{
  "id": 3659,
  "url": "https://arxiv.org/abs/2605.27286v2",
  "title": "Falcon-X: A Time Series Foundation Model for Heterogeneous Multivariate Modeling",
  "summary": "Time series foundation models (TSFMs) are transforming the forecasting paradigm through large-scale cross-domain pretraining. However, most existing TSFMs remain univariate, and recent efforts to enable cross-variate modeling still operate directly within the raw variate space. This design introduces fundamental limitations in semantic alignment and relational expressivity. Specifically, raw-space group mixing lacks a dedicated mechanism to align heterogeneous physical quantities, while standard",
  "authors": "Yiding Liu, Yifan Hu, Hongjie Xia, Peiyuan Liu, Hongzhou Chen, Xilin Dai et al.",
  "category": "research",
  "topics": "safety-alignment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-26T17:03:21.000Z",
  "fetched_at": "2026-07-14T16:30:23.248Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/3659",
  "original_url": "https://arxiv.org/abs/2605.27286v2",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}