arXiv cs.AI· Peicheng Wu, Zhenyu Bu, Runze Ma, Lin Du·· 14 小时前AI 评分22
REALM：面向 LFP 建模的回顾式编码器对齐框架
REALM: Retrospective Encoder Alignment for LFP Modeling
AI 导读
REALM 是一个用于因果 LFP 行为解码的回顾式知识蒸馏框架，将预训练的多会话双向 Mamba-2 教师模型（经连续掩码自编码预训练）的表征迁移到紧凑的因果学生模型。
正文 · 原文
Abstract:Spike activity has been the dominant neural signal for behavior decoding because its high spatiotemporal resolution supports accurate decoding. However, as intracortical brain-computer interfaces (iBCIs) move toward higher channel counts and wireless operation, the high sampling rates required to record spikes create substantial power and bandwidth demands. Local field potentials (LFPs) offer complementary advantages, including greater long-term stability, lower energy consumption, and lower bandwidth requirements. However, LFP-based decoders often achieve lower accuracy and rely on non-causal architectures that cannot be used directly for real-time deployment. We propose REALM, a retrospective knowledge distillation (RKD) framework for causal LFP behavior decoding. Inspired by offline-to-online distillation in speech recognition, REALM transfers non-causal representational knowledge from a pretrained, multi-session bidirectional LFP teacher to a causal student model. We first pretrain a bidirectional Mamba-2 teacher across multiple recording sessions using continuous masked autoencoding (CMAE), and then distill its representation into a compact causal student using a combined objective of representation alignment and autoencoding. REALM achieves the highest mean accuracy among the compared decoders in both label-free and fine-tuned pipelines, with statistically significant improvements over each baseline, including the state-of-the-art CrossModalDistill. It does so using LFPs alone throughout pretraining, distillation, and decoding, with less than half the parameters of CrossModalDistill's published student and one-tenth of its pretraining time. These results show that a causal LFP-only model can achieve decoding accuracy competitive with a non-causal multi-modal model, offering a practical and scalable approach for next-generation wireless and implantable iBCIs.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Neurons and Cognition (q-bio.NC) |
| Cite as: | arXiv:2605.14867 [cs.LG] |
| (or arXiv:2605.14867v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.14867 arXiv-issued DOI via DataCite |
Submission history
From: Peicheng Wu [view email]
[v1]
Thu, 14 May 2026 14:16:22 UTC (4,080 KB)
[v2]
Wed, 30 Sep 2026 23:31:03 UTC (2,792 KB)
[v3]
Sun, 25 Oct 2026 19:01:03 UTC (2,794 KB)
来源：arXiv cs.AI · arxiv.org