DeepSeek-OCR: Contexts Optical Compression — mentioned by michaelt

Fri, 03 Jul 2026 21:58:36 GMT

Not necessarily. See the paper See "DeepSeek-OCR: Contexts Optical Compression" [1] One option, when an image is fed into an LLM, is to divide it into tiles, then those tiles pass through a 'vision encoder' neural network to make 'vision tokens' which are then input into the LLM much like text tokens are. Obviously you train the vision encoder and LLM to understand one another. This is known as an 'end-to-end OCR model'. And it turns out, once you've trained a model to do this, you can vary the number of 'vision tokens' used to represent a given text document by scaling an image of a document…

Paper and discussion history. A mention is not an endorsement.

DeepSeek-OCR: Contexts Optical Compression — HN submission

Wed, 29 Oct 2025 18:33:29 GMT

DeepSeek-OCR: Contexts Optical Compression

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

DeepSeek-OCR: Contexts Optical Compression · HackerPapers discussions

DeepSeek-OCR: Contexts Optical Compression — mentioned by michaelt

DeepSeek-OCR: Contexts Optical Compression — HN submission