Publications (27)
Securing the Future Internet of Things with Post-Quantum Cryptography
Adarsh Kumar, Carlo Ottaviani, Sukhpal Singh Gill +1
Traditional and lightweight cryptography primitives and protocols are insecure against quantum attacks. Thus, a real-time application using traditional or lightweight cryptography…
Accelerating Deep Learning Inference via Learned Caches
Arjun Balasubramanian, Adarsh Kumar, Yuhan Liu +3
Deep Neural Networks (DNNs) are witnessing increased adoption in multiple domains owing to their high accuracy in solving real-world problems. However, this high accuracy has been…
From Words to Music: A Study of Subword Tokenization Techniques in Symbolic Music Generation
Adarsh Kumar, Pedro Sarmento
Subword tokenization has been widely successful in text-based natural language processing (NLP) tasks with Transformer-based models. As Transformer models become increasingly popul…
MA-DST: Multi-Attention Based Scalable Dialog State Tracking
Adarsh Kumar, Peter Ku, Anuj Kumar Goyal +2
Task oriented dialog agents provide a natural language interface for users to complete their goal. Dialog State Tracking (DST), which is often a core component of these systems, tr…
Exploring ideas in topological quantum phenomena: A journey through the SSH model
Anantha Hegde, Adarsh Kumar, Adhip Agarwala +1
Geared as an invitation for undergraduates, beginning graduate students, we present a pedagogical introduction to one-dimensional topological phases -- in particular the Su-Schrief…
The PAU Survey: Uncovering the connection between intrinsic and observed galaxy properties using symbolic regression
Adarsh Kumar, Carlton M. Baugh, Suttikoon Koonkor +12
Estimating stellar masses for billions of galaxies in upcoming surveys requires methods that are both accurate and computationally efficient. We present a new approach using symbol…