Saptarshi Saha

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 Fellow
  2024 - 2025
• Helmholtz Center for Information Security Helmholtz Visiting Researcher
  2024 - 2024

Education

• Indian Statistical Institute PhD
  2020 - Present
• Indian Institute of Science Education and Research Kolkata 5 Year BS-MS Dual Degree Programme
  2015 - 2020

Projects & Funding

Projects & funding information is unavailable.

Publications (13)

• From pixels to strokes: A survey on generative handwriting
  International Journal on Document Analysis and Recognition (IJDAR) 2026 DOI: 10.1007/s10032-026-00609-2
  +Save
• Overview of the HASOC Track at FIRE 2025: Abusive Meme Identification — Shadows Behind the Laughter
  Forum for Information Retrieval Evaluation 2026
  +Save
• BeatVision: Explainable AI for Clinician-Grade Atrial Fibrillation Detection
  Communications in Computer and Information Science 2026 DOI: 10.1007/978-3-032-19099-4_15
  +Save
• Findings from shared tasks on hate speech detection: Performance patterns for low-resource languages
  Pattern Recognition Letters 2026 DOI: 10.1016/J.PATREC.2025.09.004
  +Save
• Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia
  PROCEEDINGS OF THE ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1: LONG PAPERS 2025 DOI: 10.18653/V1/2025.ACL-LONG.916
  +Save
• Cyclic Counterfactuals under Shift-Scale Interventions
  Advances in Neural Information Processing Systems 2025 DOI: 10.48550/ARXIV.2510.25005
  +Save
• Language Models are Crossword Solvers
  Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers) 2025 DOI: 10.18653/v1/2025.naacl-long.104
  +Save
• On Measuring Intrinsic Causal Attributions in Deep Neural Networks
  Proceedings of the Fourth Conference on Causal Learning and Reasoning 2025
  +Save
• SEMI-CAVA: A Causal Variational Approach to Semi-Supervised Learning
  IEEE Transactions on Pattern Analysis and Machine Intelligence 2025 DOI: 10.1109/TPAMI.2025.3594360
  +Save
• SafeSpeech: a three-module pipeline for hate intensity mitigation of social media texts in Indic languages
  Social Network Analysis and Mining 2025 DOI: 10.1007/S13278-024-01393-9
  +Save