PPL
Yohan Jo
Papers (4)
Where Should Diffusion Enter a Language Model? Geometry-Guided Hidden-State ReplacementKL for a KL: On-Policy Distillation with Control Variate BaselineYour Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal StatesMIST: Multimodal Interactive Speech-based Tool-calling Conversational Assistants for Smart Homes