My research focuses on (a) developing methods that harness information from multiple modalities, and (b) improving models' ability to generalize across time.
Divyam Madaan is a fifth-year Ph.D. student 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.
@inproceedings{madaan2026multimodal,
title={Multi-modal Data Spectrum: Multi-modal Datasets are Multi-dimensional},
author={Madaan, Divyam and Muhunthan, Varshan and Cho, Kyunghyun and Chopra, Sumit},
booktitle={International Conference on Learning Representations},
year={2026}
}
@inproceedings{madaan2024jointly,
title={Jointly Modeling Inter- & Intra-Modality Dependencies for Multi-modal Learning},
author={Madaan, Divyam and Makino, Taro and Chopra, Sumit and Cho, Kyunghyun},
booktitle={Advances in Neural Information Processing Systems},
year={2024}
}
@inproceedings{huang2024histaid,
title={HIST-AID: Leveraging Historical Patient Reports for Enhanced Automatic Diagnosis},
author={Huang, Haoxu and Deniz, Cem M and Cho, Kyunghyun and Chopra, Sumit and Madaan, Divyam},
booktitle={Machine Learning for Health},
year={2024}
}
@inproceedings{zhu2024predicting,
title={Predicting Alzheimer's Diseases and Related Dementias in 3-year timeframe with AI Foundation Model on Electronic Health Records},
author={Zhu, Weicheng and others},
booktitle={Alzheimer's Association International Conference},
year={2024}
}
@inproceedings{madaan2023heterogeneous,
title={Heterogeneous Continual Learning},
author={Madaan, Divyam and Yin, Hongxu and Byeon, Wonmin and Kautz, Jan and Molchanov, Pavlo},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year={2023}
}
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
@inproceedings{michael2023nlp,
title={What Do NLP Researchers Believe? Results of the NLP Community Metasurvey},
author={Michael, Julian and others},
booktitle={Association for Computational Linguistics},
year={2023}
}
@inproceedings{madaan2023sensitivity,
title={On Sensitivity and Robustness of Normalization Schemes to Input Distribution Shifts in Automatic MR Image Diagnosis},
author={Madaan, Divyam and Sodickson, Daniel and Cho, Kyunghyun and Chopra, Sumit},
booktitle={Medical Imaging with Deep Learning},
year={2023}
}
@inproceedings{madaan2022representational,
title={Representational Continuity for Unsupervised Continual Learning},
author={Madaan, Divyam and Yoon, Jaehong and Li, Yuanchun and Liu, Yunxin and Hwang, Sung Ju},
booktitle={International Conference on Learning Representations},
year={2022}
}
@inproceedings{madaan2021learning,
title={Learning to Generate Noise for Multi-Attack Robustness},
author={Madaan, Divyam and Shin, Jinwoo and Hwang, Sung Ju},
booktitle={International Conference on Machine Learning},
year={2021}
}
@inproceedings{madaan2019vayuanukulani,
title={VayuAnukulani: Adaptive Memory Networks for Air Pollution Forecasting},
author={Madaan, Divyam and Dua, Radhika and Mukherjee, Prerana and Lall, Brejesh},
booktitle={IEEE Global Conference on Signal and Information Processing},
year={2019}
}
@article{gomez2019learning,
title={Learning Sparse Networks Using Targeted Dropout},
author={Gomez, Aidan N and Zhang, Ivan and Kamalakara, Siddhartha Rao and Madaan, Divyam and Swersky, Kevin and Gal, Yarin and Hinton, Geoffrey E},
journal={arXiv preprint arXiv:1905.13678},
year={2019}
}
Academic Service
Conference Reviewer
Neural Information Processing Systems (NeurIPS) (2020 – 2025)
International Conference on Machine Learning (ICML) (2020 – 2025)
International Conference on Learning Representations (ICLR) (2022 – 2026)
Conference on Lifelong Learning Agents (CoLLAs) (2023, 2025)
Conference on Health, Inference, and Learning (CHIL) 2025
International Conference on Artificial Intelligence and Statistics (AISTATS) 2025
Association for the Advancement of Artificial Intelligence (AAAI) 2021
Asian Conference on Machine Learning (ACML) 2019-2020
Journal Reviewer
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
International Journal of Computer Vision (IJCV)
Transactions on Machine Learning Research (TMLR)
Workshop Reviewer
ContinualAI Unconference 2023
NeurIPS MetaLearning Workshop 2020
ICML New Frontiers in Adversarial Machine Learning Workshop 2020
Volunteer
International Conference on Learning Representations (ICLR) (2020, 2022)
International Conference on Machine Learning (ICML) (2020, 2021)
Neural Information Processing Systems (NeurIPS) (2020, 2022)
Teaching
New York University, Teaching Assistant (Fall 2022 – Spring 2025)
Machine Learning (DS-GA 1003) – Spring 2025
Natural Language Processing with Representation Learning (DS-GA 1011) – Fall 2024
Causal Inference (DS-GA 3001) – Spring 2024
Fundamentals of Machine Learning (CSCI-UA 473) – Fall 2023, 2025
Machine Learning for Healthcare (CSCI-GA 3033 / DS-GA 3001) – Fall 2022