Luozhijie Jin

Kullback-Leibler (KL) divergence regularization is essential for stabilizing reinforcement learning from human feedback (RLHF) in large language models (LLMs), yet its exact computation requires summing over vocabularies of all tokens, incurring prohibitive memory costs during training. Existing...

Speech codecs provide an important interface between continuous speech signals and large language models. An ideal codec for speech language models should not only preserve acoustic information but also capture rich semantic information. However, existing codecs struggle to balance these objectiv...