Decoupling Token Roles in Autoregressive Pretraining
Using controlled corruption, this work decouple these two roles and finds a reversal: making a noisy token easier to predict reduces its damage as a target but increases it as context.
2 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Using controlled corruption, this work decouple these two roles and finds a reversal: making a noisy token easier to predict reduces its damage as a target but increases it as context.
A robust dynamic-expansion framework that integrates sample purification, selective recovery, and robust expert routing into a unified continual learning paradigm is proposed, and Bi-Prototype Purification (BPP) is introduced to identify suspicious samples by exploiting semantic discrepancies in feature space.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.