arXiv:2609.31204v1 Announce Type: cross
Abstract: Recent fMRI foundation models differ substantially in the spatial scale at which they represent brain activity. ROI- and connectivity-based models ar...
By Mo Wang, Wenhao Ye, Zihan Ning, Jiayu Zuo, Junfeng Xia, Hongkai Wen, Quanying Liu
arXiv:2606. 04772v1 Announce Type: cross Abstract: Understanding the relationship between deep visual representations and the human visual system is a fundamental challenge in computational neuroscience.
By Hoang-Son Vo, Van-Hung Bui, Minh-Huy Mai-Duc, Tien-Dung Mai, Soo-Hyung Kim
The paper presents a unified framework that links vision foundation models to fMRI brain activity using sparse, interpretable visual prototypes. By replacing black‑box features with these prototypes and applying a linear readout, the model reveals which visual concepts drive neural responses, maps cortical organization through voxel tuning, and enables controlled stimulus synthesis to probe cortical selectivity. This approach provides a transparent, prototype‑based representation for studying visual representations in the human brain.
By Shi Chen, Seoyoung Ahn, Doris Tsao
FiberGeoText (FGT) is a vision‑language model that clusters short‑range superficial white matter streamlines from ultra‑high‑resolution diffusion MRI into population‑level groups. It jointly encodes each streamline’s 3‑D trajectory, cortical anatomical context (via text from multiple parcellation schemes), and shape, using a pretrained large language model to unify heterogeneous anatomical descriptions. Evaluations on 0.76 mm diffusion data show that FGT outperforms state‑of‑the‑art methods in cortical parcel coherence, shape consistency, cluster‑size consistency, and cross‑subject correspondence, and it generalizes well to unseen subjects, recovering 96.7 % of learned clusters.
By Yuqian Chen, R. Jarrett Rushmore, Guikun Chen, Fan Zhang, Edward Yeterian, Nikos Makris, Yogesh Rathi, Lauren J. O'Donnell
arXiv:2606. 00121v1 Announce Type: cross Abstract: Reconstructing visual stimuli from brain recordings has been a meaningful and challenging task in brain decoding.
By Yizhuo Lu, Changde Du, Qiongyi Zhou, Liuyun Jiang, Huiguang He
Understanding the relationship between deep visual representations and the human visual system is a fundamental challenge in computational neuroscience. While modern vision models achieve strong performance in image recognition, their correspondence with the hierarchical organization of the human visual cortex remains an open question.
FlatClip is a method that leverages frozen image foundation models to predict fMRI activity by mapping cortical signals onto anatomy‑linked flatmaps and extracting features with a SigLIP2 encoder. Only a lightweight downstream probe is trained, avoiding fMRI‑specific encoder pretraining or fine‑tuning. Experiments on four resting‑state benchmarks show FlatClip surpasses ROI‑level baselines on HCP and ADNI, while its performance varies on PPMI and remains below the best voxel‑level models; on NSD visual‑fMRI decoding, restricting inputs to task‑active cortex improves recognition, and spatial perturbations confirm the importance of cortical arrangement and input‑region selection.
By Mo Wang, Wenhao Ye, Zihan Ning, Jiayu Zuo, Junfeng Xia, Hongkai Wen, Quanying Liu
NEvo is a neural‑guided evolutionary video synthesis framework that generates dynamic stimuli optimized for specific brain regions in the visual cortex. It performs evolutionary search over a structured prompt space, guided by a dynamic encoding model that predicts voxel‑level responses to video inputs, thereby discovering hyper‑activating videos that outperform handcrafted localizers. The synthesized videos recover known selectivities across ventral, dorsal, and lateral pathways and reveal systematic differences in sensitivity to temporal dynamics, offering new insights into the progression of social‑dynamic features along the lateral stream.
By Yingtian Tang, Sogand Salehi, Ming Zhou, Amir Zamir, Leyla Isik, Martin Schrimpf
arXiv:2503. 13212v3 Announce Type: replace Abstract: Alignment between human brain networks and artificial models has become an active research area in vision science and machine learning.
By Mina Kamao, Hayato Ono, Ayumu Yamashita, Kaoru Amano, Masataka Sawayama
The human brain processes dynamic visual input through hierarchically organized, functionally specialized regions. While recent in silico brain encoding models can synthesize optimal stimuli to probe selectivity in different brain regions, prior work has been largely limited to static images, leaving dynamic visual processing underexplored.
The paper introduces Vis‑Lens, a framework that combines a variational autoencoder and a diffusion model to generate natural, realistic images that match preferred visual representations in both artificial neural networks and the human visual cortex. By applying an activation‑based prior, the method regularizes a structured visual representation landscape, enabling direct modification of latent codes without per‑image optimization. Experiments using fMRI data demonstrate that Vis‑Lens improves activation modulation and image realism compared to recent state‑of‑the‑art approaches.
By Yusong Zhao, Edgar Y. Walker, Hao Wang, Mi Lu
The study investigates whether sensory-aligned receptive fields provide computational benefits beyond mere resource efficiency in recurrent networks of Expressive Leaky Memory neurons. Across auditory and event-based visual classification tasks, receptive fields aligned with task-relevant sensory coordinates improve test accuracy compared to budget-matched random fields, but this advantage disappears when coordinates are scrambled or irrelevant. The benefit diminishes as neuronal expressivity increases, and generic synaptic sparsity regularization only partially recovers performance, indicating that structured receptive fields act as a computational prior beyond sparsity alone.
By Agnese Adorante, Aaron Spieler, Anna Levina