Ege Onur Taga

reinforcement learning (1) few-shot learning (1) model selection (1) bayesian inference (1) policy learning (1) multivariate time series (1) synthetic datum (1) prompt selection (1) cost saving (1) latency constraint (1) text embedding (1) prior-data fitted network (1) cost optimization (1) latency optimization (1) budget constraint (1) reinforcement learning policy (1) cost efficiency (1) large language model (1)