notesum.ai

Published at December 9

Training Large Language Models to Reason in a Continuous Latent Space

cs.CL

Released Date: December 9, 2024

Authors: Shibo Hao1, Sainbayar Sukhbaatar, DiJia Su, Xian Li, Zhiting Hu, Jason Weston, Yuandong Tian

Aff.: 1FAIR at Meta

Arxiv: http://arxiv.org/pdf/2412.06769v1