Line-Coupled Language Model
Autoregressive language models generate one token per decoding step, limiting the useful output of each forward pass. Although diffusion models, insertion-based decoding, and multi-token prediction enable parallel generation, they either incur additional training-time token traffic or struggle to predict strongly depen...
Shi-Yuan Li, Shao-Rong Zhang, Zhaorui Yang et al.
· 0 citations