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.
Martin, Rhodri Cusack, and Stefan Köhler
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4roles
background 1polarities
background 1representative citing papers
Errors-in-variables regression on ABIDE-I shows the IQ-motion slope is 4.67 times smaller than OLS estimates, and pooled models yield negative out-of-sample R-squared across all 19 sites.
Replacing the generic Stable Diffusion VAE with domain-specific MedVAE pretrained on 1.6M medical images improves diffusion-based SR PSNR by 2.91-3.29 dB on knee/brain MRI and chest X-ray, with gains in fine details and VAE quality predicting SR performance (R²=0.67).
EEG2Vision reconstructs images from EEG using diffusion models plus LLM-guided boosting, with reconstruction quality holding up reasonably as electrode count drops from 128 to 24 channels.
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.
-
The IQ-Motion Confound in Multi-Site Autism fMRI May Be Inflated by Site-Correlated Measurement Uncertainty
Errors-in-variables regression on ABIDE-I shows the IQ-motion slope is 4.67 times smaller than OLS estimates, and pooled models yield negative out-of-sample R-squared across all 19 sites.
-
Domain-Specific Latent Representations Improve the Fidelity of Diffusion-Based Medical Image Super-Resolution
Replacing the generic Stable Diffusion VAE with domain-specific MedVAE pretrained on 1.6M medical images improves diffusion-based SR PSNR by 2.91-3.29 dB on knee/brain MRI and chest X-ray, with gains in fine details and VAE quality predicting SR performance (R²=0.67).
-
EEG2Vision: A Multimodal EEG-Based Framework for 2D Visual Reconstruction in Cognitive Neuroscience
EEG2Vision reconstructs images from EEG using diffusion models plus LLM-guided boosting, with reconstruction quality holding up reasonably as electrode count drops from 128 to 24 channels.