3 papers
cs.CL2026
Location-Aware Language Models via Secondary Embeddings
Gokul Srinivasagan, Munir Georges
Pretrained transformer-based language models achieve strong performance across a wide range of NLP tasks but remain limited in encoding geo-locational semantics, leading to subopti…
cs.AI2026
Entropy-aware Masking for Masked Language Modeling
Gokul Srinivasagan, Kai Hartung, Munir Georges
Masked language modeling has become a standard pretraining objective for training encoder-based language models. In this approach, certain tokens in the input are masked, and the m…
eess.AS2023
Compression of end-to-end non-autoregressive image-to-speech system for low-resourced devices
Gokul Srinivasagan, Michael Deisher, Munir Georges
People with visual impairments have difficulty accessing touchscreen-enabled personal computing devices like mobile phones and laptops. The image-to-speech (ITS) systems can assist…