2 papers
cs.LG2026
Write Back the : Revisiting the Same Tokens with Fresh Representations
Wencheng Ye, Anning Hu, Xiangdong Zhang +5
Transformers process information strictly forward through depth, preventing deeper computation from revisiting and refining earlier representations. To augment the standard forward…
cs.CL2026
Line-Coupled Language Model
Shiyuan Li, Shaorong Zhang, Zhaorui Yang +3
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…