arXiv：cs.LG· Hanrui Lyu, Baiyuan Chen, Tianshu Tan, Matthew R. Whiteway, Maxwell D. Melin, Ji Xia, Linyang He, Bradly C. Stadie, Anne Churchland, Liam Paninski, Yizi Zhang·· 3 小时前AI 评分37
NeuroLens：从长期神经记录中学习神经语义的潜在嵌入
NeuroLens: Learning Latent Embeddings of Neural Semantics from Chronic Recordings
AI 导读
基于 JEPA 框架的自监督模型 NeuroLens 可从长期神经记录中学习去噪的语义潜在表示，通过自适应编码器将变化的神经元群体映射到统一潜在空间，并在潜在空间中进行预测以降低对记录不稳定性的敏感度。在小鼠和人类的长期皮层内数据上，该表示提升了对决策与语义任务变量的解码能力，多日预训练可泛化到未来会话并实现对新神经元群体的快速少样本适配，解码稳定性优于现有基线。
正文
Authors:Hanrui Lyu, Baiyuan Chen, Tianshu Tan, Matthew R. Whiteway, Maxwell D. Melin, Ji Xia, Linyang He, Bradly C. Stadie, Anne Churchland, Liam Paninski, Yizi Zhang
Abstract:Understanding how neural activity represents higher-order cognition and how these representations evolve over time has long been a central pursuit in neuroscience. However, current analytical tools cannot easily distinguish representational plasticity from recording instability in chronic neural recordings. Here, we introduce NeuroLens (Latent Embeddings of Neural Semantics), a self-supervised model based on the Joint-Embedding Predictive Architecture (JEPA) framework that learns denoised, semantically informative latents from chronic neural recordings. An adaptive encoder maps changing neural populations into a common latent space, while a temporal predictor learns structure that supports prediction of future latent states. By predicting in latent space, NeuroLens captures temporally predictable structure and reduces sensitivity to transient, recording-specific variability. Across chronic intracortical data in mice and humans, the learned representations improve decoding of decision-making and semantic task variables. Multi-day pretraining enables generalization to future sessions, rapid few-shot adaptation to unseen neural populations, and more stable decoding over time than state-of-the-art baselines. Together, these results establish NeuroLens as a new paradigm for studying how neural representations change during learning and over long timescales.
| Subjects: | Machine Learning (cs.LG); Neurons and Cognition (q-bio.NC) |
| Cite as: | arXiv:2610.02864 [cs.LG] |
| (or arXiv:2610.02864v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02864 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hanrui Lyu [view email]
[v1]
Fri, 2 Oct 2026 06:00:26 UTC (3,966 KB)
来源：arXiv：cs.LG · arxiv.org