mlsanityData to 14 Oct 2026

StimFlow: Synthesizing Brain Activity from Images via Stimulus-conditioned Flow Matching

arXiv 2610.15341 ↗First posted 11 Oct 2026cs.CV cs.AIcited by 0

On the map: Diffusion models → Flow matching, time series and science also fits: Medical imaging and segmentation

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 23 of its 37 references that are in the map. First posted on arXiv 11 Oct 2026.

Builds on

23 of 37 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Riemannian Flow Matching for Brain Connectivity Matrices via Pullback Geometry20 May
  2. 2022Flow Matching for Generative Modeling6 Oct
  3. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow7 Sep

Other references · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  5. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  7. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  8. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  9. 2022Scalable Diffusion Models with Transformerscited by 6,054
  10. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  11. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  12. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
8 more
  1. 2022A ConvNet for the 2020scited by 3,579
  2. 2020GLU Variants Improve Transformercited by 1,804
  3. 2019Root Mean Square Layer Normalizationcited by 1,480
  4. 2023Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priorscited by 160
  5. 2024MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Datacited by 109
  6. 2014Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Brain's Ventral Visual Pathwaycited by 94
  7. 2023The Algonauts Project 2023 Challenge: How the Human Brain Makes Sense of Natural Scenescited by 36
  8. 2025Flow Matching for Medical Image Synthesis: Bridging the Gap Between Speed and Qualitycited by 25

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026MultiFlow: Vision-Driven Multimodal fMRI Encoding via Stimulus-Informed Source Flow Matching
  2. 2026FM-fMRI: Event Conditioned Flow Matching for Rest-to-Task fMRI Time-Series Synthesis
  3. 2026Flow Matching with In-Context Priors for Out-of-Distribution Brain Dynamics
  4. 2023Reconstructing seen images from human brain activity via guided stochastic search
  5. 2026NeuroFlow: Toward Unified Visual Encoding and Decoding from Neural Activity
  6. 2022Semantic Brain Decoding: from fMRI to conceptually similar image reconstruction of visual stimuli
  7. 2025Sparse Autoencoders Bridge The Deep Learning Model and The Brain
  8. 2026Functional MRI Time Series Generation via Wavelet-Based Image Transform and Spectral Flow Matching for Brain Disorder Identification