arXiv Machine Learning By Jeonghoon Lee

A Held-Out Transition-Pair Falsifier for Long-Horizon Non-Abelian State Tracking

Read the original on arXiv Machine Learning →

arXiv:2606. 07254v1 Announce Type: new Abstract: State tracking exposes a sharp limitation of sequence models: the relevant signal is often not a summary of observed tokens, but an ordered latent state that evolves through non-commutative transformations.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
2d ago

The Expressive Limits of Diagonal SSMs for State-Tracking

arXiv:2603. 01959v2 Announce Type: replace Abstract: State-Space Models (SSMs) have recently been shown to achieve strong empirical performance on a variety of long-range sequence modeling tasks while remaining efficient and highly-parallelizable.

By Mehran Shakerinava, Behnoush Khavari, Siamak Ravanbakhsh, Sarath Chandar
arXiv Machine Learning
Jun 26

Learning State-Tracking from Code Using Linear RNNs

arXiv:2602. 14814v3 Announce Type: replace Abstract: Over the last years, state-tracking tasks, particularly permutation composition, have become a testbed to understand the limits of sequence models architectures like Transformers and RNNs (linear and non-linear).

By Julien Siems, Riccardo Grazzi, Korbinian P\"oppel, Kirill Kalinin, Hitesh Ballani, Babak Rahmani