{
  "id": "2312.03052",
  "title": "Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models",
  "authors": "Yushi Hu, Otilia Stretcu, Chun-Ta Lu, Krishnamurthy Viswanathan, Kenji Hata, Enming Luo, Ranjay Krishna, Ariel Fuxman",
  "first_public": "2023-12-05",
  "added_at": "2026-10-26",
  "venue": "CVPR 2024",
  "arxiv": "2312.03052",
  "paper_url": "https://arxiv.org/abs/2312.03052",
  "html_url": "https://arxiv.org/html/2312.03052v2",
  "lens": [
    "internalized"
  ],
  "representation": [
    "hidden-state"
  ],
  "computation": [
    "depth-wise"
  ],
  "training": [
    "distillation",
    "supervised"
  ],
  "questions": [
    "capability",
    "efficiency"
  ],
  "evidence": [
    "empirical"
  ],
  "modality": [
    "multimodal",
    "vision"
  ],
  "summary": "Trains a vision-language model on answers and reasoning steps from executed visual programs. Separate answer and rationale objectives let the model answer image questions without generating the intermediate program or rationale at inference.",
  "provenance": "Primary-source literature review, 2026-10-26",
  "author_names": [
    "Yushi Hu",
    "Otilia Stretcu",
    "Chun-Ta Lu",
    "Krishnamurthy Viswanathan",
    "Kenji Hata",
    "Enming Luo",
    "Ranjay Krishna",
    "Ariel Fuxman"
  ],
  "record_url": "https://latent-implicit-thinking.github.io/papers/2312.03052/",
  "legacy_record_url": "https://latent-implicit-thinking.github.io/papers/#paper-2312-03052",
  "citation_date": "2023-12-05",
  "json_url": "https://latent-implicit-thinking.github.io/papers/2312.03052/record.json",
  "markdown_url": "https://latent-implicit-thinking.github.io/papers/2312.03052/index.md",
  "bibtex_url": "https://latent-implicit-thinking.github.io/papers/2312.03052/citation.bib",
  "csl_url": "https://latent-implicit-thinking.github.io/papers/2312.03052/citation.csl.json",
  "pdf_url": "https://arxiv.org/pdf/2312.03052",
  "publication": {
    "title": "Visual Program Distillation: Distilling Tools and Programmatic Reasoning into Vision-Language Models",
    "author_names": [
      "Yushi Hu",
      "Otilia Stretcu",
      "Chun-Ta Lu",
      "Krishnamurthy Viswanathan",
      "Kenji Hata",
      "Enming Luo",
      "Ranjay Krishna",
      "Ariel Fuxman"
    ],
    "year": 2024,
    "type": "paper-conference",
    "container_title": "Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)",
    "pages": "9590-9601",
    "url": "https://openaccess.thecvf.com/content/CVPR2024/html/Hu_Visual_Program_Distillation_Distilling_Tools_and_Programmatic_Reasoning_into_Vision-Language_CVPR_2024_paper.html",
    "source_url": "https://openaccess.thecvf.com/content/CVPR2024/html/Hu_Visual_Program_Distillation_Distilling_Tools_and_Programmatic_Reasoning_into_Vision-Language_CVPR_2024_paper.html",
    "verified_at": "2026-10-26"
  },
  "publication_bibtex_url": "https://latent-implicit-thinking.github.io/papers/2312.03052/publication.bib",
  "publication_csl_url": "https://latent-implicit-thinking.github.io/papers/2312.03052/publication.csl.json"
}