Hamish Ivison

Reinforcement Learning (1)

instruction following (3) language model (2) reinforcement learning (2) instruction tuning (2) variational inference (1) natural language processing (1) reward modeling (1) knowledge distillation (1) probabilistic modeling (1) in-context learning (1) question answering (1) model evaluation (1) language modeling (1) text summarization (1) sequence classification (1) direct preference optimization (1) multitask learning (1) continued pretraining (1) preference learning (1) few-shot learning (1)