{
  "id": "2609.33402",
  "title": "VaME: Exploring Variational Latent Reasoning for Multimodal Embeddings",
  "authors": "Peixi Wu, Mingzhou Jiang, Feipeng Ma, Biao Yang, Yunhao Zhou, Wei Yuan, Bosong Chai, Huizu Lin, Jie Chen, Zhangchi Hu, Fan Yang, Wenwu Ou, Hebei Li, Xiaoyan Sun",
  "first_public": "2026-09-27",
  "venue": "arXiv",
  "arxiv": "2609.33402",
  "paper_url": "https://arxiv.org/abs/2609.33402",
  "lens": [
    "continuous"
  ],
  "representation": [
    "multimodal-latent",
    "continuous-state"
  ],
  "computation": [
    "token-wise",
    "search"
  ],
  "training": [
    "supervised",
    "reinforcement-learning"
  ],
  "questions": [
    "capability",
    "efficiency"
  ],
  "evidence": [
    "empirical"
  ],
  "modality": [
    "multimodal",
    "vision"
  ],
  "summary": "Learns a distribution over continuous reasoning trajectories before producing a retrieval embedding. A lightweight decoder provides reconstruction supervision and a semantic reward for reinforcement learning, evaluated on image, video, and visual-document retrieval.",
  "provenance": "Primary-source literature search, 2026-10-18",
  "added_at": "2026-10-18",
  "author_names": [
    "Peixi Wu",
    "Mingzhou Jiang",
    "Feipeng Ma",
    "Biao Yang",
    "Yunhao Zhou",
    "Wei Yuan",
    "Bosong Chai",
    "Huizu Lin",
    "Jie Chen",
    "Zhangchi Hu",
    "Fan Yang",
    "Wenwu Ou",
    "Hebei Li",
    "Xiaoyan Sun"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2609.33402/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2609-33402",
  "citation_date": "2026-09-27",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2609.33402/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2609.33402/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2609.33402/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2609.33402/citation.csl.json"
}