3 papers
cs.CL2026
A Declarative-Procedural Perspective on Expert Routing in Bilingual Mixture-of-Experts Language Models
Amrit Gopinath, Raghul, Durairaj Thenmozhi
We investigate whether Mixture-of-Experts (MoE) language models develop linguistically structured expert routing during bilingual language acquisition. Inspired by the Declarative-…
cs.SD2025
Memristive Nanowire Network for Energy Efficient Audio Classification: Pre-Processing-Free Reservoir Computing with Reduced Latency
Akshaya Rajesh, Pavithra Ananthasubramanian, Nagarajan Raghavan +1
Efficient audio feature extraction is critical for low-latency, resource-constrained speech recognition. Conventional preprocessing techniques, such as Mel Spectrogram, Perceptual…
cs.CL2025
RomanLens: The Role Of Latent Romanization In Multilinguality In LLMs
Alan Saji, Jaavid Aktar Husain, Thanmay Jayakumar +3
Large Language Models (LLMs) exhibit strong multilingual performance despite being predominantly trained on English-centric corpora. This raises a fundamental question: How do LLMs…