profile

Hi, I'm Gagan

Machine Learning Researcher

Microsoft AI

🚀 Featured Publications

NIPS'24
Mixture of Nested Experts teaser
Mixture of Nested Experts: Adaptive Processing of Visual Tokens
Gagan Jain, Nidhi Hegde, ...
NeurIPS 2024Mixture of ExpertsConditional Computation
TL;DR: Token-wise routing between nested experts for tackling redundancy.
ECCV'24
LookupViT teaser
LookupViT: Compressing Visual Information to a smaller number of tokens
Rajat Koner, Gagan Jain, ...
ECCV 2024VisionEfficiency
TL;DR: An asynchronous version of attention with sub-quadratic scaling and superior performance.

📰 News & Updates Archive

  • [May'25]🎉Moved to Microsoft AI. Working on Retrieval Augmented Generation.
  • [May'25]📄Decode time scaling accepted at ICML'25 & ICLR'25 Workshop.
  • [Dec'24]📄Collaborative bandits accepted at AAMAS'25! Optimal regret bounds!
  • [Dec'24]🎤Presented DL efficiency at UCLA Artificial General Intelligence Lab.
  • [May'24]🚀Joined Google DeepMind's Foundational Research Unit.
  • [Sep'23]🚀Started as Pre-doctoral Researcher at Google Research.

🌍 Visitors

Visitor Map
Last updated: June 2025