2 papers
cs.LG2025
Domain Expansion: Parameter-Efficient Modules as Building Blocks for Composite Domains
Mann Patel, Divyajyoti Panda, Hilay Mehta +2
Parameter-Efficient Fine-Tuning (PEFT) is an efficient alternative to full scale fine-tuning, gaining popularity recently. With pre-trained model sizes growing exponentially, PEFT…
cs.CL2023
Multilingual Neural Machine Translation System for Indic to Indic Languages
Sudhansu Bala Das, Divyajyoti Panda, Tapas Kumar Mishra +2
This paper gives an Indic-to-Indic (IL-IL) MNMT baseline model for 11 ILs implemented on the Samanantar corpus and analyzed on the Flores-200 corpus. All the models are evaluated u…