Hi! I'm

DhruvAgarwal

Photograph of Dhruv Agarwal

I am a PhD student at Cornell University, advised by Aditya Vashistha. Previously, I was a Research Fellow at Microsoft Research, where I worked with Tanuja Ganu, Srinivasan Iyengar, Mohit Jain, and Manohar Swaminathan.

Research Interests

I work on Responsible AI and Human-AI Interaction. I study cultural and racial bias in generative AI models. This includes dicovering, benchmarking, and mitigating bias in AI models. I also work on AI for social good, such as in healthcare, misinformation, and sustainability. My work has been published at ACM CSCW, COMPASS, and SenSys, and has also been open-sourced by Microsoft.

Past Life :)

Prior to MSR, I graduated magna cum laude in Computer Science from Ashoka University, India. At Ashoka, I was awarded the Undergraduate Research Excellence award. I also won the Student Life Excellence award for my contributions to student life and social impact. I have played varsity-level badminton and football/soccer, and national-level tennis.

Resources for Students/Applicants

Awards

  • Quad Fellow, 2023
  • Cornell University Fellow, 2022
  • Methods Recognition Award, CSCW 2021
  • Best Paper, COMPASS 2020
  • Undergraduate Research Excellence Award (Top 2)
  • Student Life Excellence (<1%; for social impact)

Publications

1. Steering AI-driven Personalization of Scientific Text for General Audiences

Taewook Kim, Dhruv Agarwal, Jordan Ackerman, Manaswi Saha

Under Review

coming soon


2. AI Agents Mitigate Racial Bias in Large Language Models

Dhruv Agarwal, Taewook Kim, Manaswi Saha, Jordan Ackerman

In progress


3. AI Suggestions Homogenize Writing Toward Western Styles and Diminish Cultural Nuances

Dhruv Agarwal, Mor Naaman, Aditya Vashistha

Under review

arXiv


4. "One Style Does Not Regulate All": Moderation Practices in Public and Private WhatsApp Groups

Farhana Shahid, Dhruv Agarwal, Aditya Vashistha

CSCW 2025

arXiv


5. Conversational Agents to Facilitate Deliberation on Harmful Content in WhatsApp Groups

Dhruv Agarwal, Farhana Shahid, Aditya Vashistha

CSCW 2024

arXiv | Video


6. “If it is easy to understand then it will have value”? Examining Perceptions of Explainable AI with Community Health Workers in Rural India

Dhruv Agarwal*, Chinasa T. Okolo*, Nicola Dell, Aditya Vashistha

CSCW 2024

ACM DL | PDF


7. PollutionMapper: Identifying Global Air Pollution Sources

Dhruv Agarwal, Srinivasan Iyengar, Pankaj Kumar

COMPASS 2023

Overview | ACM DL | PDF | Video | Code


8. India’s “Aadhaar” Biometric ID: Structure, Security, and Vulnerabilities

Dhruv Agarwal*, Pratyush Ranjan Tiwari*, Prakhar Jain, Swagam Dasgupta, Preetha Datta, Vineet Reddy, Debayan Gupta

Financial Crypto 2022

PDF | Video


9. Understanding Driver-Passenger Interactions in Vehicular Crowdsensing

Dhruv Agarwal, Srishti Agarwal, Vidur Singh, Rohita Kochupillai, Rosemary Pierce-Messick, Srinivasan Iyengar, Mohit Jain

CSCW 2021 | Methods Recognition Award

Overview | PDF | Video


10. Modulo: Drive-by Sensing at City-scale on the Cheap

Dhruv Agarwal, Srinivasan Iyengar, Manohar Swaminathan, Eash Sharma, Ashish Raj, Aadithya Hatwar

COMPASS 2020 | Best Paper Award

Overview | PDF | Video | Code


11. An Alternative to India's Reservation Policy: A Unified Framework for Rigorous and Adaptive Measurement of Socio-Economic Status [Poster]

Dhruv Sinha, Ojas Sahasrabudhe, Dhruv Agarwal, Debayan Gupta

COMPASS 2020

ACM DL | PDF


12. System for vehicle selection in drive-by sensing [Poster]

Dhruv Agarwal, Srinivasan Iyengar, Manohar Swaminathan

SenSys 2019

ACM DL | PDF


Projects for Fun

Ashoka Bot

Python (+ Flask), Facebook APIs

A Messenger bot I developed as a weekend hack to give Ashoka University users information about mess menu, shuttle timings and important phone numbers. The bot has received and sent over 80k messages to over 600 unique users since it was started in March 2017.

VAHN: Vehicle Accident Hazard Notifier

TF Object Detection API, Socket.io, Python, Node.js

A real-time smart city system for automatic detection and reporting of road accidents, using a machine learning and vision algorithm, for reduced relief response time and avoiding chaining of accidents. Adjudged 5th best project out of 400 teams at HackIIIT-D 2018.

Fake News Challenge: Stance Detection

NLP (TF-IDF, BoW), Keras, Python, SciPy stack

Undertook the Fake News Challenge to distinguish between the following relationships between a news headline and an article body: unrelated, agree, disagree, discuss. We got comparable (if not better) results than winners of the competition (although we did break some rules of the competition!).

Energy Sensing System

Arduino, Raspberry Pi, Python (+ Flask), MySQL

We developed a device that could be placed in dorm rooms at Ashoka to monitor wastage of energy. We used multiple sensors to detect whether energy was being wasted in the form of unnecessary use of lights and AC, and displayed the information on a user-friendly web app.

Beating Facial Image Obfuscation

Keras, Python, SciPy stack

A machine learning model (autoencoder) to beat common forms of facial obfuscation like blurring and pixelation. In addition, we defined another obfucation model, "blocking", to beat our model and hence show limitations of our model. We also tried generative models like GANs and variational autoencoders, which did not give good results for this task.

Thor: Online Code Judge

Python (+ Flask), PHP, MySQL

An online code judge (like CodeChef) intended to be used for programming contests within my University. This platform was eventually used by the instructor for programming assignment submissions in the CS101 course in Spring 2016.