Research
StimFlow: Synthesizing Brain Activity from Images via Stimulus-conditioned Flow Matching
arXiv:2610.15341v1 Announce Type: new Abstract: The inherent variability of fMRI responses across trials encourages a generative view of the stimulus-to-response mapping. Prior generative encoders oft
arXiv:2610.15341v1 Announce Type: new Abstract: The inherent variability of fMRI responses across trials encourages a generative view of the stimulus-to-response mapping. Prior generative encoders often operate in compressed latent spaces and condition predominantly on semantic features, which provide limited low-level cues for early visual cortex. We propose StimFlow, which synthesizes fMRI directly in native voxel space using conditional flow matching with a linear path. This design aligns training and inference distributions, enabling competitive performance with a single sample and reducing reliance on averaging. To match the visual hierarchy, StimFlow combines structural DINOv2 features with semantic CLIP features, which prove complementary along the cortical processing stream. With a single sample, StimFlow achieves a per-voxel Pearson correlation of 0.371, matching baselines that average five draws. Generation in voxel space allows direct ROI analysis and concept localization without a decoder. Furthermore, it recovers over half of full-data performance from just one hour of scans, supporting efficient cross-subject adaptation.
Related
- Conditional Flow Matching for Single-Neuron Electrophysiology: Capturing Multimodal Responses Across Stimuli
- Flow Matching with Uncertainty Quantification and Guidance
- Divergence is Uncertainty: A Closed-Form Posterior Covariance for Flow Matching
- Zero-Shot Brain MRI Inpainting with 2.5D Unconditional Flow Priors
Source: arXiv cs.CV | 2026-10-14