发表机构
Northwestern University; Ohio State University; Bosch Research North America（西北大学; 俄亥俄州立大学; 博世北美研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
Kaleido通过自适应输入渲染几何（折叠方式）并门控融合修复结果，仅训练0.05%参数，显著提升视觉模型在时间序列零样本预测上的精度。
AI 中文摘要
时间序列基础模型通过大规模时间语料库实现零样本预测；而视觉模型则无需此类语料，因为自然图像隐式地包含了预测器必须建模的模式，且经过ImageNet预训练的掩码自编码器通过修复序列的渲染图来预测该序列。然而，渲染后的序列并非自然图像，缩小这一差距需要时间感知的自适应。我们证明，渲染几何——即序列如何折叠和绘制——是一个可控且可混合的自适应轴。Kaleido检测主导周期，渲染一组规则生成的折叠几何，通过仅在验证集上拟合的逐位置凸门控组合各修复结果，并以固定比例将融合结果与零样本输出结合，除基线已发布的设置外，无需针对每个数据集调整超参数。仅训练LayerNorm（占参数量的0.05%），Kaleido在LTSF上将已发布的零样本基线的MSE降低了13%，在冻结状态下降低了6.6%；在GIFT-Eval上，其MASE较基线改善了7.4%，CRPS改善了19.3%。
英文摘要
Time-series foundation models buy zero-shot forecasting with large temporal corpora; a vision model needs none, since a natural image implicitly embeds the patterns a forecaster must model, and an ImageNet-pretrained masked autoencoder forecasts a series by inpainting a rendering of it. A rendered series is not a natural image, however, and closing that gap takes temporal-aware adaptation. We show that the rendering geometry - how the series is folded and drawn - is a controllable, mixable axis for it. Kaleido detects the dominant periods, renders a rule-generated set of fold geometries, combines the inpaintings with a convex per-position gate fit on validation only, and fuses the result with the zero-shot output at one fixed share, with no per-dataset hyperparameter beyond the baseline's published settings. Training only LayerNorm (0.05%), Kaleido lowers MSE by 13% against the published zero-shot baseline on LTSF and, frozen, by 6.6%; on GIFT-Eval it improves the baseline by 7.4% in MASE and 19.3% in CRPS.
CommentsAccepted at the NeurIPS 2026 Workshop on Foundation Models for Temporal Systems (FMTS)
