Projects:

RAVEN: Query-Guided Representation Alignment for Question Answering over Audio, Video, Embedded Sensors, and Natural Language

LLaSA: A Multimodal Large Language Model for Human Activity Analysis Using Sensor Data

<aside> <img src="/icons/database_blue.svg" alt="/icons/database_blue.svg" width="40px" />

Datasets

</aside>

<aside> <img src="/icons/copy_red.svg" alt="/icons/copy_red.svg" width="40px" />

Publications:

RAVEN: Query-Guided Representation Alignment for Question Answering over Audio, Video, Embedded Sensors, and Natural Language Subrata Biswas, Mohammad Nur Hossain Khan, and Bashima Islam Empirical Methods in Natural Language Processing (EMNLP) - Main, 2025

LLaSA: A Multimodal LLM for Human Activity Analysis Through Wearable and Smartphone Sensors Sheikh Imran, Mohammad Khan, Subrata Biswas, and Bashima Islam Generative AI and Foundation Models for Human Sensing Workshop (GenAI4HS), UbiComp 2025

</aside>