Varun Khurana

I am a Research Associate at Adobe Systems, working in the Media and Data Science Research (MDSR) Lab on human behavior modeling using large language and vision models (LLMs/VLMs). My research focuses on predicting, optimizing, and explaining human behavior in real-world contexts, particularly at the intersection of multimodal learning and computational social science. At Adobe, I work with Yaman Kumar Singla and Balaji Krishnamurthy.

I completed my B.Tech (Hons.) in Computer Science & Engineering with a Minor in Economics from IIIT Delhi in 2023. During my undergraduate studies, I was consistently recognized on the Dean’s List of Academic Excellence for three consecutive years.

My research interests span Natural Language Processing, Computer Vision, Behavioral Sciences, and Graph Learning. I have published papers at top-tier conferences including ICLR, EACL, NAACL, and WACV, and have filed multiple patents for my work on synthetic gaze generation and multimodal content understanding.

During my undergraduate studies, I completed my Bachelor’s thesis on “LearnAd: Multi-modal Fusion Transformer for Understanding Digital Advertisements” advised by Prof. Rajiv Ratn Shah at MIDAS Lab, IIIT Delhi. I have also worked with Prof. Mukesh Mohania on developing a “Multi-Relational Graph Transformer for Automatic Short Answer Grading”.

News

Jan 2025	Our paper “Measuring And Improving Engagement of Text-to-Image Generation Models” has been accepted at ICLR 2025! 🎉
Oct 2024	Our work “AdQuestA: Knowledge-Guided Visual Question Answer Framework for Advertisements” accepted at WACV 2025.
Jul 2024	Got promoted to Research Associate 2 at Adobe Systems! 🎉
Jun 2023	Joined Adobe Systems full time as ML Research Associate in the Media and Data Science Research Lab! 🚀
May 2023	Graduated from IIIT Delhi with a B.Tech (Honors) in Computer Science and Engineering and Minor in Economics! 🎓
Apr 2022	Our work “Multi-Relational Graph Transformer for Automatic Short Answer Grading” got accepted at NAACL 2022, selected for oral presentation! 🎉

Selected Publications

Note: For an up-to-date list of publications and patents filed, please refer to my Google Scholar profile.

ICLR

Measuring And Improving Engagement of Text-to-Image Generation Models

Varun Khurana^*, Yaman Kumar Singla^*, Jayakumar Subramanian, and 4 more authors

In International Conference on Learning Representations, 2025

Bib HTML

@inproceedings{khurana2025engagement,
  title = {Measuring And Improving Engagement of Text-to-Image Generation Models},
  author = {Khurana, Varun and Singla, Yaman Kumar and Subramanian, Jayakumar and Chen, Changyou and Shah, Rajiv Ratn and Xu, Zhiqiang and Krishnamurthy, Balaji},
  booktitle = {International Conference on Learning Representations},
  year = {2025},
}

EACL

Synthesizing Human Gaze Feedback for Improved NLP Performance

Varun Khurana^*, Yaman Kumar^*, Nora Hollenstein, and 2 more authors

In European Chapter of the Association for Computational Linguistics, 2023

Bib HTML

@inproceedings{khurana2023synthesizing,
  title = {Synthesizing Human Gaze Feedback for Improved NLP Performance},
  author = {Khurana, Varun and Kumar, Yaman and Hollenstein, Nora and Kumar, Rajesh and Krishnamurthy, Balaji},
  booktitle = {European Chapter of the Association for Computational Linguistics},
  year = {2023},
}

NAACL-HLT

Multi-Relational Graph Transformer for Automatic Short Answer Grading

Rajat Agarwal, Varun Khurana^*, Karish Grover^*, and 2 more authors

In North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2022

Bib HTML

@inproceedings{agarwal2022multirelational,
  title = {Multi-Relational Graph Transformer for Automatic Short Answer Grading},
  author = {Agarwal, Rajat and Khurana, Varun and Grover, Karish and Mohania, Mukesh and Goyal, Vikram},
  booktitle = {North American Chapter of the Association for Computational Linguistics: Human Language Technologies},
  year = {2022},
}