J. Patrick Mayo

The paper trains an autoregressive Transformer on neural spiking data to decode motor behavior, showing broad utility across tasks but highlighting limitations in scaling.

The paper distinguishes attentional state and behavioral outcome using LFP power and phase in monkeys performing a visual attention task.

The paper identifies thalamic commissures in primates, showing they connect cortex to contralateral thalamus and exist in both healthy and malformed human brains.

The paper shows that high-frequency LFP power can decode attentional states as accurately as spikes, even with multiple electrodes.