I’m Ashmit Khandelwal, final year Computer Science student at BITS Pilani, Machine Learning Research Intern at Adobe, Research Assistant at University of Pittsburgh, and core member at SAiDL. I’m broadly interested in Vision, Language, and the relation between these media and their consumers.

My research experiance spans working with:

  Yaman Kumar at Adobe Research

  Adriana Kovashka at University of Pittsburgh

  APPCAIR at BITS Pilani

  Sravan Danda at BITS Pilani

My recent research work - “Large Content And Behavior Models To Understand, Simulate, And Optimize Content And Behavior”, done in collaboration with Adobe Research, has been accepted as a Spotlight paper at the International Conference on Learning Representations (ICLR) 2024.

I’ve worked on simulating human behavior using large language models, integrating vision in language models, semi-supervised segmentation, neural network pruning, Bayesian networks, and mass data scraping and processing. Check out my CV for more details.

Updates

Jan ‘24 - “Large Content And Behavior Models To Understand, Simulate, And Optimize Content And Behavior” has been accepted as a Spotlight paper at ICLR 2024!

Sep ‘23 - My work on “Large Content And Behavior Models To Understand, Simulate, And Optimize Content And Behavior” is available on arXiv.

Jun ‘23 - I’ll be working remotely with Dr. Adriana Kovashka at the University of Pittsburgh as a Research Assistant.

Jan ‘23 - I’ll be working as a Research Assistant with APPCAIR and Wadhwani AI during the spring semester.

Nov ‘22 - I’ll be joining Adobe Media and Data Science Research as a Research Intern.

Nov ‘22 - I’ll be an instructor for the Introduction to ML and DL course by Center of Technical Education, BITS Pilani, Goa.

July ‘22 - I’ll be an instructor for the Introduction to Deep Learning course by Quark Controls, BITS Pilani - Goa.

May ‘22 - Interning at National Centre for Polar and Ocean Research, working on Antarctic weather forecasting research.