Robert Belanec

large language model (3) parameter-efficient fine-tuning (3) text classification (1) knowledge distillation (1) low-resource language (1) synthetic datum (1) noise regularization (1) pre-trained language model (1) model interpolation (1) multilingual classification (1) noisy interpolation (1) fine-tuning instability (1) model instability (1) model compression (1) delayed ensemble (1) ensemble learning (1)