Sang Truong

large language model (3) adversarial robustness (1) uncertainty quantification (1) multilingual nlp (1) toxicity detection (1) bias detection (1) gaussian process (1) experimental design (1) label efficiency (1) supervised fine-tuning (1) molecular representation (1) supervised finetuning (1) vietnamese language (1) bayesian optimisation (1) kernel methods (1) trustworthiness evaluation (1) active learning (1) chemical reaction optimisation (1)