Write Back the $\Delta$: Revisiting the Same Tokens with Fresh Representations
ReFlux is introduced, a learnable feedback graph that dynamically selects and composes increment-carrying routes that establishes ReFlux as an efficient paradigm for unlocking the latent computational potential of LLMs, allowing them to revisit the same tokens with fresh representations.
Wen Ye, An-Ning Hu, Xiang-Dong Zhang et al.
· 0 citations