Hi there! I'm Subhankar
I'm a Computer Science Ph.D. candidate at the University of Minnesota, Twin Cities.
I am advised by Professor Shashi Shekhar and am a member of the Spatial Computing Research Group. I also work with Professor Aneesh Subramanian.
I am a Graduate Assistant at iHARP, where we aim to reduce uncertainty in geospatial forecasting using Generative and Multimodal AI.
Upcoming Events
- I will be joining Amazon Science (Seattle, WA) as an Applied Scientist II Intern during Summer 2026, where I will be working on Generative AI and LLM-based methods for Fraud Detection.
Past Work and Events
- I was an Applied Scientist II Intern at Amazon Science (Bellevue, WA) during Summer 2025, where I developed Generative AI and Multimodal Fusion methods for Anomaly Detection in the Amazon Science Geospatial Team.
- I was a Research Intern at the Oak Ridge National Laboratory during Spring 2025, where I worked with Diffusion Models and Vision Transformers for Super-resolution tasks.
- I was a student organizer for the Scientific Modeling out of distribution (Scientific-Mood) ML Challenge and workshop.
- I co-organized the 2025 NSF HDR Machine Learning Challenge on Anomaly Detection. Pre-print of the paper describing the Anomaly Detection Challenge is out now. Check out our AAAI Workshop on Anomaly Detection in Scientific Domains.
- Recently, I worked on spatial pattern mining with statistical guarantees.
Current Projects
- Spatio-temporal modeling and forecasting using Generative AI
- Adaptive Multimodal Data Fusion and integration strategies
- Scalable Anomaly Detection and pattern discovery for complex systems
- Multimodal Recommendation Agents using Vision-Language Models (VLMs)
- Autonomous agents for complex reasoning, planning, and workflow automation
- Retrieval-Augmented Generation (RAG) pipelines for domain-specific knowledge grounding
- Model Quantization and efficiency optimization for Foundation Models