公开(公告)号：US20250077850A1

公开(公告)日：2025-03-06

申请号：US18823288

申请日：2024-09-03

Applicant: GOOGLE LLC

Inventor： Mara Finkelstein ,  Qijun Tan ,  Markus Freitag ,  Apurva Pradip Shah

IPC: G06N3/0475

Abstract: Implementations disclose utilizing a less computationally efficient decoding method in automatically generating corresponding single generative content predictions for training instances and fine-tuning a student generative model based on those automatically generated training instances. Those implementations are further directed to then utilizing, in an inference time environment, the fine-tuned student generative model and a more computationally efficient decoding method in generating generative predictions—and without any utilization of the less computationally efficient decoding method in generating the generative predictions.