Association profile conditioning in a set-temporal transformer for cross-session intracortical motor decoding

arXiv:2609.39080 · q-bio.NC, cs.AI · Submitted 2026-09-30 · Read on arXiv

q-bio.NC, cs.AI

Submitted: 2026-09-30

Updated: 2026-09-30

Comments: 5 pages, 3 figures. Submitted to ICASSP 2027

Code: https://github.com/HsinyuanZhang/APST

License: http://creativecommons.org/licenses/by/4.0/

The gist: Intracortical motor decoders degrade across sessions because the set of recorded units changes and persisting units can alter how their firing relates to behavior.

Terminology

Abstract

Intracortical motor decoders degrade across sessions because the set of recorded units changes and persisting units can alter how their firing relates to behavior. Most existing methods update network weights on each new session or rely on unlabeled activity, which does not directly reveal such changes. We present APST, an Association Profile-conditioned Set-Temporal transformer that adapts to new sessions with all network weights frozen. From a few labeled calibration trials, APST summarizes how each unit's firing relates to behavior in a four-dimensional association profile computed in closed form. The profiles condition a set-attention encoder that accepts any number and order of units, followed by a causal transformer for streaming decoding. On held-out DANDI688 sessions from two monkeys, APST reaches velocity R squared of 0.78 and 0.81, versus 0.40 and 0.58 for a variant that uses neural activity alone, and matches or exceeds an RNN fine-tuned on the same trials. On FALCON private held-out evaluation, it attains R squared of 0.65, 0.42, and 0.44 on M1, M2, and H1.

Related papers