today local_bar

Andrei Barbu

Researcher, Massachusetts Institute of Technology

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 6

Friday, December 5, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Training the Untrainable: Introducing Inductive Bias via Representational Alignment

#3417 · Vighnesh Subramaniam, David Mayo, Colin Conwell, Tomaso Poggio, Boris Katz, Brian Cheung, Andrei Barbu

We design a method to make untrainable networks trainable using representational alignment.