Publications

2026

1. BlackBoxNLP '26

   Recurrence Is Not Enough: Causally Validating Multilingual SAE Translation Features in Gemma 2 and 3

   Giang Son Nguyen, Nhi Ngoc-Yen Nguyen, Wray Buntine, and Dung D. Le

   Started from an observation during the SAE reading session.

   arXiv Code Website
2. Interspeech '26

   PiDA: Phonetically-Informed Data Augmentation for Robust Vietnamese Speech Translation

   Giang Son Nguyen, Tung X. Nguyen, Hieu Minh Truong, Nhu Vo, Wray Buntine, and Dung D. Le

   In retrospect, I should have named this PhoGA: Phonetically-Guided Augmentation.

   Proceedings arXiv Website
3. Interspeech '26

   Contrastive Training with LLM-generated Near-Misses for Robust Code-Switching Speech Recognition

   Tung X. Nguyen^*, Hieu Minh Truong^*, Giang Son Nguyen, Nhu Vo, Wray Buntine, and Dung D. Le

   Proceedings arXiv
4. LREC '26

   ViMedCSS: A Vietnamese Medical Code-Switching Speech Dataset & Benchmark

   Tung X. Nguyen, Nhu Vo, Giang Son Nguyen, Duy Mai Hoang, Chien Dinh Huynh, Iñigo Jauregi Unanue, Massimo Piccardi, Wray Buntine, and Dung D. Le

   Proceedings arXiv