Publications

2025

1. Can Perplexity Predict Finetuning Performance? An Investigation of Tokenization Effects on Sequential Language Models for Nepali

   Nishant Luitel, Nirajan Bekoju, Anand Kumar Sah, and Subarna Shakya

   In Proceedings of the Fourth Workshop on Generation, Evaluation and Metrics (GEM2), Jul 2025

2024

1. Contextual Spelling Correction with Language Model for Low-Resource Setting

   Nishant Luitel, Nirajan Bekoju, Anand Kumar Sah, and Subarna Shakya

   In 2024 International Conference on Inventive Computation Technologies (ICICT), Jul 2024

   arXiv PDF Code
2. RobustFormer: Noise-Robust Pre-training for images and videos

   Ashish Bastola, Nishant Luitel, Hao Wang, Danda Pani Paudel, Roshani Poudel, and 1 more author

   arXiv preprint arXiv:2411.13040, Jul 2024