按年被提到
20252025 · 1 次2026
视觉、语音与图像生成›视觉语言与自监督表征·arXiv:2510.18234 · cs.CV

DeepSeek-OCR: Contexts Optical Compression

Haoran Wei, Yaofeng Sun, Yukun Li · 2025
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2025-10-29 · 最近 2026-07-03
2不同的人
2活跃月份
2讨论串
91被引(OpenAlex)
arXiv 摘要(候选层不写导读)

We present DeepSeek-OCR as an initial investigation into the feasibility of compressing long contexts via optical 2D mapping. DeepSeek-OCR consists of two components: DeepEncoder and DeepSeek3B-MoE-A570M as the decoder. Specifically, DeepEncoder serves as the core engine, designed to maintain low activations under high-resolution input while achieving high compression ratios to ensure an optimal and manageable number of vision tokens. Experiments show that when the number of text tokens is within 10 times that of vision tokens (i.e., a compression ratio < 10x), the model can achieve decoding (OCR) precision of 97%. Even at a compression ratio of 20x, the OCR accuracy still remains at about 60%. This shows considerable promise for research areas such as historical long-context compression and memory forgetting mechanisms in LLMs. Beyond this, DeepSeek-OCR also demonstrates high practical value. On OmniDocBench, it surpasses GOT-OCR2.0 (256 tokens/page) using only 100 vision tokens, and outperforms MinerU2.0 (6000+ tokens per page on average) while utilizing fewer than 800 vision tokens. In production, DeepSeek-OCR can generate training data for LLMs/VLMs at a scale of 200k+ pages per day (a single A100-40G). Codes and model weights are publicly accessible at http://github.com/deepseek-ai/DeepSeek-OCR.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论michaelt · 2026-07

“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…”

60% Fable cost cut by converting code to images and having the model OCR it原评论 ↗
被提交为 story · 1 次