多模态潜在扩散生成稀有金融事件样本，XGBoost 分类 AUC 达 0.96
Scenario Augmentation for Rare Financial Events via Multimodal Latent Diffusion
搞量化风控的可以看看：用扩散模型合成极端行情样本，XGBoost 分类 AUC 冲到 0.96，比纯真实数据训练还高。
一篇 arXiv 论文提出用多模态潜在扩散模型增广稀有金融事件数据。每个市场窗口用三种对齐模态表示：结构化市场变量、空间图像变换、组合收益序列，分别经 VAE 映射到潜在空间后由类条件扩散模型学习联合分布。以 CVaR 定义稀有窗口并引导生成少数类样本，在美国科技股四个窗口长度上合成保真度超过表格扩散基线。混合真实与生成样本训练的 XGBoost 分类器 AUC 达 0.953-0.960，高于仅用真实数据的基线。
Scenario Augmentation for Rare Financial Events via Multimodal Latent Diffusion
Extreme market movements are scarce, heterogeneous, and difficult to learn from imbalanced historical data. We study whether generative augmentation can improve the representation and classification of CVaR-labeled rare financial windows while retaining the complementary structure exposed by different financial representations. Each market window is expressed through three aligned modalities: structured market variables, a spatial image transformation, and a sequence of portfolio returns. Separate variational autoencoders map the modalities to compact latent codes, and a class-conditional diffusion model learns their joint latent distribution. Conditional Value-at-Risk (CVaR) provides a risk-aware definition of rare windows and directs generation toward the minority regime. Across four window lengths on U.S. technology equities, the resulting synthetic samples improve fidelity and support relative to tabular diffusion baselines. An XGBoost classifier trained with real and generated samples attains AUCs of 0.953 - 0.960, exceeding both tabular generators and the corresponding real-only baselines. These results show that multimodal latent generation can provide useful synthetic stress scenarios for data-scarce financial risk models.