Hi, I am a fourth year Ph.D. student at New York University, Courant Institute of Mathematical Sciences, under the supervision of Sumit Chopra and Kyunghyun Cho. Previously, I completed my Masters at Machine Learning and Artificial Intelligence (MLAI) Lab in Korea Advanced Institute of Science and Technology (KAIST), where I was advised by Sung Ju Hwang. My research has two primary objectives: (a) develop methods that can harness information from multiple modalities, and (b) improve the model's ability to perform consistently in future time periods.

Publications

A Framework for Multi-modal Learning: Jointly Modeling Inter- & Intra-Modality Dependencies
Divyam Madaan , Taro Makino, Sumit Chopra, Kyunghyun Cho
Neural Information Processing Systems (NeurIPS) 2024 CONFERENCE
PDF Code

Predicting Alzheimer’s Diseases and Related Dementias in 3-year timeframe with AI Foundation Model on Electronic Health Records
Weicheng Zhu, Huanze Tang, Hao Zhang, Haresh Rengaraj Rajamohan, Shih-Lun Huang, Xinyue Ma, Ankush Chaudhari, Divyam Madaan, Elaf Almahmoud, Sumit Chopra, John A Dodson, Abraham A Brody, Arjun V Masurkar, Narges Razavian
Alzheimer’s Association International Conference 2024 CONFERENCE
PDF

Heterogeneous Continual Learning
Divyam Madaan, Hongxu Yin, Wonmin Byeon, Jan Kautz, Pavlo Molchanov
Conference on Computer Vision and Pattern Recognition (CVPR) 2023 (Highlight) CONFERENCE
PDF Code Video

What Do NLP Researchers Believe? Results of the NLP Community Metasurvey
Julian Michael, Ari Holtzman, Alicia Parrish, Aaron Mueller, Alex Wang, Angelica Chen, Divyam Madaan, Nikita Nangia, Richard Yuanzhe Pang, Jason Phang, Samuel R. Bowman
Association for Computational Linguistics (ACL) 2023 CONFERENCE
PDF

On Sensitivity and Robustness of Normalization Schemes to Input Distribution Shifts in Automatic MR Image Diagnosis
Divyam Madaan, Daniel Sodickson, Kyunghyun Cho, Sumit Chopra
Medical Imaging with Deep Learning (MIDL) 2023 CONFERENCE
PDF

Representational Continuity for Unsupervised Continual Learning.
Divyam Madaan, Jaehong Yoon, Yuanchun Li, Yunxin Liu, Sung Ju Hwang.
International Conference on Learning Representations (ICLR) 2022 (Oral presentation) CONFERENCE
PDF Code Video Slides

Online Coreset Selection for Rehearsal-based Continual Learning.
Jaehong Yoon, Divyam Madaan, Eunho Yang, Sung Ju Hwang.
International Conference on Learning Representations (ICLR) 2022 CONFERENCE
PDF Video

Learning to Generate Noise for Multi-Attack Robustnesss
Divyam Madaan, Jinwoo Shin, Sung Ju Hwang.
International Conference for Machine Learning (ICML) 2021 CONFERENCE
NeurIPS Meta-Learning Workshop 2020 WORKSHOP
PDF Code Video Slides

Adversarial Neural Pruning with Latent Vulnerability Suppression
Divyam Madaan, Jinwoo Shin, Sung Ju Hwang.
International Conference for Machine Learning (ICML) 2020 CONFERENCE
NeurIPS Safety and Robustness in Decision Making Workshop 2019 WORKSHOP
PDF Code Video Slides

VayuAnukulani: adaptive memory networks forair pollution forecasting
Divyam Madaan, Radhika Dua, Prerana Mukherjee, and Brejesh Lall.
IEEE Global Conference on Signal and Information Processing (GlobalSIP) 2019CONFERENCE
PDF Code Slides

Learning sparse networks using targeted dropout
Aidan N. Gomez, Ivan Zhang, Siddhartha Rao Kamalakara, Divyam Madaan, Kevin Swersky, Yarin Gal, and Geoffrey E.Hinton
Preprint 2019 PREPRINT
PDF Code

I can also be found on Google Scholar.

Academic Service

  • Conference reviewer
    • NeurIPS (2020 – 2024)
    • ICML (2020 – 2024)
    • ICLR (2022 – 2025)
    • AAAI 2021
    • ACML 2020
  • Workshop reviewer
    • NeurIPS MetaLearning workshop 2020
    • ICML New Frontiers in Adversarial Machine Learning Workshop 2020
  • Volunteer
    • ICLR (2020, 2022)
    • ICML (2020, 2021)
    • NeurIPS (2020, 2022)