← Meet the rest of the cohort
Divyam Madaan

Divyam Madaan

Multimodal learning for smarter medical data collection

PhD Candidate

New York University

Your week at a glance

  • Small group — you facilitate Group 1 · Orion on Day 3 (Evaluation).
  • Job talk — Day 6 (Sat, Jun 27), 10:35 AM · Room A · Alder 107 — “From Complete to Missing Modalities: A Framework for Multimodal Learning”.
  • Poster — Day 7 (Sun, Jun 28) · Session B (10:30–11:30 AM).

Divyam Madaan is a fifth-year Ph.D. candidate at New York University, advised by Sumit Chopra and Kyunghyun Cho. His research focuses on developing models that can effectively learn from multiple modalities and generalize across distribution shifts, with a special emphasis on healthcare applications.

Prior to NYU, he earned his M.S. in Computer Science from KAIST, where he worked on model robustness against adversarial examples and continual adaptation to evolving data and architectures. His work has been published at leading venues including ICML, NeurIPS, CVPR and ICLR, where he has also been recognized with oral and spotlight presentation awards.

Awards & honors

Recognition

  • CVPR Spotlight, top 10% of submissions (2023)
  • ICLR Oral, top 1.6% of submissions (2022)
  • NeurIPS Top Reviewer, top 0.1% of reviewers (2022)
  • NYU MacCracken PhD Fellowship (2021-present)
  • ICML Top Reviewer, top 30% of reviewers (2020)
  • KAIST International Students Scholarship (2019-2021)