Home
| I’m a Senior Applied Scientist at Borealis AI (RBC Research Institute) in Montreal, where I work on Foundation Models and LLMs for Capital Markets and Credit Modeling within the AI Solutions group led by Prof. Greg Mori. Previously, I was a Research Engineer at Samsung AI Center Toronto, where I worked with Dr. Alex Levinshtein and Prof. Allan Jepson on computer vision research, focusing on burst photography, neural implicit representations, and image enhancement and synthesis. Before that, I was a Software Engineer at Broadcom Inc., where I developed behavior-based malware classifiers for Norton AntiVirus using machine learning. I have over 7 years of full-time experience in applied AI and software engineering, and I serve as a reviewer for NeurIPS, CVPR, ICLR, and ICML. |    | |
Misc: I enjoy Kaggle challenges in healthcare and medicine, and I rank as a Competitions Expert (Top 5% globally, 5 medals). I custom-built a Nvidia GeForce RTX 3090 Ti workstation for these projects – check out its detailed specs and benchmarks on PC Part Picker!
Current Research Interests: Calibration, uncertainty estimation, and robustness of large language models (LLMs), particularly for risk-sensitive applications in healthcare and finance.
Contact: For opportunities and mentorship inquiries, feel free to reach out at vin [dot] bhaskara [at] gmail [dot] com.
Education
| M.Sc. Applied Computing (Deep Learning) |   | |
| Department of Computer Science, University of Toronto | 2018 - 2020 | |
| Grade: A+ [4.0/4.0], Vector Scholar in AI | ||
| Research Topic: Robust Single-Shot Object Detection for Computer Vision | ||
| B.Tech. Engineering Physics |   | |
| Indian Institute of Technology Guwahati (IIT Guwahati) | 2012 - 2016 | |
| Institute Silver Medalist, IQC Research Visitor |
Patents
| Jan 2025 | Unsupervised Super-Resolution Training Data Construction Haicheng Wang, Xinyu Sun, Vin Bhaskara, Stavros Tsogkas, Allan Jepson, Alex Levinshtein US Patent 12,210,587 (Granted) Patent Cite |  |
Publications
Machine Learning
| Jan 2022 | GraN-GAN: Piecewise Gradient Normalization for Generative Adversarial Networks Vin Bhaskara*, Tristan Aumentado-Armstrong*, Allan Jepson, Alex Levinshtein Winter Conference on Applications of Computer Vision (WACV 2022) Paper Arxiv Poster Slides Video Cite |  | ||
| Jan 2021 | Efficient Super-Resolution Using MobileNetV3 Haicheng Wang*, Vin Bhaskara*, Alex Levinshtein*, Stavros Tsogkas, Allan Jepson European Conference on Computer Vision (ECCV 2020) Workshops Paper PDF Cite |  |
Quantum Information
| May 2022 | Generalized Entanglement Measure for Continuous-Variable Systems Nibedita Swain*, Vin Bhaskara*, Prasanta K. Panigrahi Physical Review A 105, 052441 Paper PDF Arxiv Cite |  | ||
| Mar 2017 | Generalized Entanglement Measure for Multiparticle Pure States in Arbitrary Dimensions Vin Bhaskara, Prasanta K. Panigrahi Quantum Information Processing, Volume 16, Article number: 118 Paper PDF Arxiv Cite |  | ||
| Mar 2017 | Implementing Bragg Mirrors in a Hollow-Core Photonic-Crystal Fiber Jeremy Flannery, Golam Bappi, Vin Bhaskara, Omar Alshehri, Michal Bajcsy Optical Materials Express, Volume 7, Issue 4, pp. 1198-1210 Paper Cite |  | ||
| Sep 2016 | Mesoscale Cavities in Hollow-Core Waveguides for Quantum Optics with Atomic Ensembles C.M. Haapamaki, J. Flannery, G. Bappi, R. Al Maruf, Vin Bhaskara, O. Alshehri, T. Yoon, M. Bajcsy Nanophotonics, Volume 5, No. 3, pp. 392-408 Paper Cite |  | ||
(* denotes equal contribution)
Preprints
| Apr 2020 | Part-based Auxiliary Objectives with No Extra Labels for Robust Single-Shot Object Detection Vin Bhaskara, Stavros Tsogkas, Kosta Derpanis, Alex Levinshtein DOI: 10.13140/RG.2.2.10079.47521 Link PDF Cite |  | ||
| May 2019 | Exploiting Uncertainty of Loss Landscape for Stochastic Optimization Vin Bhaskara, Sneha Desai arXiv:1905.13200 [cs.LG] Arxiv Cite |  | ||
| Apr 2019 | Risk Prediction in the General Internal Medicine Ward at St. Michael's Hospital Vin Bhaskara, Yingying Fu, Sindhu Gowda DOI: 10.13140/RG.2.2.27695.55205 Link PDF Cite |  | ||
| Jul 2018 | Emulating Malware Authors for Proactive Protection using GANs over File Behaviors Vin Bhaskara, Debanjan Bhattacharyya arXiv:1807.07525 [stat.ML] Arxiv Cite |  |