Expert specialization in vision MoE models is dominated by a stable animate-inanimate distinction visible from gating to readout, with broader tuning to continuous visual and semantic dimensions rather than narrow categorical preferences.
Walker, Fabian H
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Feature visualization on TRIBE v2 brain encoders recovers the known ventral visual hierarchy from V1 to V4 and produces distinctive patterns for MT, FFA, and PPA, with optimized stimuli driving ~4x higher activation than natural images.
citing papers explorer
-
Beyond Routing: Characterising Expert Tuning and Representation in Vision Mixture-of-Experts
Expert specialization in vision MoE models is dominated by a stable animate-inanimate distinction visible from gating to readout, with broader tuning to continuous visual and semantic dimensions rather than narrow categorical preferences.
-
Feature Visualization Recovers Known Cortical Selectivity from TRIBE v2
Feature visualization on TRIBE v2 brain encoders recovers the known ventral visual hierarchy from V1 to V4 and produces distinctive patterns for MT, FFA, and PPA, with optimized stimuli driving ~4x higher activation than natural images.