nidhin [dot] harilal [at] colorado [dot] edu
About
My name is Nidhin Harilal and I am third-year Ph.D. student in computer science at the University of Colorado Boulder, where I am advised by Dr. Claire Monteleoni. I am recipient of Awtar and Teji Singh Fellowship. Prior to my Ph.D, I recieved my Bachelor’s
degree with honours in Computer Science & Engineering in 2021 from IIT
Gandhinagar.
My research interests broadly lie in machine learning, with a focus on unsupervised representation learning. I want to study how large-scale spatiotemporal data with complex correlations and high dimensionality affect the representation and thus the generalization of machine learning models. In the past, I have focused on improving the spatiotemporal resolution of climate datasets for enhanced prediction, alongside projects on generating high-dynamic-range videos and image captioning. Recently, I am working on harnessing Generative AI to advance modern machine learning techniques. I also care about deep learning robustness and interpretability.
Publications & Preprints
[10] Reza Akbarian* Nidhin Harilal*, Claire Monteleoni, and Maziar Raissi. "Parameter Efficient Fine-tuning of Self-supervised ViTs without Catastrophic Forgetting."
Accepted at CVPR - Efficient Large Vsion Models (eLVM). 2024.
[9] Reza Akbarian* Nidhin Harilal*, Claire Monteleoni, and Maziar Raissi. "DiffMix: Mixing Natural and Synthetic Images for Robust Self-Supervised Representations."
In submission
[8] Nidhin Harilal, B. M Hodge, Claire Monteleoni, and Aneesh Subramanian. "STint: Self-supervised Temporal Interpolation for Geospatial Data."
arXiv preprint arXiv:2309.00059 (2023).
[7] Nidhin Harilal, B. M Hodge, Claire Monteleoni, and Aneesh Subramanian. "EnhancedSD: Predicting Solar
Power Reanalysis from Climate Projections via Image Super-Resolution" NeurIPS - Tackling Climate
Change with Machine Learning. 2022.
[6] Nidhin Harilal , and Rohan Patil. "Effectiveness of the Recent Advances in Capsule Networks." arXiv
preprint arXiv:2210.05834 (2022)
[5] Kumar, Athul, Aarchi Agrawal, KS Ashin Shanly, Sudip Das, and Nidhin Harilal. "Image caption generator
using siamese graph convolutional networks and LSTM." In 5th International Conference on Data Science &
Management of Data (9th ACM IKDD CODS and 27th COMAD), pp. 306-307. 2022.
[4] Anand, Mrinal, Nidhin Harilal, Chandan Kumar, and Shanmuganathan Raman. "HDRVideo-GAN: deep generative
HDR video reconstruction." In Proceedings of the Twelfth Indian Conference on Computer Vision, Graphics and
Image Processing, pp. 1-9. 2021.
[3] Nidhin Harilal, Udit Bhatia, and Auroop R. Ganguly. "Bayesian Deep Learning Hyperparameter Search for
Robust Function Mapping to Polynomials with Noise." arXiv preprint arXiv:2106.12532 (2021).
[2] Nidhin Harilal, Mayank Singh, and Udit Bhatia. "Augmented convolutional LSTMs for generation of
high-resolution climate change projections." IEEE Access 9 (2021): 25208-25218.
[1] Nidhin Harilal, Rushil Shah, Saumitra Sharma, and Vedanta Bhutani. "CARO: an empathetic health
conversational chatbot for people with major depression." In Proceedings of the 7th ACM IKDD CoDS and 25th
COMAD, pp. 349-350. 2020.