{"id":9150,"date":"2025-10-21T03:19:50","date_gmt":"2025-10-21T03:19:50","guid":{"rendered":"https:\/\/jobuzo.com\/en\/deepseek-unveils-ai-model-that-uses-visual-perception-to-compress-text-input\/"},"modified":"2025-10-21T03:19:50","modified_gmt":"2025-10-21T03:19:50","slug":"deepseek-unveils-ai-model-that-uses-visual-perception-to-compress-text-input","status":"publish","type":"post","link":"https:\/\/jobuzo.com\/en\/deepseek-unveils-ai-model-that-uses-visual-perception-to-compress-text-input\/","title":{"rendered":"DeepSeek unveils AI model that uses visual perception to compress text input"},"content":{"rendered":"
\n
DeepSeek<\/span> on Monday released a new multimodal artificial intelligence<\/span> model that can handle large and complex documents with significantly fewer tokens – the smallest unit of text that a model processes – by using visual perception as a compression medium for information.<\/div>\n
\n
\n

Advertisement<\/p>\n<\/div>\n<\/div>\n

The open-source DeepSeek-OCR (optical character recognition) model, available via online developer platforms Hugging Face<\/span> and GitHub<\/span>, was the result of an “investigation into the role of vision encoders” to compress text for large language models (LLMs), the Hangzhou<\/span>-based AI start-up said in a blog post.<\/div>\n

By using that approach, LLMs would be able to process a massive amount of text without incurring a proportional increase in computing cost.<\/p>\n

“Through DeepSeek-OCR, we demonstrated that vision-text compression can achieve significant token reduction – seven to 20 times – for different historical context stages, offering a promising direction” to address long-context challenges in LLMs, the company said.<\/p>\n

That showed DeepSeek’s steadfast efforts to raise the efficiency of AI models, while driving down the costs of building and using them – a principle that the company followed in the development of its breakthrough open-source models V3<\/span> and R1<\/span> that were released in December and February, respectively.<\/div>\n
\n
\n
\n
\n
\n
\n

[LIVE] China Future Tech webinar | How is DeepSeek shaping the race for AI supremacy?<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n

<\/path><\/svg>\n

[LIVE] China Future Tech webinar | How is DeepSeek shaping the race for AI supremacy?<\/p>\n<\/div>\n<\/div>\n<\/div>\n

According to the company’s blog post, DeepSeek-OCR consisted of two main components: DeepEncoder and DeepSeek3B-MoE-A570M as the decoder.<\/p>\n

\n
\n
News :<\/span><div>12 weeks' jail for school IT support technician who took upskirt videos of teachers<\/div><\/span><\/a><\/div>

Advertisement<\/p>\n<\/div>\n<\/div>\n<\/div>\n

DeepSeek unveils AI model that uses visual perception to compress text input<\/sub><\/p>\n","protected":false},"excerpt":{"rendered":"

DeepSeek on Monday released a new multimodal artificial intelligence model that can handle large and complex documents with significantly fewer tokens – the smallest unit of text that a model processes – by using visual perception as a compression medium for information. Advertisement The open-source DeepSeek-OCR (optical character recognition) model, available via online developer platforms…<\/p>\n

Read More “DeepSeek unveils AI model that uses visual perception to compress text input”<\/span> »<\/a><\/p>\n","protected":false},"author":1,"featured_media":9151,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-9150","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news"],"_links":{"self":[{"href":"https:\/\/jobuzo.com\/en\/wp-json\/wp\/v2\/posts\/9150","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/jobuzo.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/jobuzo.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/jobuzo.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/jobuzo.com\/en\/wp-json\/wp\/v2\/comments?post=9150"}],"version-history":[{"count":0,"href":"https:\/\/jobuzo.com\/en\/wp-json\/wp\/v2\/posts\/9150\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/jobuzo.com\/en\/wp-json\/wp\/v2\/media\/9151"}],"wp:attachment":[{"href":"https:\/\/jobuzo.com\/en\/wp-json\/wp\/v2\/media?parent=9150"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/jobuzo.com\/en\/wp-json\/wp\/v2\/categories?post=9150"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/jobuzo.com\/en\/wp-json\/wp\/v2\/tags?post=9150"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}