• transformer — The neural network architecture behind modern AI models, built on attention — letting every word directly consider every other word in parallel.
• embedding — A list of numbers representing a piece of text's meaning, so that similar meanings end up numerically close and can be searched.
• quantization — Shrinking a model by storing its numbers less precisely — like rounding — so it runs faster and fits on smaller hardware, at a small quality cost.

A document retrieval encoder that drops the pretrained vision tower and still lands on the ViDoRe v3 frontier, with pooling and quantization that shrink late-interaction indexes from about 1.5 MB to 6 kB per page.

• postOne transformer for text and images, no screen parsing pipelineVoyage AI by MongoDB
• articleIntroducing Gemma 4 12B: a unified, encoder-free multimodal modeldeepmind.google
• postTwo 350M retrieval models: one dense, one late interactionLiquid AI

Checking sign-in…

Loading comments…