LensVLM: Compressing long context as images, expanding only relevant pages
長文脈を画像として圧縮し、関連するページのみを拡張するLensVLMという技術について言及されている
Related articles(LLM / Model Trends)
See moreHacker News
Flux 3 Image Klein: open weights, 5.6B parameters
Flux 3 Image Klein is an open-weights image generation model with 5.6B parameters that offers frontier image quality, customization, and speed for text-to-image and editing tasks.
Hacker News
You could have invented transformers from memory
An article exploring the possibility of reinventing the Transformer architecture from memory alone.
Hacker News
Claude reveals ECDSA curve origins
Claude explained the decades-old mystery of the origins of one of the most popular cryptographic standards, the ECDSA curve.
Hacker News
Llama.cpp on a jailbroken PS5: run any GGUF model natively on the console
A project allows running llama.cpp on a jailbroken PS5 to natively execute any GGUF model on the console, starting with Qwen 3.8.
Hacker News
Designing more efficient quantum circuits with Claude
Claude worked largely on its own to design quantum circuits that improve on the best published versions, achieving an order of magnitude or more improvement in some cases.