From $\beta$-Level to BOLD-Level: Modeling Neural Dynamics for Visual Brain Encoding

Existing visual brain encoding models typically predict GLM-estimated $\beta$ responses, which summarize each stimulus-evoked BOLD time course as a single condition-wise amplitude. However, fMRI is acquired as time-resolved BOLD signals, and compressing these signals into a single $\beta$ amplitude does not retain the temporal information needed to characterize response timing and evolution. We propose $\text{BOLDSyner}$, a stimulus-aligned BOLD encoding framework that directly predicts stimulus-aligned BOLD responses by decomposing each condition into a temporal response profile and a signed voxel-wise spatial response pattern, modeling the two factors with asymmetric dual-branch diffusion, and recombining them under direct BOLD-level supervision. Across four NSD subjects, BOLDSyner achieves the state-of-the-art prediction performance at both the $\beta$ and BOLD levels, increasing $\beta$-level correlation from 0.687 to 0.739 and BOLD-level correlation from 0.157 to 0.610. Compared with $\beta$-level signals, the predicted BOLD responses recover category-dependent temporal effects observed in measured responses ($r=0.866$ across 120 subject–ROI–category cells), while preserving the category selectivity and semantic relationships captured by $\beta$-level signals. Collectively, these results imply the effectiveness and necessity of mechanistically grounded, time-resolved BOLD signal prediction.