Nicolas Menet

PhD student, ETHZ - ETH Zurich

1 paper at NeurIPS 2025

OpenReview· Semantic Scholar· Google Scholar

Poster Session 4

1 paper

Thursday, December 4, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Structured Sparse Transition Matrices to Enable State Tracking in State-Space Models

#3411 Spotlight · Aleksandar Terzic, Nicolas Menet, Michael Hersche, Thomas Hofmann, Abbas Rahimi

We propose a parametrisation of SSM transition matrices that enables SSMs to track states of arbitrary finite-state automata while keeping the cost of the parallel scan comparable to that of diagonal SSMs.