Open Source
FM-Mamba: An Efficient Native 2D Selective State Space Model with Stability-Aware Discretization
arXiv cs.SY0 views
arXiv:2611.22061v1 Announce Type: new Abstract: When applied to two-dimensional features such as images, Mamba-based methods either flatten the feature map into 1D sequences and fuse multiple scans, which breaks spatial adjacency and multiplies computation, or recurse directly on the 2D grid but rescale the recurrence with a fixed input-independent factor and aggregate only the predecessors on a single anti-diagonal, leaving the discrete step unconstrained by 2D stability theory. We propose \textbf{FM-Mamba}, a native 2D selective state space model built on the general Fornasini--Marchesini (FM) model. Its coupled recurrence evolves along both spatial axes; cross-axis coupling induces a discrete diagonal-predecessor term $\tilde A_0$, and two independent input-dependent step sizes $\Delta_1(i,j)$, $\Delta_2(i,j)$ govern propagation along the two axes, so that the coefficients adapt per position and per direction. A normalized ratio $r_k=a_{0,k}/(a_{1,k}a_{2,k})$ yields a closed-form piecewise bound on the two step sizes; when a configuration falls outside the stable interval the steps are projected onto this bound, and the criterion is re-verified per position after training, which suppresses systematic local amplification without global damping. The recurrence is executed by a dual-diagonal wavefront scan: each update gathers information from two anti-diagonals, and the input enters the current state through a single projection, so that neither training nor inference flattens the feature map. Code is available at https://github.com/BitSsm/FM-Mamba-Runtime
Source:https://arxiv.org/abs/2611.22061PreviousGrid-Aware Assessment of Forced Oscillations from Spatially Distributed Large LoadsNextFacet-offset Polytope Expansion for Dynamic Operating Envelopes of Aggregated Distribution Grid Resources
Related posts

A Link You Can Just Open
0dev.to
Your coding agent's tests pass. It still edited files you never asked about.
0dev.to OpenSource
FINAL-Bench: VIDRAFT's Daily-Updated Global Weather Model Leaderboard Pits AI Against Traditional NWP on Equal Terms
0dev.to OpenSource
Errpedia: Is Your Exact $k$-NN Vector Search Really Exact?
0arXiv cs.DB
Reconstructing the Probability Measure of a Multi-group Curie-Weiss Model with Interacting Groups
0arXiv stat.TH
Bidirectional Random Projections
0arXiv stat.TH