#state space models

try —

5 papers match

cs.CV2026

Cortical-SSM: A Deep State Space Model for Motor Imagery Decoding from EEG Signals

Shuntaro Suzuki, Shunya Nagashima, Komei Sugiura

The paper introduces Cortical-SSM, a deep state space model that decodes motor imagery EEG signals by integrating temporal, spatial, and frequency information, achieving higher acc…

#eeg decoding#motor imagery#state space models#deep learning
cs.LG2026

Lag Operator SSMs: A Geometric Framework for Structured State Space Modeling

Sutashu Tomonaga, Kenji Doya, Noboru Murata

The paper proposes a geometric, first‑principles framework for building discrete‑time structured state space models using a novel lag operator, enabling modular design of sequence…

#state space models#sequence modeling#lag operator#discrete-time systems
cs.CV2026

DCVC-MB: Neural B-Frame Video Compression using State Space Models

Arjun Arora, Calvin-Khang Ta, Carlos Restrepo-Galeano +7

The paper introduces DCVC-MB, a neural video codec for low-delay B‑frame compression that uses state‑space models for bidirectional prediction and an entropy‑aware skipping mechani…

#neural video compression#b-frame coding#state space models#entropy coding
cs.CV2026

MambaPSA: A Mamba-based Replacement for C2PSA in YOLO26

Sheng-Wei Chan, Chia-Min Lin, Hsin-Jui Pan +4

The paper introduces MambaPSA, a lightweight Mamba‑based module that replaces the C2PSA block in the YOLO26 object detector and adds a bidirectional Vision Mamba (BiViM) to the nec…

#object detection#state space models#mamba architecture#lightweight networks
cs.LG2026

TSSM: Triaxial State Space Model for Global Station Weather Forecasting with Temporal-Variable-Historical Modeling

Songru Yang, Zili Liu, Tao Han +7

The paper introduces a Triaxial State Space Model that leverages period‑aligned historical weather data and a temporal‑variable‑historical paradigm to improve global station weathe…

#weather forecasting#time series modeling#state space models#extreme event prediction

One search, two signals: results blend meaning (embedding similarity, so papers that never use your words still surface) with keyword matches on titles, abstracts and summaries. Free, no sign-in needed.