IC-based encoding models predict stimulus-driven functional network time series from LLM representations in story-listening fMRI, yielding consistent auditory and language components across subjects while noise artifacts remain unpredictable.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Independent-Component-Based Encoding Models of Brain Activity During Story Comprehension
IC-based encoding models predict stimulus-driven functional network time series from LLM representations in story-listening fMRI, yielding consistent auditory and language components across subjects while noise artifacts remain unpredictable.