BrainDistill: Implantable ECoG-based Motor Decoding with Task-Specific Knowledge Distillation

Transformer-based neural decoders with high parameter counts, pre-trained on large-scale datasets, have recently achieved high accuracy on complex brain-computer interface (BCI) tasks, such as motion-intention decoding. However, their large model size and high computational demands hinder their deployment in power-constrained implantable systems. To address this challenge, we introduce BrainDistill, a novel implantable motor decoding pipeline that integrates an implantable neural decoder (IND) with a task-specific knowledge distillation (TSKD) framework. Unlike standard feature distillation methods that attempt to preserve teacher representations in full, TSKD explicitly prioritizes features critical for decoding through supervised projection. Across multiple ECoG datasets, IND consistently outperforms prior neural decoders on motor decoding tasks, while its TSKD-distilled variant further outperforms alternative distillation methods. Finally, we present a quantization-aware training scheme that enables integer-only inference with activation clipping ranges learned during training. The quantized IND enables deployment under the strict power constraints of implantable BCIs with minimal performance loss.