{
  "id": "2609.30783",
  "title": "Skip the Talk, Re-Focus on Vision: Latent Reasoning for Reasoning Segmentation in Multimodal Large Language Models",
  "authors": "Tianhang Guo, Yulin He, Wei Chen, Wenjuan Zhou, Yuhang Li, Xinbiao Gan",
  "first_public": "2026-09-25",
  "venue": "arXiv",
  "arxiv": "2609.30783",
  "paper_url": "https://arxiv.org/abs/2609.30783",
  "lens": [
    "learned-tokens"
  ],
  "representation": [
    "discrete-token",
    "hidden-state",
    "multimodal-latent"
  ],
  "computation": [
    "token-wise"
  ],
  "training": [
    "supervised",
    "reinforcement-learning"
  ],
  "questions": [
    "capability",
    "efficiency"
  ],
  "evidence": [
    "empirical"
  ],
  "modality": [
    "multimodal",
    "vision"
  ],
  "summary": "LIRSeg generates a fixed sequence of learned special tokens before a target description and bounding box used for segmentation. Spatial alignment grounds the tokens' hidden states in relevant image regions, followed by training with segmentation rewards.",
  "provenance": "Primary-source literature search, 2026-10-18",
  "added_at": "2026-10-18",
  "author_names": [
    "Tianhang Guo",
    "Yulin He",
    "Wei Chen",
    "Wenjuan Zhou",
    "Yuhang Li",
    "Xinbiao Gan"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2609.30783/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2609-30783",
  "citation_date": "2026-09-25",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2609.30783/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2609.30783/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2609.30783/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2609.30783/citation.csl.json"
}