Rohit Agarwal

Bio-AI Lab

Department of Computer Science

UiT The Arctic University of Norway

Tromsø, Norway 9019

I am Rohit Agarwal, an AI Researcher at the Bio-AI Lab, Department of Computer Science, UiT The Arctic University of Norway, Tromsø. I completed my Ph.D. in Artificial Intelligence in 2025 under the supervision of Dilip K. Prasad, Alexander Horsch, and Krishna Agarwal.

My research focuses on building scalable online deep learning models for streaming data with varying feature spaces — a setting I call Haphazard Inputs. This involves online learning, continual learning, and dynamic neural architectures that adapt as the number of available inputs changes over time. I also have experience in time series, LLMs, computer vision and natural language processing. My current research focusses on LLMs and Haphazard Inputs.

I have also authored the book Cloud Computing for Everyone (BPB Online, 2025). The book provides an accessible overview of cloud computing — from foundational concepts to advanced practices — and received the Golden Wings Award.

news

Dec 22, 2025	Organized the CHOMPS Workshop at AACL, Dec 2025.
Jun 30, 2025	Started as an AI Researcher at UiT The Arctic University of Norway (Bio-AI Lab), working on hallucinations in LLMs.
May 31, 2025	Paper accepted at IJCNN 2025 — Haphazard Inputs as Images in Online Learning. Presenting doctoral dissertation at IEEE IJCNN Conference with a travel grant of $1000.
Apr 05, 2025	Paper published at ICASSP 2025 — Hedging Is Not All You Need: A Simple Baseline for Online Learning Under Haphazard Inputs.
Jan 14, 2025	Book published — Cloud Computing for Everyone: From Basics to Advanced Practices (BPB Online, 2025). Received the Golden Wings Award for this book.

Selected Publications

Haphazard Inputs

Haphazard Inputs as Images in Online Learning

Rohit Agarwal, Aryan Dessai, Arif Ahmed Sekh , and 3 more authors

In International Joint Conference on Neural Networks , 2025

HTML PDF Code
Cloud Computing

Cloud Computing for Everyone

Rohit Agarwal, and Dilip K Prasad

2025

HTML

Haphazard Inputs

packetLSTM: Dynamic LSTM Framework for Streaming Data with Varying Feature Space

Rohit Agarwal, Karaka Prasanth Naidu, Alexander Horsch , and 2 more authors

arXiv preprint arXiv:2410.17394, 2024

Bib HTML PDF Code

@article{agarwal2024packetlstm,
  title = {packetLSTM: Dynamic LSTM Framework for Streaming Data with Varying Feature Space},
  author = {Agarwal, Rohit and Naidu, Karaka Prasanth and Horsch, Alexander and Agarwal, Krishna and Prasad, Dilip K},
  journal = {arXiv preprint arXiv:2410.17394},
  year = {2024},
  doi = {10.48550/arXiv.2410.17394},
}

Haphazard Inputs

Aux-Drop: Handling Haphazard Inputs in Online Learning Using Auxiliary Dropouts

Rohit Agarwal, Deepak Gupta, Alexander Horsch , and 1 more author

Transactions on Machine Learning Research, 2023

Reproducibility Certification

Bib HTML PDF Code

@article{agarwal2023auxdrop,
  title = {Aux-Drop: Handling Haphazard Inputs in Online Learning Using Auxiliary Dropouts},
  author = {Agarwal, Rohit and Gupta, Deepak and Horsch, Alexander and Prasad, Dilip K.},
  journal = {Transactions on Machine Learning Research},
  issn = {2835-8856},
  year = {2023},
  url = {https://openreview.net/forum?id=R9CgBkeZ6Z},
  note = {Reproducibility Certification},
}