M4Fuse introduces a lightweight state-space MoE architecture with cross-scale dual-stage gating that reduces parameters by 62.63% and improves average performance by 0.09% on BraTS2019 and BraTS2021 even at half the usual input resolution.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 4years
2026 4verdicts
UNVERDICTED 4roles
baseline 1polarities
baseline 1representative citing papers
The first generative framework that anonymizes event streams by synthesizing non-existent identities in an intermediate image domain while preserving structural integrity for downstream perception.
A differentiable fuzzy logic module called DKU discovers implicit concepts from image classification supervision and applies logical adjustments to improve class probabilities on PASCAL-VOC, COCO, and MedMNIST.
SBF augments 2D skeletons with scale, body, and optical-flow maps predicted by SFSNet to raise accuracy in video-based human action recognition.
citing papers explorer
-
M\textsuperscript{4}Fuse: Lightweight State-Space MoE with a Cross-Scale Gating Bridge for Brain Tumor Segmentation
M4Fuse introduces a lightweight state-space MoE architecture with cross-scale dual-stage gating that reduces parameters by 62.63% and improves average performance by 0.09% on BraTS2019 and BraTS2021 even at half the usual input resolution.
-
Generative Anonymization in Event Streams
The first generative framework that anonymizes event streams by synthesizing non-existent identities in an intermediate image domain while preserving structural integrity for downstream perception.
-
Learning to Reason: Targeted Knowledge Discovery and Fuzzy Logic Update for Robust Image Recognition
A differentiable fuzzy logic module called DKU discovers implicit concepts from image classification supervision and applies logical adjustments to improve class probabilities on PASCAL-VOC, COCO, and MedMNIST.
-
SBF: An Effective Representation to Augment Skeleton for Video-based Human Action Recognition
SBF augments 2D skeletons with scale, body, and optical-flow maps predicted by SFSNet to raise accuracy in video-based human action recognition.