Skip to content

Author

Yi-Xin Wang

1 paper 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.

#artificial intelligence Preprint Sep 2026

Terminal Shrinkage Averaging Reveals a Schedule-Estimator Interaction in LLM Pretraining

This work proposes TSA, which interpolates between the raw final iterate and the average of recent checkpoints to balance recent progress against terminal variation and demonstrates that the resulting gains transfer to depth-22 NanoChat, where the combined schedule and estimator improve validation quality.

Adam Ousherovitch, Yi-Xin Wang · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.