{
  "id": "2611.05066",
  "title": "VIGOR: Visual Gain Ordering for Hallucination Mitigation in Multimodal Discrete Diffusion Language Models",
  "authors": "Junzhe Chen, Tian Qin, Eugenie Shi, Tianshu Zhang, Qiang Ju, Lijie Wen",
  "first_public": "2026-11-03",
  "added_at": "2026-11-09",
  "venue": "arXiv",
  "arxiv": "2611.05066",
  "paper_url": "https://arxiv.org/abs/2611.05066",
  "html_url": "https://arxiv.org/html/2611.05066v1",
  "lens": [
    "beyond-sequential"
  ],
  "representation": [
    "discrete-token"
  ],
  "computation": [
    "diffusion",
    "parallel"
  ],
  "training": [
    "inference-only"
  ],
  "questions": [
    "controllability",
    "capability"
  ],
  "evidence": [
    "empirical"
  ],
  "modality": [
    "multimodal",
    "vision"
  ],
  "summary": "Chooses which masked positions to fill by comparing predictions with and without the image. Committing visually supported tokens earlier reduces hallucination during multimodal diffusion decoding.",
  "provenance": "Primary-source literature review, 2026-11-09",
  "author_names": [
    "Junzhe Chen",
    "Tian Qin",
    "Eugenie Shi",
    "Tianshu Zhang",
    "Qiang Ju",
    "Lijie Wen"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2611.05066/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2611-05066",
  "citation_date": "2026-11-03",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2611.05066/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2611.05066/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2611.05066/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2611.05066/citation.csl.json",
  "pdf_url": "https://arxiv.org/pdf/2611.05066"
}