LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence

2026-09-15

AI Summary

LimiX-2通过采用Contextual Mechanism Networks和Context-Conditional Masked Modeling预训练方法，解决了结构化数据智能的一般性问题，并在多个评估中表现出色。

Abstract

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, 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.

Problem

• Contextual Mechanism Networks
• Structured-Data Intelligence
• in-context learning
• joint modeling
• causal awareness

Innovation

• Contextual Mechanism Networks
• Context-Conditional Masked Modeling
• Structural Causal Models
• Causal Awareness