Apple releases LensVLM-9B, compressing long context as images and expanding only relevant pages
victormustar · hn · 2026-09-24
Apple has released LensVLM-9B on Hugging Face, a new approach to long-context processing: documents are compressed into image form, and only the relevant pages get expanded when needed. Model weights are available on Hugging Face.
More from Research
- ScienceBuddy Now Free to Sign Up With a Regular Email, No Invite Code Needed — lxfater · 2026-09-24
- Visualizing a modular addition transformer: 2k vs 20k training steps side by side — Sauers_ · 2026-09-24
- Anthropic's Claude-led gene editing discovery disputed for ignoring prior work — soumitrashukla9 · 2026-09-24
- Cohere Labs paper: data mixing lifts in-language reasoning above 93% across 60 languages — ShahabBakht · 2026-09-24
- AI discovers a previously unknown process in the human body — rand_longevity · 2026-09-24
- Collapsing redundant layers: a unified framework for faster ViT inference without accuracy loss — burkov · 2026-09-24