AI 中文总结
研究针对金融序列建模，提出VAIOM这一仅解码器的Transformer。它将输入表示与输出似然分离，采用混合连续输入模型结合多种目标与监督。实验表明其在测试中优于LightGBM基线，验证了连续输入等方法的有效性，提升了回报似然。
AI 中文摘要
金融观测是连续、异质且有噪声的，而仅解码器的下一个令牌模型通常围绕离散符号输入构建。我们引入了用于序数回报建模的向量输入自回归推理（VAIOM），这是一种仅解码器的Transformer，用于对一小时外汇数据条进行概率下一个回报建模。VAIOM将输入表示与输出似然分开：连续多元金融事件向量在输入时保留数值结构，而下一个波动率归一化回报桶上的分类分布支持交叉熵训练和似然评估。所选的0.9M混合连续输入模型将连续事件特征与分类资产元数据、混合市场状态回报头、Gap、波动率 regime和序数辅助目标以及全序列监督相结合。模型和预处理使用2024年之前的训练数据进行拟合；模型在2024年下半年验证中进行选择，并在两个2025年测试期进行评估，无需重新拟合。在三个独立的训练种子中，每个模型在两个测试半期中均优于固定的单条LightGBM基线。对于规范检查点，相对于LightGBM的配对增益为每个事件0.029和0.043比特。验证实验表明，在相同分类回报目标下，连续输入优于离散令牌输入，全序列监督优于最后位置训练，并且辅助表示塑造与混合结构回报头一起在受控比较中提高了回报似然。一项支持能力研究发现，评估的最小完整架构等级在当前语料库上实现了最强的验证似然。
英文摘要
Financial observations are continuous, heterogeneous, and noisy, whereas decoder-only next-token models are usually built around discrete symbolic inputs. We introduce Vector-Input Autoregressive Inference for Ordinal-Return Modeling (VAIOM), a decoder-only Transformer for probabilistic next-return modeling on one-hour foreign-exchange bars. VAIOM separates input representation from output likelihood: continuous multivariate financial-event vectors preserve numerical structure at the input, while a categorical distribution over the next volatility-normalized return bucket supports cross-entropy training and likelihood evaluation. The selected 0.9M Hybrid Continuous Input model combines continuous event features with categorical asset metadata, a Mixture-of-Market-States return head, Gap, volatility-regime, and Ordinal auxiliary objectives, and full-sequence supervision. Models and preprocessing are fit using pre-2024 Train data; models are selected on 2024H2 Validation and evaluated without refitting on two 2025 Test periods. Across three independent training seeds, every model outperforms fixed single-bar LightGBM baseline in both Test halves. For the canonical checkpoint, paired gains over LightGBM are 0.029 and 0.043 bits per event. Validation experiments show that continuous input improves over discrete-token input under the same categorical return objective, full-sequence supervision improves over last-position training, and auxiliary representation shaping together with a mixture-structured return head improves return likelihood in controlled comparisons. A supporting capacity study finds that the smallest evaluated complete architecture rung achieves the strongest Validation likelihood on the present corpus.
