Dipesh Tamboli

Dipesh Tamboli

Research Scientist at Meta

I am a Research Scientist at Meta, working on alignment, privacy-preserving training, and trustworthiness evaluation for large language and foundation models.

I completed my PhD in Electrical and Computer Engineering at Purdue University in 2025, advised by Prof. Vaneet Aggarwal, where I worked on trustworthy and generative AI. During my PhD, I interned at Meta (2024) and at Amazon Robotics as an Applied Scientist (2023). Earlier, I was a Machine Learning Researcher at AWL Inc., working on self-supervised learning for object detection.

I finished my undergrad at IIT Bombay with a major in Electrical Engineering and a minor in Computer Science, advised by Prof. Biplab Banerjee and Prof. Subhasis Chaudhuri. During my undergrad, I interned at AWL Inc., the Video Analytics Laboratory (VAL) at IISc Bangalore with Prof. R. Venkatesh Babu, at UC San Diego with Prof. Pengtao Xie, and at VAIL Labs, Oxford with Prof. Fabio Cuzzolin.

Journey

Timeline

IISc Β· VAL
2019
IISc Bangalore
AWL Inc.
2021
AWL Inc.
Amazon Robotics
2023
Amazon Robotics
Meta (intern)
2024
Meta
Jawahar Navodaya Vidyalaya
Navodaya
2010–2015
Dakshana Foundation
Dakshana
2015–2017
IIT Bombay
IIT Bombay
2017–2021
Purdue University
Purdue
2021–2025
Meta
Meta
2025–present

Recent

News

  • 2026PRIVATEEDIT published in IEEE Transactions on AI (patent-pending) β€” featured across national & international press.
  • 2026TARo accepted to ACL 2026 Findings; BalancedDPO published in TMLR.
  • 2026Received the ICML 2026 Gold Reviewer Award.
  • 2025Completed my PhD at Purdue and joined Meta as a Research Scientist.

Alignment Β· Privacy Β· Trustworthy ML Β· RL for LLMs

Selected Publications

265 citations Β· h-index 9 Β· i10-index 9 β€” Google Scholar.

IEEE TAI2026Journal

PRIVATEEDIT: A Privacy-Preserving Pipeline for Face-Centric Generative Image Editing

Dipesh Tamboli, Vineet Punyamoorty, Atharv Pawar, Vaneet Aggarwal

IEEE Transactions on Artificial Intelligence (TAI)

First author Patent-pending In the news arXiv
TMLR2026Journal

BalancedDPO: Adaptive Multi-Metric Alignment

Dipesh Tamboli, Souradip Chakraborty, Aditya Malusare, Biplab Banerjee, Amrit Singh Bedi, Vaneet Aggarwal

Transactions on Machine Learning Research (TMLR)

First author Page arXiv
ACL2026Conference

TARo: Token-level Adaptive Routing for LLM Test-time Alignment

Arushi Rai, Qiang Zhang, Hanqing Zeng, Yunkai Zhang, Dipesh Tamboli, Xiangjun Fan, Zhuokai Zhao, Lizhu Zhang

Findings of the Association for Computational Linguistics (ACL Findings)

Meta ACL arXiv
ICML2023Conference

Multi-task Hierarchical Adversarial Inverse Reinforcement Learning

Jiayu Chen, Dipesh Tamboli, Tian Lan, Vaneet Aggarwal

International Conference on Machine Learning (ICML)

28 citations PMLR
See all publications (18) β†’

Recognition

Awards

  • πŸ₯‡ICML 2026 β€” Gold Reviewer Award
  • ⭐CVPR 2025 β€” Outstanding Reviewer
  • πŸ†IEEE WIECON-ECE 2019 β€” Best Paper