iiinova — where your digital self keeps evolving

Reposted by Yash Shah

bioRxiv Neuroscience @biorxiv-neursci.bsky.social · 02/10/2026

Eccentricity, but not category, organizes infant ventral temporal cortex www.biorxiv.org/content/10.64898/20…

Reposted by Yash Shah

bioRxiv Neuroscience @biorxiv-neursci.bsky.social · 19/08/2026

Sign language communication enhances representations for hands in high-level visual cortex www.biorxiv.org/content/10.64898/20…

011

Reposted by Yash Shah

bioRxiv Neuroscience @biorxiv-neursci.bsky.social · 14/08/2026

Spatial organization of neural responses to physical and agentive movement dynamics is reflected in intrinsic functional connectivity www.biorxiv.org/content/10.64898/20…

011

Reposted by Yash Shah

Stanford Vision and Perception Neuroscience Lab @stanfordvpnl.bsky.social · 04/08/2026

VPNL is at #CCN2026 !! Check out our lab members' presentations this week :)

0176

Reposted by Yash Shah

Khai Loong Aw @khaiaw.bsky.social · 04/08/2026

Our Stanford NeuroAI Lab is presenting at the Cognitive Computational Neuroscience conference #CCN2026 🥳 Come say hi to us!! Imran, @norcalneuro.bsky.social, @dyamins.bsky.social, Khaled, @ynshah.bsky.social @seojinlee.bsky.social , @clionaod.bsky.social , Khai

085

Reposted by Yash Shah

arXiv q-bio.NC Neurons and Cognition @qbionc-bot.bsky.social · 20/07/2026

Trepka, Xia, Zhu, Saleki, Lopes, Cital, Willeke, Kim, Moore: STSBench: A Large-Scale Dataset for Modeling Neuronal Activity in the Dorsal Stream of Primate Visual Cortex arxiv.org/abs/2607.15631 arxiv.org/pdf/2607.15631 arxiv.org/html/2607.15631

011

Reposted by Yash Shah

bioRxiv Neuroscience @biorxiv-neursci.bsky.social · 30/06/2026

Dorsal visual stream development improves symmetry of receptive field coverage and spatial attention www.biorxiv.org/content/10.64898/20…

042

Yash Shah @ynshah.bsky.social · 23/05/2026

A really neat work on how representations evolve over time in DNNs

020

Reposted by Yash Shah

bioRxiv Neuroscience @biorxiv-neursci.bsky.social · 21/04/2026

Prolonged development of tonotopic tuning in human auditory cortex www.biorxiv.org/content/10.64898/20…

032

Reposted by Yash Shah

Khai Loong Aw @khaiaw.bsky.social · 14/04/2026

Children exhibit visual understanding from limited experience, orders of magnitude less than our best models. We introduce the Zero-shot World Model (ZWM). Trained on a single child's visual experience, BabyZWM rapidly generates competence across diverse benchmarks with no task-specific training. 🧵

15724

Reposted by Yash Shah

bioRxiv Neuroscience @biorxiv-neursci.bsky.social · 07/04/2026

A retinotopic wiring principle of the human brain www.biorxiv.org/content/10.64898/20…

0107

Reposted by Yash Shah

bioRxiv Neuroscience @biorxiv-neursci.bsky.social · 10/02/2026

Self-supervised learning yields representational signatures of category-selective cortex www.biorxiv.org/content/10.64898/20…

072

Reposted by Yash Shah

bioRxiv Neuroscience @biorxiv-neursci.bsky.social · 08/02/2026

Geometric constraints in the development of primate extrastriate visual cortex www.biorxiv.org/content/10.64898/20…

012

Reposted by Yash Shah

bioRxiv Neuroscience @biorxiv-neursci.bsky.social · 03/02/2026

Efficient task generalization and humanlike face perception in models that learn to discriminate face geometry www.biorxiv.org/content/10.64898/20…

053

Reposted by Yash Shah

bioRxiv Neuroscience @biorxiv-neursci.bsky.social · 06/02/2026

Early face deprivation leads to long-lasting deficits in cortical face processing www.biorxiv.org/content/10.64898/20…

173

Reposted by Yash Shah

bioRxiv Neuroscience @biorxiv-neursci.bsky.social · 05/02/2026

Retinal waves shape starburst amacrine cell dendrite development through a direction-selective dendritic computation www.biorxiv.org/content/10.64898/20…

