Sanjay Suryanarayanan

AI4Bhārat Lab

Indian Institute of Technology, Madras

Chennai, Tamil Nadu, India

Hello · नमस्ते · வணக்கம் · ನಮಸ್ಕಾರ !

I’m Sanjay, a Research Associate at the AI4Bhārat Lab in IIT Madras, where I am advised by Dr. Mitesh Khapra, Dr. Raj Dabre and Dr. Anoop Kunchukuttan.

My current research focuses on Multilingual and Multimodal Language Modeling. Additionally, I am exploring Mechanistic Interpretability and Reinforcement Learning as complementary directions within these domains. Previously, I was a Research Intern at AI4Bhārat, where I worked on building large-scale data infrastructure to create, curate, and clean Indic Language data for training LLMs. I am fluent in English, Hindi, Tamil, and Kannada (Being a polyglot naturally complements my work in multilingual NLP).

Beyond CS research, I’m a curious soul with wide-ranging interests. I’m passionate about sports, cars, cinema, and music, and I love studying mathematics, physics, economics, neuroscience, philosophy, spirituality, and yes, a decillion other things!

I am actively seeking work and research opportunities where I can apply my skills to solve complex real-world problems. I am also eager to collaborate with researchers and research groups, if you share similar interests or have collaborative ideas, please feel free to reach out to me via my Email, LinkedIn or X!

news

Apr 01, 2026	Our work “Seeing Isn’t Believing: Uncovering Blind Spots in Evaluator Vision-Language Models” is out on arXiv!
Dec 12, 2025	I will be attending AACL 2025 at IIT Bombay, India, from Dec 20 to 24 and will be presenting our poster on Dec 21 from 4:00 PM to 5:30 PM at VMCC (Session MC-PP4: Multilingual NLP and Machine Translation). Feel free to drop by to chat and learn more about our work. Resources are available here.
Oct 25, 2025	Happy to share that our work “Pralekha: Cross Lingual Document Alignment for Indic Languages” has been accepted to the main conference of AACL 2025!
Sep 01, 2025	Featuring Pralekha in the English–Indic Language Document Translation Task at WAT 2025.
Nov 27, 2024	Our work “Pralekha: Cross-Lingual Document Alignment for Indic Languages” is out on arXiv.

selected publications

arXiv

Seeing Isn’t Believing: Uncovering Blind Spots in Evaluator Vision-Language Models

Mohammed Safi Ur Rahman Khan, Sanjay Suryanarayanan, Tushar Anand, and Mitesh M. Khapra

arXiv preprint arXiv:2604.21523, Apr 2026

Bib PDF Code Data

@article{khan-etal-2026-seeingisntbelieving,
  title = {Seeing Isn't Believing: Uncovering Blind Spots in Evaluator Vision-Language Models},
  author = {Khan, Mohammed Safi Ur Rahman and Suryanarayanan, Sanjay and Anand, Tushar and Khapra, Mitesh M.},
  month = apr,
  year = {2026},
  journal = {arXiv preprint arXiv:2604.21523},
  url = {https://arxiv.org/abs/2604.21523},
}

AACL 25

Pralekha: Cross-Lingual Document Alignment for Indic Languages

Sanjay Suryanarayanan, Haiyue Song, Mohammed Safi Ur Rahman Khan, Anoop Kunchukuttan, and Raj Dabre

Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, Dec 2025

Bib PDF Code Data

@article{suryanarayanan-etal-2025-pralekha,
  title = {Pralekha: Cross-Lingual Document Alignment for Indic Languages},
  author = {Suryanarayanan, Sanjay and Song, Haiyue and Khan, Mohammed Safi Ur Rahman and Kunchukuttan, Anoop and Dabre, Raj},
  month = dec,
  year = {2025},
  address = {Mumbai, India},
  journal = {Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics},
  publisher = {The Asian Federation of Natural Language Processing and The Association for Computational Linguistics},
  url = {https://aclanthology.org/2025.ijcnlp-long.37/},
  pages = {662--676},
}