I am a Research Scientist at Adobe Research, India. I am broadly interested in machine learning, natural language processing and related fields. In my post-graduate work, I have had a specific focus on knowledge graphs (KG) and question answering. In this area, I have tried to improve QA performance by combining pre-trained language models with KG embeddings. I have also worked on making KG embeddings more scalable and easier to apply to downstream tasks.

Previously I was a PhD candidate in the Department of Computational and Data Sciences (CDS) at the Indian Institute of Science, Bangalore. I was supervised by Prof. Partha Pratim Talukdar.

My personal website can be found here.

Publications

Enhancing Post-Hoc Attributions in Long Document Comprehension via Coarse Grained Answer Decomposition

Ramu, P., Goswami, K., Saxena, A., Srinivasan, B. (Nov. 11, 2024)

2024 Conference on Empirical Methods in Natural Language Processing

Enhancing Presentation Slide Generation by LLMs with a Multi-Staged End-to-End Approach

Bandyopadhyay, S., Maheshwari, H., Natarajan, A., Saxena, A. (Sep. 23, 2024)

17th International Natural Language Generation Conference (INLG) 2024

Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answering

Phukan, A., Somasundaram, S., Saxena, A., Goswami, K., Srinivasan, B. (Aug. 12, 2024)

Findings of the Association for Computational Linguistics (ACL 2024)

A-STAR: Test-time Attention Segregation and Retention for Text-to-image Synthesis

Agarwal, A., Karanam, S., J, J., Saxena, A., Goswami, K., Srinivasan, B. (Oct. 2, 2023)

International Conference on Computer Vision (ICCV)