{
  "id": "2610.23302",
  "title": "Look, Reason, Draw a Region: Recursive Refinement for Spatial Context Prediction",
  "authors": "Wajeeha Tahir, Anna Tegon, Lionnus Kesting, Gamze İslamoğlu, Kristóf Karacs, Luca Benini, Thorir Mar Ingolfsson",
  "first_public": "2026-10-16",
  "added_at": "2026-10-22",
  "venue": "arXiv",
  "arxiv": "2610.23302",
  "paper_url": "https://arxiv.org/abs/2610.23302",
  "html_url": "https://arxiv.org/html/2610.23302v1",
  "lens": [
    "recurrent"
  ],
  "representation": [
    "multimodal-latent",
    "hidden-state"
  ],
  "computation": [
    "recurrent",
    "hierarchical"
  ],
  "training": [
    "supervised"
  ],
  "questions": [
    "architecture",
    "capability",
    "generalization"
  ],
  "evidence": [
    "empirical"
  ],
  "modality": [
    "multimodal",
    "vision"
  ],
  "summary": "Repeatedly updates hidden reasoning and answer states from image features and a spatial-language prompt using a shared transformer. Decodes the refined answer state into a convex region mask and compares it with a single-step model.",
  "provenance": "Primary-source literature review, 2026-10-22",
  "author_names": [
    "Wajeeha Tahir",
    "Anna Tegon",
    "Lionnus Kesting",
    "Gamze İslamoğlu",
    "Kristóf Karacs",
    "Luca Benini",
    "Thorir Mar Ingolfsson"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2610.23302/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2610-23302",
  "citation_date": "2026-10-16",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2610.23302/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2610.23302/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2610.23302/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2610.23302/citation.csl.json",
  "pdf_url": "https://arxiv.org/pdf/2610.23302"
}
