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

  • 类型：arxiv
  • 标识：2609.17488
  • 链接：https://arxiv.org/abs/2609.17488
  • 主分类：engineering
  • 形态：method
  • 被引：5
  • 被引来源：Semantic Scholar
  • S2被引：5
  • OpenAlex被引：0
  • 影响力被引：0
  • TLDR：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 representat
  • OpenAlex ID：W7213412166
  • OpenAlex DOI：10.48550/arxiv.2609.17488
  • DOI：10.48550/arxiv.2609.17488
  • DOI来源：OpenAlex
  • 开放获取：green
  • 开放获取链接：https://doi.org/10.48550/arxiv.2609.17488
  • OpenAlex更新：2026-09-18
  • 待LLM分类：否
  • 标题中文：LimiX-2：迈向通用结构化数据智能的上下文机制网络
  • TLDR中文：我们推出 LimiX 家族新模型 LimiX-2，通过先前建立的 scaling laws 指导模型与数据规模扩展。LimiX-2 采用上下文机制网络 (CMNs) 范式，并以上下文条件掩码建模 (CCMM) 进行预训练。CMNs 将上下文学习的组织原则从以目标为中心的预测转向以机制为导向的联合建模。它并非围绕传统表格 PFN 的 p(y|x, D_context) 目标设计网络，而是围绕学习 p(x, y|D_context)——一种上下文依赖的表征
  • 来源文件：
  • /inbox/tom/_candidates/2026-09-17-agent-rag-longcontext-candidates.json
  • [OpenAlex backfill]
  • /inbox/tom/_candidates/2026-09-18-agent-rag-longcontext-candidates.json
  • [S2 enrich]