The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean Labels

NeurIPSSpotlight2025

Authors: Yonatan Slutzky, Yotam Alexander, Noam Razin, Nadav Cohen
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

Neural networks are powered by an implicit bias: a tendency of gradient descent to fit training data in a way that generalizes to unseen data…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

← All NeurIPS 2025 Spotlight papers · Browse the whole archive