LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence· Limix-2：实现通用结构化数据智能的上下文机制网络
We introduce LimiX-2, a new model in the LimiX family, developed through model and data scaling guided by our previously established scaling laws. LimiX-2 adopts the Contextual Mechanism Networks (CMNs) paradigm and is pretrained with Context-Conditional Masked Modeling (CCMM). CMNs shifts the organizing principle of in-context learning from target-centric prediction to mechanism-oriented joint modeling. Rather than centering the network on the $p(y \mid x, D_{\mathrm{context}})$ objective of conventional tabular PFNs, it is designed around learning $p(x, y \mid D_{\mathrm{context}})$, a context-dependent representation of the joint structure underlying data generation. Pretraining uses synthetic datasets generated by structural causal models (SCMs) spanning diverse graph structures, funct
Limix-2 通过上下文机制网络实现对结构化数据的智能处理。
- 核心方法
- 采用上下文机制网络（CMNs）范式，通过上下文条件掩码建模（CCMM）进行预训练，学习数据生成的联合结构。
- 适合谁读
- 研究者
- 要解决的问题
- 现有模型在处理结构化数据时主要关注目标预测，缺乏对数据生成机制的深入理解。
- 关键实验
- 使用合成数据集进行预训练，并在多个结构化数据任务上进行了评估，但未提供具体实验结果。
- 主要贡献
- 1. 提出了CMNs范式，侧重于机制导向的联合建模；2. 通过SCMs合成的多样化图结构数据集进行预训练，提高了模型对结构化数据的理解能力。
- 意义与局限
- 该模型有望提高结构化数据的智能处理水平，推动AI在更多领域的应用；局限在于需要大量高质量的合成数据来指导预训练。