conv.

All stories
AIQuiet 2d · day 3

Apple releases LensVLM, a 9B model that compresses long text contexts as images

The vision language model selectively expands only relevant pages from compressed text, enabling efficient processing of lengthy documents.

newest coverage 2d agosummary written 2d ago3 pieces89 likes & upvotes10 comments Hacker NewsNewswires

What to know

  • Apple released LensVLM, a 9B Vision Language Model that compresses long text into images and selectively expands relevant sections.
  • The model supports multiple compression ratios (5x, 10x, 15x) for flexibility in balancing compression and quality.
  • Both model weights and source code are distributed under Apple's open research and sample code licenses.

Apple Model developer and publisher

Apple releases LensVLM, a 9B model that compresses long text contexts as images
huggingface.co

How it unfolded 2 developments, newest first · click a bar or a number to jump articlesposts

Peak 2 pieces in one hour at Sep 23, 2 PM; 3 pieces over 3 days (1 article · 2 posts) Sep 23, 2 PM — 2 pieces · 1 article · 1 post — Hacker News 1, Newswires 1Sep 23, 3 PM — quietSep 23, 4 PM — quietSep 23, 5 PM — quietSep 23, 6 PM — quietSep 23, 7 PM — quietSep 23, 8 PM — quietSep 23, 9 PM — quietSep 23, 10 PM — quietSep 23, 11 PM — quietSep 24, 12 AM — quietSep 24, 1 AM — 1 piece · 1 post — Hacker News 1Sep 24, 2 AM — quietSep 24, 3 AM — quietSep 24, 4 AM — quietSep 24, 5 AM — quietSep 24, 6 AM — quietSep 24, 7 AM — quietSep 24, 8 AM — quietSep 24, 9 AM — quietSep 24, 10 AM — quietSep 24, 11 AM — quietSep 24, 12 PM — quietSep 24, 1 PM — quietSep 24, 2 PM — quietSep 24, 3 PM — quietSep 24, 4 PM — quietSep 24, 5 PM — quietSep 24, 6 PM — quietSep 24, 7 PM — quietSep 24, 8 PM — quietSep 24, 9 PM — quietSep 24, 10 PM — quietSep 24, 11 PM — quietYesterday, 12 AM — quietYesterday, 1 AM — quietYesterday, 2 AM — quietYesterday, 3 AM — quietYesterday, 4 AM — quietYesterday, 5 AM — quietYesterday, 6 AM — quietYesterday, 7 AM — quietYesterday, 8 AM — quietYesterday, 9 AM — quietYesterday, 10 AM — quietYesterday, 11 AM — quietYesterday, 12 PM — quietYesterday, 1 PM — quietYesterday, 2 PM — quietYesterday, 3 PM — quietYesterday, 4 PM — quietYesterday, 5 PM — quietYesterday, 6 PM — quietYesterday, 7 PM — quietYesterday, 8 PM — quietYesterday, 9 PM — quietYesterday, 10 PM — quietYesterday, 11 PM — quietToday, 12 AM — quietToday, 1 AM — quietToday, 2 AM — quietToday, 3 AM — quietToday, 4 AM — quietToday, 5 AM — quietToday, 6 AM — quiet 12
Sep 24yesterdaynow · 7:07 AM ET
  1. 2

    Research paper published on selective context expansion

    An arXiv paper titled 'LensVLM: Selective Context Expansion for Compressed Visual Representation of Text' was posted, providing the academic foundation for the released model.

  2. 1

    Apple releases LensVLM model on Hugging Face

    Apple published LensVLM, a 9B Vision Language Model designed to compress long context as images and selectively expand only relevant pages to uncompressed form. The model supports 5x, 10x, and 15x compression options and includes modifications to the Qwen model base.

    “LensVLM is a 9B Vision Language Model (VLM) that scans compressed images of text, then selectively expands only the relevant pages to their uncompressed form via learned tools.”
    — Apple, Model developer · source
    1. 1 outlet LensVLM: Compressing long context as images, expanding only relevant pages

      first by HN Frontpage, 2d ago