LensVLM-9B by Apple

Automated excerpt

Published on May 7 Authors: , , , , , , , , Abstract Vision-Language Models can process text as rendered images, but accuracy degrades with compression; LensVLM addresses this by scanning compressed images and selectively expanding relevant parts through learned tools, maintaining high accuracy even at high compression ratios. Building on Qwen3. 5-9B-Base, LensVLM maintains accuracy comparable to the full-text upper bound at 4. 3x effective compression and outperforms retrieval-based, text- and visual-compression baselines up to 10. 1x effective compression across seven text QA benchmarks.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.