Murun Yang

reward model (2) preference learning (1) preference alignment (1) cross-lingual transfer (1) preference optimization (1) language model alignment (1) multilingual machine translation (1) reinforcement learning from human feedback (1) connectionist temporal classification (1) generative model (1) foundation model (1) supervised fine-tuning (1) hallucination mitigation (1) human preference alignment (1) non-autoregressive translation (1) speech translation (1) multi-dimensional evaluation (1) probing method (1) neural encoder (1) visual reward model (1)