MINE uses mechanistic interpretability on language-aligned image representations to generate per-voxel feature descriptions, validated via image generation and counterfactual edits that causally shift brain activation.
The Journal of Physiology160(1), 106–154 (1962)
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 6roles
background 2polarities
background 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.
Direction maps and pinwheel structures in MT emerge spontaneously when a spatiotemporal deep network is trained on videos with contrastive self-supervised learning and spatial regularization.
Stimulus symmetries render many neural representations functionally equivalent yet produce qualitatively different RSMs, including drifting ones from SGD or regularization in image-encoding networks.
Mathematical analysis shows sparse linear regression mitigates output dimension collapse in brain-to-image reconstruction at small data scales by exploiting sparsity in the brain-to-feature mapping.
Joint sparse coding and temporal dynamics in mPFC and computational networks reduce cross-context interference and enhance separability, enabling better retention in lifelong learning without extra heuristics.
citing papers explorer
-
Mechanistically Interpretable Neural Encoding Reveals Fine-Grained Functional Selectivity in Human Visual Cortex
MINE uses mechanistic interpretability on language-aligned image representations to generate per-voxel feature descriptions, validated via image generation and counterfactual edits that causally shift brain activation.
-
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.
-
Self-organized MT Direction Maps Emerge from Spatiotemporal Contrastive Optimization
Direction maps and pinwheel structures in MT emerge spontaneously when a spatiotemporal deep network is trained on videos with contrastive self-supervised learning and spatial regularization.
-
Stimulus symmetries can confound representational similarity analyses
Stimulus symmetries render many neural representations functionally equivalent yet produce qualitatively different RSMs, including drifting ones from SGD or regularization in image-encoding networks.
-
Overcoming Output Dimension Collapse: When Sparsity Enables Zero-shot Brain-to-Image Reconstruction at Small Data Scales
Mathematical analysis shows sparse linear regression mitigates output dimension collapse in brain-to-image reconstruction at small data scales by exploiting sparsity in the brain-to-feature mapping.
-
Joint sparse coding and temporal dynamics support context reconfiguration
Joint sparse coding and temporal dynamics in mPFC and computational networks reduce cross-context interference and enhance separability, enabling better retention in lifelong learning without extra heuristics.