I am a first year MSCS student at the University of Maryland, College Park. My research is focused on multimodal foundation models, specifically large audio/speech models. I am particularly interested in improving the reasoning capabilities, trustworthiness and safety of these models. At UMD, I am part of the GAMMA Lab and PIRL Lab. I am advised by Prof. Dinesh Manocha and Prof. Ramani Duraiswami.

Prior to joining UMD, I spent a year and a half working at the Indian Institute of Science, as a part of LEAP Lab, where I worked on the benchmarking and uncertainty estimation of large audio language models. In 2024, I graduated with a bachelors degree in Computer Science from PES University, Bangalore.

For research collaborations, feel free to reach out to me via email.

Updates

  • Jun 2026 Started a research internship at Hippocratic AI.
  • Jun 2026 One paper accepted to Interspeech 2026. Read the writeup →
  • Sep 2025 Began my masters in Computer Science at the University of Maryland, College Park.

Publications

A Closer Look at Failure Modes in Temporal Understanding of Large Audio-Language Models
Apoorva Kulkarni, Kaousheik Jayakumar, Sreyan Ghosh, Sarah Wiegreffe, Dinesh Manocha, Ramani Duraiswami
INTERSPEECH 2026
FESTA: Functionally Equivalent Sampling for Trust Assessment of Multimodal LLMs
Debarpan Bhattacharya*, Apoorva Kulkarni*, Sriram Ganapathy (* = Equal Contribution)
Findings of EMNLP 2025
Benchmarking and Confidence Evaluation of Audio-LLMs For Temporal Reasoning
Debarpan Bhattacharya*, Apoorva Kulkarni*, Sriram Ganapathy (* = Equal Contribution)
INTERSPEECH 2025
The Second DISPLACE Challenge: DIarization of SPeaker and LAnguage in Conversational Environments
Shareef Babu Kalluri, Prachi Singh, Pratik Roy Chowdhuri, Apoorva Kulkarni, et al.
INTERSPEECH 2024