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.
Marius Zöllner
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Self-organising memristive networks exhibit collective nonlinear dynamics that can support physical learning with parallels to biological plasticity and potential for energy-efficient edge intelligence.
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.
-
Self-Organising Memristive Networks as Physical Learning Systems
Self-organising memristive networks exhibit collective nonlinear dynamics that can support physical learning with parallels to biological plasticity and potential for energy-efficient edge intelligence.