A new framework shows concept subspaces are not unique, estimator choice affects containment and disentanglement, LEACE works well but generalizes poorly, and HuBERT encodes phone info as contained and disentangled from speaker info while speaker info resists compact containment.
and Mesgarani, Nima , month = jan, year =
2 Pith papers cite this work, alongside 5 external citations. Polarity classification is still indexing.
2
Pith papers citing it
5
external citations · external index
years
2026 2verdicts
UNVERDICTED 2representative citing papers
The CPA-PA metric approximates ground-truth neural activity via CCA alignment and participant averaging, yielding 300-1000% better single-participant evaluations than conventional scores on synthetic and real MEEG data.
citing papers explorer
-
A framework for analyzing concept representations in neural models
A new framework shows concept subspaces are not unique, estimator choice affects containment and disentanglement, LEACE works well but generalizes poorly, and HuBERT encodes phone info as contained and disentangled from speaker info while speaker info resists compact containment.
-
Robust Evaluation of Neural Encoding Models via ground-truth approximation
The CPA-PA metric approximates ground-truth neural activity via CCA alignment and participant averaging, yielding 300-1000% better single-participant evaluations than conventional scores on synthetic and real MEEG data.