Multistability is necessary for temporal horizon generalization in POMDPs, sufficient in simple tasks along with transient dynamics in complex ones, while monostable parallelizable RNNs like SSMs and gated linear RNNs fail by construction.
Efficiently modeling long sequences with structured state spaces
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
GraphScan replaces geometric or coordinate-based scanning in Vision SSMs with learned local semantic graph routing, yielding SOTA results among such models on classification and segmentation tasks.
citing papers explorer
-
On the Importance of Multistability for Horizon Generalization in Reinforcement Learning
Multistability is necessary for temporal horizon generalization in POMDPs, sufficient in simple tasks along with transient dynamics in complex ones, while monostable parallelizable RNNs like SSMs and gated linear RNNs fail by construction.
-
Can Graphs Help Vision SSMs See Better?
GraphScan replaces geometric or coordinate-based scanning in Vision SSMs with learned local semantic graph routing, yielding SOTA results among such models on classification and segmentation tasks.