Skip to content
Preprint

NeuroPB: Scaling Neural Decoding with Pretrained Behavioral Representations

Aug 2026 · 0 citations · 31 references
Computer Science

TL;DR

NeuroPB is introduced, a framework that scales neural decoding by transferring knowledge from pretrained behavioral representations and achieves performance comparable to pretraining on macaque trajectories, demonstrating that transferable kinematic structure is shared across biological and artificial models.

Abstract

Decoding continuous motor trajectories from neural activity is essential for developing practical brain-computer interfaces (BCIs). However, current neural decoders are constrained by the limited scale and heterogeneity of neural recordings. In contrast, behavioral data can be collected more readily and at substantially larger scale from humans, animals, simulations, and robotic systems. Here, we introduce NeuroPB, a framework that scales neural decoding by transferring knowledge from pretrained behavioral representations. NeuroPB first pretrains a motor encoder on large-scale motor behavior data and then aligns neural activity with the resulting behavioral representation space using a limited set of paired neural-behavioral recordings. A neural encoder and lightweight motor decoder are subsequently optimized to reconstruct continuous movement from the aligned neural representations. Across multiple macaque motor datasets, behavioral pretraining improves trajectory decoding, including an 11% $R^2$ increase on center-out and 8% on random-target compared with training the motor encoder from scratch. Notably, pretraining on robotic trajectories achieves performance comparable to pretraining on macaque trajectories, demonstrating that transferable kinematic structure is shared across biological and artificial models. Moreover, decoding performance improves as the scale and diversity of robotic pretraining data increase, when the amount of neural data is fixed. Pretraining also enhances generalization across recording sessions, subjects, and motor tasks, with only 10% calibration needed to match training from scratch. Overall, these results establish behavioral pretraining as a scalable source for neural decoding and provide a promising route toward high-performance and calibration-efficient BCIs under limited neural data.

View source

Similar papers

Brain-Conditioned Action Policies for Neural Motor Decoding

This work proposes BrainVLA, a framework that enables neural motor decoding by drawing on a pretrained vision-language-action (VLA) model through language-mediated alignment, and establishes a route for neural motor decoding to draw on large-scale robotic priors through brain-conditioned VLA policies.

Lu-Yao Jin, Run-Ning Zhao, Huan Zhao et al. · 0 citations
Open access Oct 2026

Spatial Sampling and Temporal Dynamics Shape Motor Decoding from Broadband Intracortical Signals

These findings demonstrate that the neural features most informative for motor decoding depend on both the spatial sampling configuration and the temporal structure of the recorded activity, and highlight the importance of low-frequency population dynamics.

Cong Zheng, Yong-Xiang Xiao, He Cui · 0 citations
Open access Aug 2026

LAND: Latent Aligned Neural-Behavioral Dynamics via Flow Matching for Generalizable Movement Decoding

Generalizable movement decoding remains a central challenge for invasive brain–computer interfaces (BCIs), as decoders trained under limited calibration conditions often fail to generalize to unseen movement speeds, limbs, and subjects. Existing decoding methods are typically trained on paired data collected under rest...

Ruwei Yao, Jun-Ze Zheng, Yan-Lu Wang et al. · 0 citations

Pretraining for Sample-Efficient Neural Interfaces

This work proposes MAPA, an otherwise vanilla masked autoencoder with two spatial encodings, an anatomical region embedding and a relative positional encoding that together enable it to learn neural representations that transfer to unseen subjects and across various tasks.

Ben-Ting Tang, Z. Spalding, G. Cogan · 0 citations

BrainWideBench: Benchmarking large-scale pretraining and across-animal transfer in multi-region neural recordings

BrainWideBench is presented, 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.

Alexandre Andre, S. Mahato, Vinam Arora et al. · 1 citation
Preprint Oct 2026

Decoding Neural Population Dynamics through Robotic Analog

A robotic analog of biological motor systems with artificial muscles, multimodal sensors, and a neural network controller trained via reinforcement learning discovered that neural rotations generate oscillatory maneuvers orthogonal to the reaching direction, optimizing trajectory adjustments.

Wen-Hui Chen, Ji-Yue Tao, Yi-Tao Cheng et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.