Saptarshi Saha
University at Buffalo, State University of New York, Helmholtz Center for Information Security, Indian Statistical Institute, Indian Institute of Science Education and Research Kolkata
Research areas: Computer Science · Artificial Intelligence · Bayesian Modeling and Causal Inference · Topic Modeling · Explainable Artificial Intelligence (XAI)
0000-0002-7178-8646
About
Saptarshi is a Senior Research Fellow (Ph.D. candidate) at the Indian Statistical Institute in Kolkata, West Bengal, India. His research interests include causality, computer vision, and generative models. He received his 5-year BS-MS Dual Degree in Mathematics from the Indian Institute of Science Education and Research Kolkata, where his studies were supported by the INSPIRE fellowship of the Department of Science and Technology, Government of India, from 2015 to 2020. He was a recipient of the prestigious Fulbright-Nehru Doctoral Research Fellowship for 2024–2025. He also received the Helmholtz Visiting Researcher Grant in 2024 from the Helmholtz Information & Data Science Academy. In November 2025, he received the DAAD AINeT Fellowship for Postdoc-NeT-AI from the Deutscher Akademischer Austauschdienst (DAAD).
Employment
-
University at Buffalo, State University of New York Fulbright-Nehru Doctoral Research Fellow2024 - 2025
-
Helmholtz Center for Information Security Helmholtz Visiting Researcher2024 - 2024
Education
- 2020 - Present
-
Indian Institute of Science Education and Research Kolkata 5 Year BS-MS Dual Degree Programme2015 - 2020
Projects & Funding
Projects & funding information is unavailable.
Publications (13)
- From pixels to strokes: A survey on generative handwriting Save
- Overview of the HASOC Track at FIRE 2025: Abusive Meme Identification — Shadows Behind the Laughter Save
- BeatVision: Explainable AI for Clinician-Grade Atrial Fibrillation Detection Save
- Findings from shared tasks on hate speech detection: Performance patterns for low-resource languages Save
- Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia Save
- Cyclic Counterfactuals under Shift-Scale Interventions Save
- Language Models are Crossword Solvers Save
- On Measuring Intrinsic Causal Attributions in Deep Neural Networks Save
- SEMI-CAVA: A Causal Variational Approach to Semi-Supervised Learning Save
- SafeSpeech: a three-module pipeline for hate intensity mitigation of social media texts in Indic languages Save
- Region Mixup Save
- VALUED - Vision and Logical Understanding Evaluation Dataset Save
- On Noise Abduction for Answering Counterfactual Queries: A Practical Outlook Save