Amit Kumar Jaiswal

A Model-Agnostic Framework for Recommendation via Interest-aware Item Embeddings

2023 · arXiv (Cornell University)

Item representation holds significant importance in recommendation systems, which encompasses domains such as news, retail, and videos. Retrieval and ranking models utilise item representation to capture the user-item relationship based on user behaviours. While existing …

Lightweight Adaptation of Neural Language Models via Subspace Embedding

2023

Traditional neural word embeddings are usually dependent on a richer diversity of vocabulary. However, the language models recline to cover major vocabularies via the word embedding parameters, in particular, for multilingual language models that generally …

AUTOAID: An Intelligent Accident Notifier

2025

Road accidents remain a leading cause of fatalities, injuries, and hospitalizations worldwide, primarily due to delayed emergency response and inadequate detection systems. This research paper explores advanced methods for accident detection, response facilitation, and safety …