083

Reposted by Yash Shah

bioRxiv Neuroscience @biorxiv-neursci.bsky.social · 13/12/2025

Human cortical networks trade communication efficiency for computational reliability. www.biorxiv.org/content/10.64898/20…

0178

Reposted by Yash Shah

bioRxiv Neuroscience @biorxiv-neursci.bsky.social · 05/11/2025

Functional architecture for speed tuning in primary visual cortex of carnivores www.biorxiv.org/content/10.1101/202…

022

Reposted by Yash Shah

bioRxiv Neuroscience @biorxiv-neursci.bsky.social · 25/10/2025

Re-emergence of orientation coding in primate IT cortex and deep networks reveals functional hubs for visual processing www.biorxiv.org/content/10.1101/202…

021

Reposted by Yash Shah

bioRxiv Neuroscience @biorxiv-neursci.bsky.social · 04/10/2025

Representations in the hippocampal-entorhinal system emerge from learning sensory predictions www.biorxiv.org/content/10.1101/202…

051

Reposted by Yash Shah

Robert Hawkins @rdhawkins.bsky.social · 15/09/2025

Very exciting preprint from Dan Yamins' NeuroAI lab, proposing Probabilistic Structure Integration (PSI), a way to bootstrap from pixels to higher-level visual abstractions through a kind of visual prompting. One of the deepest and most original ideas I've read in a while. arxiv.org/abs/2509.09737

arxiv.org

World Modeling with Probabilistic Structure Integration

We present Probabilistic Structure Integration (PSI), a system for learning richly controllable and flexibly promptable world models from data. PSI consists of a three-step cycle. The first step, Prob...

0185

Reposted by Yash Shah

Martin Schrimpf @mschrimpf.bsky.social · 02/10/2025

I've been arguing that #NeuroAI should model the brain in health *and* in disease -- very excited to share a first step from Melika Honarmand: inducing dyslexia in vision-language-models via targeted perturbations of visual-word-form units (analogous to human VWFA) 🧠🤖🧪 arxiv.org/abs/2509.24597

14912

Reposted by Yash Shah

arXiv q-bio.NC Neurons and Cognition @qbionc-bot.bsky.social · 30/09/2025

Haider Al-Tahan, Mayukh Deb, Jenelle Feather, N. Apurva Ratan Murty: End-to-end Topographic Auditory Models Replicate Signatures of Human Auditory Cortex arxiv.org/abs/2509.24039 arxiv.org/pdf/2509.24039 arxiv.org/html/2509.24039

014

Reposted by Yash Shah

bioRxiv Neuroscience @biorxiv-neursci.bsky.social · 29/09/2025

Metabolic organization of macaque visual cortex reflects retinotopic eccentricity and category selectivity www.biorxiv.org/content/10.1101/202…

021

Reposted by Yash Shah

bioRxiv Neuroscience @biorxiv-neursci.bsky.social · 23/09/2025

Functional organization of the human visual system at birth and across late gestation www.biorxiv.org/content/10.1101/202…

077

Reposted by Yash Shah

bioRxiv Neuroscience @biorxiv-neursci.bsky.social · 04/08/2025

Unfolding spatiotemporal representations of 3D visual perception in the human brain www.biorxiv.org/content/10.1101/202…

072

Reposted by Yash Shah

bioRxiv Neuroscience @biorxiv-neursci.bsky.social · 27/07/2025

Visual Word Form Area demonstrates individual and task-agnostic consistency but inter-individual variability www.biorxiv.org/content/10.1101/202…

043

Reposted by Yash Shah

bioRxiv Neuroscience @biorxiv-neursci.bsky.social · 26/07/2025

Many-Two-One: Diverse Representations Across Visual Pathways Emerge from A Single Objective www.biorxiv.org/content/10.1101/202…

062

Yash Shah @ynshah.bsky.social · 13/07/2025

And of course because this is my first ever post I forgot to include hashtags! #ICML2025

000

Yash Shah @ynshah.bsky.social · 13/07/2025

Check out the paper if interested and come talk to me during the poster session (July 17, Thursday at 4:30pm) if in Vancouver! icml.cc/virtual/2025.... [11/n]

icml.cc

ICML Poster Confounder-Free Continual Learning via Recursive Feature NormalizationICML 2025

