today local_bar

Ellie Pavlick

Associate Professor, Brown University

2 papers at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 3

Thursday, December 4, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Transferring Linear Features Across Language Models With Model Stitching

#1106 Spotlight · Alan Chen, Jack Merullo, Alessandro Stolfo, Ellie Pavlick

Born a Transformer -- Always a Transformer? On the Effect of Pretraining on Architectural Abilities

#4004 · Mayank Jobanputra, Yana Veitsman, Yash Sarrof, Aleksandra Bakalova, Vera Demberg, Ellie Pavlick, Michael Hahn

While large-scale pretraining brings remarkable capabilities, it cannot fundamentally rewrite the architecture’s core inductive biases.