BrainWideBench: Benchmarking large-scale pretraining and across-animal transfer in multi-region neural recordings.
Year: 2026
Type: preprint
Abstract: Advances in large-scale neural recording have made it possible to collect data across many animals and distributed brain regions, raising the question of whether this scale can be exploited to learn general-purpose neural representations transferable across diverse downstream tasks. Yet, progress toward this goal has been limited by fragmented evaluation protocols and a narrow focus on individual task domains. Here, we present BrainWideBench, a benchmark for evaluating across-animal transfer on multi-region neural recordings, built on the International Brain Laboratory Brainwide Map dataset of neural and behavioral recordings spanning 276 brain regions from 139 mice performing a sensory-guided decision-making task. The benchmark is organized around three complementary task suites that evaluate whether learned representations support downstream decoding of behavior, can predict masked or future neural activity, and can recover biologically meaningful anatomical organization. With this benchmark, we systematically evaluate pretraining methods across transfer settings, including finetuning on downstream objectives and zero-shot generalization to unseen animals. Our results confirm pretraining improves performance over matched single-session baselines, but we show current methods exhibit heterogeneity in transfer capabilities: gains depend strongly on the alignment between pretraining objectives and downstream tasks. No single approach performs uniformly well across all three suites, and most methods are designed to only address a subset of them. Together, these findings suggest that learning representations that jointly generalize across behavior, dynamics, and anatomy remains an open challenge. By providing a unified and reproducible evaluation suite, BrainWideBench establishes a framework for measuring progress toward general-purpose models of the mouse brain. Code is available at this link.
Source: PubMed
Authors: Alexandre Andre, Shivashriganesh P Mahato, Vinam Arora, Keshav Balaji, Divyansha Lachi, Nanda H Krishna, Jingyun Xiao, Yizi Zhang, Ximeng Mao, Wenrui Ma, Han Yu, Daniel Birman, Niccolò Bonacchi, Gaelle A Chapuis, Joana A Catarino, Felicia Davatolhagh, Mayo Faulkner, Laura Freitas-Silva, Fei Hu, Julia M Huntenburg, Anup Khanal, Inês Laranjeira, Petrina Lau, Guido T Meijer, Nathaniel J Miska, Jean-Paul Noel, Alejandro Pan-Vazquez, Georg Raiser, Cyrille Rossant, Karolina Z Socha, Anne E Urai, Miles J Wells, Steven J West, Olivier Winter, Blake Richards, Guillaume Lajoie, Cole Hurwitz, Mehdi Azabou, Matthew R Whiteway, Liam Paninski, Eva L Dyer
Institutions: University of Pennsylvania, Mila - Quebec Artificial Intelligence Institute, Université de Montréal, Stanford University, Columbia University, Allen Institute, ISPA - Instituto Universitário, William James Center for Research, University of Geneva, Karolinska Institutet, University of California, Los Angeles, University College London, Champalimaud Foundation, Chinese University of Hong Kong, Donders Institute for Brain, Cognition and Behaviour, University of Minnesota, Princeton University, Leiden University, McGill University
Language: English
Subfield: Cognitive Neuroscience
Field: Neuroscience
Domain: Life Sciences
Open Access status: green
Funders: National Science Foundation, University of Pennsylvania, Canadian Institute for Advanced Research, Wellcome Trust, National Institutes of Health, University of California, San Diego, Natural Sciences and Engineering Research Council of Canada, National Institute of Neurological Disorders and Stroke
Awards: CI-New: Cognitive Hardware and Software Ecosystem Community Infrastructure (CHASE-CI), G2271590008, Towards Deploying a Science-Driven Regional Interoperable Science DMZ, NeuroNex Theory Team: Columbia University Theoretical Neuroscience Center, CC* NPEO: Toward the National Research Platform, CCRI: ABR: Cognitive Hardware and Software Ecosystem Community Infrastructure (CHASE-CI), Category II: A Prototype National Research Platform, International Brain Laboratory, CC*DNI DIBBs: The Pacific Research Platform, AI Institute for Artificial and Natural Intelligence, CAREER: Building interpretable models of neural population activity through view-invariant representation learning and alignment, CCRI: ENS: Cognitive Hardware and Software Ecosystem Community Infrastructure (CHASE-CI), Neural and Computational Architecture for Complex Navigation and Subjective Self-Location, State-dependent Decision-making in Brainwide Neural Circuits, Enhancing the International Brain Laboratory's Video Processing Pipeline with Advanced Pose Estimation and Action Segmentation Tools
OpenAlex ID: W7213988565