跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2609.17488 · v2

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

首次提交 2026-09-16 01:30
版本更新 2026-11-19 15:56
雷达观测 2026-11-20 19:58
arXiv ↗PDF ↗

摘要

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∣x,Dcontext)p(y \mid x, D_{\mathrm{context}}) objective of conventional tabular PFNs, it is designed around learning p(x,y∣Dcontext)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.

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

本站首次收录为 v2,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v2 · 2026-11-19 15:56 · 最新观测版本

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

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∣x,Dcontext)p(y \mid x, D_{\mathrm{context}}) objective of conventional tabular PFNs, it is designed around learning p(x,y∣Dcontext)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.

查看此版本解读 →查看此版本原文 ↗