{
  "id": "2610.30824",
  "title": "Loop to Look Better: Learning Adaptive Depth for Question-Guided Perception in Vision-Language Models",
  "authors": "Wencheng Ye, Anning Hu, Hongye Fang, Tianyi Wang, Junchi Yan",
  "first_public": "2026-10-22",
  "added_at": "2026-10-23",
  "venue": "arXiv",
  "arxiv": "2610.30824",
  "paper_url": "https://arxiv.org/abs/2610.30824",
  "html_url": "https://arxiv.org/html/2610.30824v1",
  "lens": [
    "recurrent"
  ],
  "representation": [
    "hidden-state",
    "multimodal-latent"
  ],
  "computation": [
    "recurrent",
    "depth-wise"
  ],
  "training": [
    "supervised"
  ],
  "questions": [
    "architecture",
    "capability",
    "efficiency"
  ],
  "evidence": [
    "empirical"
  ],
  "modality": [
    "multimodal",
    "vision",
    "language"
  ],
  "summary": "LoopLook repeatedly refines visual features in response to a question, with a learned stopping rule and token-wise mixing of intermediate states. Adapts the vision encoder while keeping the language model frozen; the extra computation occurs before ordinary answer generation.",
  "provenance": "Primary-source literature review, 2026-10-23",
  "author_names": [
    "Wencheng Ye",
    "Anning Hu",
    "Hongye Fang",
    "Tianyi Wang",
    "Junchi Yan"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2610.30824/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2610-30824",
  "citation_date": "2026-10-22",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2610.30824/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2610.30824/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2610.30824/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2610.30824/citation.csl.json",
  "pdf_url": "https://arxiv.org/pdf/2610.30824"
}