{
  "url": "https://appliedfrontier.nl/en/research/signal-a0d5fb4ea71c8f86/",
  "title": "Homebrewed SLMs: Autoregressive and Masked Diffusion Language Models Built at Home for Portuguese",
  "published": "2026-10-29",
  "excerpt": "Building a language model of one's own no longer requires a data centre. This tutorial trains one from scratch, tokenizer included, on one consumer GPU,",
  "content_sha256": "85855ba1228e926d2a938a85b759a8363af6ee300e98640f190a076a53309330",
  "extracted_chars": 1679,
  "artifact_links": [
    "https://arxiv.org/abs/2610.40533"
  ],
  "arxiv_id": "2610.40533",
  "extraction_scope": "preprint_abstract_metadata",
  "full_text_available": false,
  "id": "signal-a0d5fb4ea71c8f86",
  "org": "Research community",
  "topic": "Compute & efficiency",
  "source_kind": "preprint",
  "status": "unreviewed-source-report",
  "analysis_method": "deterministic_research_triage_v2",
  "novelty_verified": false,
  "proof_checked": false,
  "peer_review_verified": false,
  "matched_terms": [
    "Compute & efficiency"
  ],
  "checked_at": "2026-11-01T12:17:04+00:00",
  "first_seen": "2026-10-31T19:32:55+00:00",
  "source_hash": "ae299d219f86dcf2c7b11873eb5a861b3d6e737228f57a5feeda9491bd37c0c5",
  "source_url": "https://arxiv.org/abs/2610.40533",
  "language": "en",
  "indexing": "noindex_until_editorially_enriched"
}
