{
  "id": "2609.19878",
  "title": "Uni-LaDiR: Latent Diffusion Unifies Multimodal Reasoning",
  "authors": "Haoqiang Kang, Yizhe Zhang, Nikki Lijing Kuang, Jiatao Gu, Yian Ma, Lianhui Qin",
  "first_public": "2026-09-17",
  "venue": "arXiv",
  "arxiv": "2609.19878",
  "paper_url": "https://arxiv.org/abs/2609.19878",
  "lens": [
    "continuous",
    "beyond-sequential"
  ],
  "representation": [
    "multimodal-latent",
    "continuous-state"
  ],
  "computation": [
    "diffusion"
  ],
  "training": [
    "supervised",
    "distillation"
  ],
  "questions": [
    "architecture",
    "capability",
    "generalization"
  ],
  "evidence": [
    "empirical"
  ],
  "modality": [
    "multimodal",
    "vision",
    "language"
  ],
  "summary": "Encodes teacher reasoning steps from text, images, point clouds, and robot states into a shared continuous representation. A jointly trained diffusion reasoner generates these states at inference, evaluated on visual question answering and robotic manipulation.",
  "provenance": "Primary-source literature search, 2026-10-18",
  "added_at": "2026-10-18",
  "author_names": [
    "Haoqiang Kang",
    "Yizhe Zhang",
    "Nikki Lijing Kuang",
    "Jiatao Gu",
    "Yian Ma",
    "Lianhui Qin"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2609.19878/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2609-19878",
  "citation_date": "2026-09-17",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2609.19878/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2609.19878/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2609.19878/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2609.19878/citation.csl.json"
}