# LimiX-2 发布：面向通用结构化数据智能的上下文机制网络

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-09-15 08:00
- AIHOT 分数：37
- AIHOT 链接：https://aihot.news/items/cmu4u1o28084orokckbbtyaz6
- 原文链接：https://arxiv.org/abs/2609.17488

## AI 摘要

LimiX-2 是 LimiX 家族新模型，采用上下文机制网络（CMN）范式，并以 Context-Conditional Masked Modeling（CCMM）预训练，将上下文学习从目标中心预测转向机制导向的联合建模。在 TabArena、TALENT 和 BCCO 评测中，LimiX-2 优于当前数据集专用模型和表格基础模型。其特征注意力还能编码直接因果关系，可准确恢复因果骨架。

## 正文

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_{context}) objective of conventional tabular PFNs, it is designed around learning p(x, y mid D_{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, functional mechanisms, and observation processes. Evaluations on TabArena, TALENT, and BCCO show that LimiX-2 outperforms current dataset-specific models and tabular foundation models. Beyond predictive performance, the CMN paradigm also promotes causal awareness in LimiX-2: its feature attention encodes direct causal relationships, enabling accurate causal skeleton recovery.