100

Yash Shah @ynshah.bsky.social · 13/07/2025

Finally, R-MDN, because it operates on the level of individual examples, can be integrated in both convolutional neural networks and vision transformers—which was one of the significant limitations of the MDN algorithm. [10/n]

110

Yash Shah @ynshah.bsky.social · 13/07/2025

And R-MDN makes equitable predictions across population groups, such as across both boys and girls when performing sex classification on the ABCD (Casey et al., 2008) dataset in the presence of pubertal development scores as the confounder. [9/n]

110

Yash Shah @ynshah.bsky.social · 13/07/2025

R-MDN can also remove the influence from multiple confounding variables, as seen when testing on the ADNI (Mueller et al., 2005) dataset. [8/n]

110

Yash Shah @ynshah.bsky.social · 13/07/2025

Since R-MDN is a normalization layer, it can be tacked on to various already-proposed model architectures. [7/n]

100

Yash Shah @ynshah.bsky.social · 13/07/2025

R-MDN effectively removes confounder influence from learned DNN features, as rigorously verified in both synthetically controlled environments and real-world datasets. [6/n]

100

Yash Shah @ynshah.bsky.social · 13/07/2025

We propose Recursive Metadata Normalization (R-MDN), a normalization layer that leverages the statistical recursive least squares algorithm to iteratively update its internal parameters based on previously computed values whenever new data are received. [5/n]

100

Yash Shah @ynshah.bsky.social · 13/07/2025

However, within continual learning, data becomes available sequentially, often over the span of several years, as in longitudinal studies. [4/n]

100

Yash Shah @ynshah.bsky.social · 13/07/2025

Prior work such as BR-Net (Adeli et al., 2020), MDN (Lu et al., 2021), and P-MDN (Vento et al., 2022) proposed to learn confounder-invariant representations in DNNs work within a static learning setting and assume that the algorithm has access to all data at the outset of training. [3/n]

100

Yash Shah @ynshah.bsky.social · 13/07/2025

Confounders are variables that influence both the outcome (i.e., the output) and the exposure (i.e., the input) in a study, causing spurious associations. [2/n]

100

Yash Shah @ynshah.bsky.social · 13/07/2025

I am excited to share that my work on "Confounder-Free Continual Learning via Recursive Feature Normalization" has been accepted at ICML 2025! Very grateful to @camgonza.bsky.social , @mhabbasi.bsky.social , @qingyuz.bsky.social, Kilian Pohl, and @eadeli.bsky.social for always supporting me. [1/n]

151

Reposted by Yash Shah

bioRxiv Neuroscience @biorxiv-neursci.bsky.social · 12/07/2025

Retinal waves reveal axial biases in modular patterns of cortical activity that predict future orientation preferences www.biorxiv.org/content/10.1101/202…

053

Reposted by Yash Shah

bioRxiv Neuroscience @biorxiv-neursci.bsky.social · 03/06/2025

Visual processing of manipulable objects in the ventral stream is modulated by inputs from parietal action systems www.biorxiv.org/content/10.1101/202…

071

Reposted by Yash Shah

Hannes Mehrer @CCN2026 @hannesmehrer.bsky.social · 27/05/2025

Announcement: Workshop at #CCN2025 🧠 Modeling the Physical Brain: Spatial Organization & Biophysical Constraints 🗓️ Monday, Aug 11 | 🕦 11:30–18:00 CET | 📍 Room A2.07 🔗 Register: tinyurl.com/CCN-physical... #NeuroAI @cogcompneuro.bsky.social

tinyurl.com

Home

1145

Reposted by Yash Shah

bioRxiv Neuroscience @biorxiv-neursci.bsky.social · 23/05/2025

A two-dimensional space of linguistic representations shared across individuals www.biorxiv.org/content/10.1101/202…

021

Reposted by Yash Shah

arxiv cs.CV @arxiv-cs-cv.bsky.social · 08/04/2025

Wanhee Lee, Klemen Kotar, Rahul Mysore Venkatesh, Jared Watrous, Honglin Chen, Khai Loong Aw, Daniel L. K. Yamins 3D Scene Understanding Through Local Random Access Sequence Modeling arxiv.org/abs/2504.03875

021