Entity · paper

Leveraging unlabelled data for generalizable neural population decoding

paperactiveprovisionalleveraging-unlabelled-data-for-generalizable-neural-population-decoding-a02277b0·1 events·first seen Jul 16, 2026

Aliases: Leveraging unlabelled data for generalizable neural population decoding

Co-occurring entities

MOJO

More like this (12)

Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation Graph Neural Network leveraging Higher-order Class Label Connectivity for Heterophilous Graphs Beyond Independent Labels: Schwartz-Geometry Decoding for Human Value Detection lambda-scaled structural decoding Graph Neural Network Encoder Selective Disclosure Watermarking for Large Language Models Scaling LLM Reasoning from Minimal Labels: A Semi-Supervised Framework with a Lightweight Verifier Influcoder: Distilling Decoders' Gradient Influence Rankings into an Encoder for Data Attribution Localized Adaptation Reveals Distinct Learning Signatures in Transformers Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal Linear representations of grammaticality in neural language models Neural Surrogate Models

Recent events (1)

4arXiv · cs.LG·Jul 16, 2026·source ↗

MOJO framework combines masked autoencoding with supervised learning for generalizable neural population decoding

Researchers introduce MOJO (Masked autOencoder-based JOint training), a training framework that augments spike-tokenizing neural decoding models with self-supervised learning via masked autoencoding alongside supervised objectives. Evaluated on spiking datasets from monkey motor cortex and multi-regional mouse recordings, MOJO outperforms purely supervised models, with especially strong gains in few-shot and label-limited settings. The framework also generalizes to human electrocorticography during speech, achieving performance comparable to neuro-foundation models designed for continuous signals. The work advances a path toward more scalable and flexible training of neural foundation models using unlabelled data.

MOJO Leveraging unlabelled data for generalizable neural population decoding