{
  "id": 10203,
  "url": "https://arxiv.org/abs/2607.11374v1",
  "title": "Surprisingly Simple and Effective Multi-Domain Graph Foundation Model through Graph-to-Table Alignment",
  "summary": "Graph Foundation Models (GFMs) have emerged as a promising paradigm for learning transferable representations across diverse graph domains. Recent advancements in GFMs have been largely dominated by two paradigms: Graph Neural Network and Large Language Model (LLM) based methods. However, these methods often face a fundamental dilemma between training with limited data and a heavy reliance on textual attributes. Tabular foundation models (TFMs) offer a potential alternative, as node features and",
  "authors": "Chunyu Hu, Tianyin Liao, Ge Lan, Xingxuan Zhang, Jianxin Li, Peng Cui et al.",
  "category": "research",
  "topics": "safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-13T10:35:56.000Z",
  "fetched_at": "2026-07-14T16:55:59.928Z",
  "source_slug": "arxiv-cslg",
  "source_name": "arXiv cs.LG",
  "source_homepage": "https://arxiv.org/list/cs.LG/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/10203",
  "original_url": "https://arxiv.org/abs/2607.11374v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}