{
  "id": "2412.08635",
  "title": "Multimodal Latent Language Modeling with Next-Token Diffusion",
  "authors": "Yutao Sun, Hangbo Bao, Wenhui Wang, Zhiliang Peng, Li Dong, Shaohan Huang, Jianyong Wang, Furu Wei",
  "first_public": "2024-12-11",
  "venue": "arXiv",
  "arxiv": "2412.08635",
  "paper_url": "https://arxiv.org/abs/2412.08635",
  "lens": [
    "beyond-sequential"
  ],
  "representation": [
    "multimodal-latent"
  ],
  "computation": [
    "diffusion"
  ],
  "training": [
    "pretraining"
  ],
  "questions": [
    "capability"
  ],
  "evidence": [
    "empirical"
  ],
  "modality": [
    "multimodal"
  ],
  "summary": "Encodes continuous data such as images as vectors, then generates those vectors with diffusion inside a causal transformer. This is related work on multimodal generation, rather than a method trained directly on reasoning steps.",
  "provenance": "Awesome-Latent-CoT",
  "author_names": [
    "Yutao Sun",
    "Hangbo Bao",
    "Wenhui Wang",
    "Zhiliang Peng",
    "Li Dong",
    "Shaohan Huang",
    "Jianyong Wang",
    "Furu Wei"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2412.08635/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2412-08635",
  "citation_date": "2024-12-11",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2412.08635/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2412.08635/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2412.08635/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2412.08635/citation.csl.json"
}