{
  "id": 13735,
  "url": "https://arxiv.org/abs/2607.22314v1",
  "title": "Evolution-Aware MSA Reasoning for Subsampling via Factor Graphs",
  "summary": "Multiple Sequence Alignments (MSAs) provide protein language models with explicit evolutionary context, but their large depth makes subsampling unavoidable under limited token budgets. Existing strategies, including random selection, identity-based filtering, and diversity-driven sampling, are effective heuristics, yet provide limited control over the evolutionary signals retained in the subset. In this work, we recast MSA subsampling as an explicit optimization problem, where key evolutionary m",
  "authors": "Zhangzhi Xiong, Minzhang Li, Haotian Yu, Sixian Shen, Kexin Zhang, Mingrui Li et al.",
  "category": "research",
  "topics": "biotech",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-24T13:55:21.000Z",
  "fetched_at": "2026-07-27T05:10:06.638Z",
  "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/13735",
  "original_url": "https://arxiv.org/abs/2607.22314v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}