael Heinz, Damien Lekkas, Shayan Mirjafari, Matthew Nemesure, George Price, et al. (*co-primary)

CHI 2024 — ACM Conference on Human Factors in Computing Systems

Experience

See all →

Student Researcher

Google

Summer 2025  ·  Cambridge, MA

Research Intern

Nokia Bell Labs

Summer 2024  ·  Cambridge, UK

AI & Data Graduate Scientist

AstraZeneca

2019 – 2021