Chris Cremer

large language model (2) reinforcement learning (1) policy optimization (1) policy gradient (1) preference optimization (1) language model alignment (1) reinforcement learning from human feedback (1) model alignment (1) off-policy learning (1) posterior approximation (1) amortized inference (1) latent variable model (1) variational autoencoder (1) proximal policy optimization (1) language model finetuning (1) recognition network (1) sequence-level optimization (1) contrastive learning (1) sequence-level scoring (1)