DEX is a modular network using dynamically activated experts and a group-EMA director to learn emergent modular representations for multi-modality medical vision foundation models, evaluated on a new 4M-image benchmark across 10 modalities and 26 downstream tasks.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
dataset 1polarities
use dataset 1representative citing papers
FusionSense uses server-side fusion learning, filter-out-safe labels, and edge compaction to enable runtime-adaptive multimodal sensing that cuts energy up to 33x while preserving task quality on RGB+Depth data.
citing papers explorer
-
Learning Emergent Modular Representations in Multi-modality Medical Vision Foundation Models
DEX is a modular network using dynamically activated experts and a group-EMA director to learn emergent modular representations for multi-modality medical vision foundation models, evaluated on a new 4M-image benchmark across 10 modalities and 26 downstream tasks.
-
FusionSense: Tri-Stage Near-Sensor Learning for Runtime-Adaptive Multimodal Edge Intelligence
FusionSense uses server-side fusion learning, filter-out-safe labels, and edge compaction to enable runtime-adaptive multimodal sensing that cuts energy up to 33x while preserving task quality on RGB+Depth data.