arXiv cs.LG + cs.RO + cs.HC· Xinhong Xu, Yimeng Zhang, Yuanlong Zhang·· 2 天前AI 评分58
CAPT：跨数据集跨物种迁移的钙成像群体动态多任务 Transformer
CAPT: A Multi-task Continuous Autoregressive Transformer enabling Cross-dataset and Cross-species Transfer for Calcium Population Dynamics
AI 导读
作者提出 CAPT，一个连续自回归群体 Transformer，通过连续 patch tokenization 直接建模钙成像轨迹，并以均方误差目标自回归训练。
正文 · 原文
Abstract:Calcium imaging has enabled large-scale recordings of neural population activity across diverse animals, laboratories, and experimental paradigms. However, these datasets remain highly fragmented: Existing approaches are often designed for individual datasets or tasks, making it unclear whether their learned representations are reusable for new calcium imaging trace datasets. To tackle this gap, we present \textbf{CAPT}, a \textbf{C}ontinuous \textbf{A}utoregressive \textbf{P}opulation \textbf{T}ransformer for calcium population dynamics. CAPT models continuous calcium traces directly through a continuous patch tokenization strategy and is trained autoregressively with a mean squared error objective, enabling end-to-end training and adaptation to diverse downstream tasks. We first pretrain CAPT on a large-scale mouse calcium imaging dataset and evaluate its transferability across independent mouse, larval zebrafish, and \textit{C. elegans} datasets collected by different laboratories. In these transfer settings, the pretrained backbone is frozen and only adaptation modules, i.e., neuron and session embeddings or task-specific heads, are updated. Across neural population forecasting and behavior decoding tasks, CAPT consistently outperforms specialized and general-purpose baselines, demonstrating that a single continuous autoregressive backbone can learn representations that transfer beyond the original pretraining distribution. Beyond predictive performance, multimodal analyses using NeuroPAL annotations in \textit{C. elegans} datasets show that CAPT embeddings form a shared functional space across datasets and capture cell-identity-related structure. Together, these results suggest that continuous autoregressive modeling provides an effective framework for learning reusable calcium population representations that transfer across datasets, experimental paradigms, and species.
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2607.23258 [cs.AI] |
| (or arXiv:2607.23258v3 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.23258 arXiv-issued DOI via DataCite |
Submission history
From: Xinhong Xu [view email]
[v1]
Sat, 25 Jul 2026 15:53:55 UTC (6,395 KB)
[v2]
Tue, 4 Aug 2026 13:16:56 UTC (6,396 KB)
[v3]
Sun, 18 Oct 2026 07:57:05 UTC (6,404 KB)
来源：arXiv cs.LG + cs.RO + cs.HC · arxiv.org