SPINT: Spatial Permutation-Invariant Neural Transformer for Consistent Intracortical Motor Decoding

Eli Shlizerman (UW) · Jingyuan Li (University of Washington, Seattle) · Trung Le (University of Washington, Seattle) · Hao Fang (University of Washington) · Tung Nguyen (University of California, Los Angeles) · Lu Mi (Tsinghua University) · Amy L Orsborn (University of Washington) · Uygar Sümbül (Allen Institute)

context-dependent positional embeddingcontinuous motor decodingcross-session nonstationarityexplicit alignment techniquesfew-shot adaptationfixed neural identitiesflexible generalizationgradient-free adaptationintracortical brain-computer interfacesmulti-session datasetsneural population activity nonstationarityrobust cross-session generalizationscalable neural decoding frameworkspatial permutation-invariant neural transformerunit-specific identities

Intracortical Brain-Computer Interfaces (iBCI) decode behavior from neural population activity to restore motor functions and communication abilities in individuals with motor impairments. A central challenge for long-term iBCI deployment is the nonstationarity of neural recordings, where the composition and tuning profiles of the recorded populations are unstable across recording sessions. Existing approaches attempt to address this issue by explicit alignment techniques; however, they rely on fixed neural identities and require test-time labels or parameter updates, limiting their generalization across sessions and imposing additional computational burden during deployment. In this work, we address the problem of cross-session nonstationarity in long-term iBCI systems and introduce SPINT - a Spatial Permutation-Invariant Neural Transformer framework for behavioral decoding that operates directly on unordered sets of neural units. Central to our approach is a novel context-dependent positional embedding scheme that dynamically infers unit-specific identities, enabling flexible generalization across recording sessions. SPINT supports inference on variable-size populations and allows few-shot, gradient-free adaptation using a small amount of unlabeled data from the test session. We evaluate SPINT on three multi-session datasets from the FALCON Benchmark, covering continuous motor decoding tasks in human and non-human primates. SPINT demonstrates robust cross-session generalization, outperforming existing zero-shot and few-shot unsupervised baselines while eliminating the need for test-time alignment and fine-tuning. Our work contributes an initial step toward a robust and scalable neural decoding framework for long-term iBCI applications.