today local_bar

Ziyang Cai

PhD student, Princeton University

1 paper at NeurIPS 2025

OpenReview· Semantic Scholar· Google Scholar

Poster Session 5

Friday, December 5, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Extrapolation by Association: Length Generalization Transfer In Transformers

#4109 Spotlight · Ziyang Cai, Nayoung Lee, Avi Schwarzschild, Samet Oymak, Dimitris Papailiopoulos

We show that transformers achieve length generalization when training on shorter main task and longer auxiliary tasks together.