LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence
LimiX-2 uses scaled contextual mechanism networks pretrained on synthetic causal data to outperform tabular foundation models and recover causal skeletons.
Published Sep 15, 2026▲ 816 on Hugging FaceCode ★ 4,373arXiv ↗
Only vote on papers you've read. Sign in with GitHub to vote.
LimiX-2 earns praise for scaling contextual mechanism networks via synthetic SCM pretraining and causal skeleton recovery, though critics find its joint-modeling claims unsupported by mechanism ablations, missing causal benchmarks, and absent code, weights, and latency figures.
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.