Group 1 - DeepSeek has launched the new DeepSeek-OCR2 model, which utilizes the innovative DeepEncoderV2 method to dynamically rearrange image components based on their meaning, rather than scanning mechanically from left to right [1] - The new model achieved a performance of 91.09%, an improvement of 3.73% over its predecessor, while reducing the maximum visual token usage from 1156 to 1120 [1] - The release of DeepSeek-OCR2 is significant as it may disrupt traditional document processing methods and pave the way for native multimodal reasoning [1] Group 2 - Haitong International states that DeepSeek-OCR represents a new generation of "compressed storage" by mapping text to visual representations and compressing it at high rates, achieving about 97% text restoration accuracy at less than 10x compression [2] - At a 20x compression rate, the model maintains approximately 60% accuracy, suitable for scenarios with higher tolerance for errors [2] - Huachuang Securities highlights DeepSeek-OCR's capability to process 33 million pages of data daily on 20 A100 nodes and its strong support for minor languages, indicating a significant advantage for global business deployment [2] Group 3 - Jin Modern has collaborated with Baidu on the development of large model applications and complementary OCR recognition capabilities [3] - Hanwang Technology has provided clients with various platforms, including a low-code development platform and an OCR platform [3]

Group 1 - Alibaba officially launched the Qwen3-Max-Thinking model, which has over 1 trillion parameters and a pre-training data volume of 36 trillion tokens, making it the largest and most capable model from Alibaba to date [1] - The Qwen3-Max-Thinking model achieved significant performance improvements, setting new global records in multiple key performance benchmarks, and features a new testing expansion mechanism that enhances inference performance while being more economical [1] - Developers can experience the Qwen3-Max-Thinking model for free on QwenChat, while enterprises can access the new model's API services through Alibaba Cloud [1] Group 2 - The DeepSeek team released the DeepSeek-OCR 2 model, which has gained attention for its high compression ratio and recognition accuracy, significantly improving long text processing efficiency and precision [2] - The DeepSeek-OCR 2 model utilizes the innovative DeepEncoder V2 method, allowing AI to dynamically rearrange image components based on their meaning, aligning more closely with human visual encoding logic [2] - Experts note that DeepSeek represents a breakthrough in multimodal capabilities, while Qwen enhances AI agent capabilities, highlighting two distinct approaches in the development of leading domestic large models [2] Group 3 - The focus on AI agents like Qwen is expected to be a key area of interest by 2026, as the current high computational demands may overwhelm AI model companies without practical application scenarios [3] - Data from the Hugging Face community indicates that by August 2025, the cumulative download volume of open-source models in China surpassed that of the United States [3] - The market for enterprise-level large model AI application solutions in China is projected to reach 239.4 billion yuan by 2029, with a compound annual growth rate of 44.0% from 2024 to 2029 [3]

Core Insights - The article highlights significant advancements in AI technology with the release of new models and chips by various companies, indicating a competitive landscape in the AI sector. Group 1: AI Model Releases - DeepSeek has launched the DeepSeek-OCR 2 model, enhancing optical character recognition capabilities [1] - Alibaba has officially released its flagship reasoning model, Qwen3-Max-Thinking, marking a significant step in AI development [1] - Kimi announced the release and open-sourcing of the Kimi K2.5 model, contributing to the open-source AI community [1] - MiniMax introduced the MiniMax M2.1 × Clawdbot, aimed at creating an open-source AI assistant to build superintelligent workflows [1] Group 2: AI Hardware Developments - Microsoft has unveiled the next-generation AI chip, Maia 200, which is expected to improve AI processing capabilities [1] - NVIDIA has released the AI "Earth-2" system, designed to enhance the accuracy of weather forecasting [1]

Core Insights - The article reports that Nine Dragons Paper's Chongqing base has increased the price of corrugated paper by 50 yuan per ton starting January 26, indicating a potential increase in market demand or supply constraints [2][3]. Group 1: Price Adjustment - Nine Dragons Paper has raised the price of corrugated paper by 50 yuan per ton, effective January 26 [2][3]. - This price increase suggests a direct positive impact on spot prices due to increased market demand or supply tightness [3]. Group 2: Market Implications - The price adjustment may be driven by rising raw material costs or a recovery in downstream demand, leading to expectations of short-term support and slight increases in spot prices [3]. - The pricing mechanism is based on the PriceSeek model, which utilizes big data to generate transaction guidance prices, known as the PriceSeek price [3]. Group 3: Pricing Formula - The pricing formula for determining transaction settlement prices includes a base price adjusted by a coefficient (K) and a premium or discount (C) [3][4]. - K accounts for factors such as account period costs, while C includes logistics costs, brand price differences, and regional price differences [4].

Core Insights - DeepSeek team released the paper "DeepSeek-OCR 2: Visual Causal Flow" and open-sourced the DeepSeek-OCR 2 model, which features an innovative DeepEncoder V2 structure that dynamically adjusts the processing order of visual information based on image semantics [1][2] - The new model aims to align machine processing more closely with human visual reading logic, addressing limitations in traditional visual language models that process images in a fixed grid order [1] Model Performance - DeepSeek-OCR 2 achieved an overall score of 91.09% on the OmniDocBench v1.5 benchmark, representing a 3.73% improvement over its predecessor [2] - The model demonstrated enhanced accuracy in reading order, with the edit distance decreasing from 0.085 to 0.057, indicating a better understanding of document content structure [2]

每经编辑｜程鹏 1月27日，DeepSeek团队发布全新DeepSeek-OCR 2模型并开源，采用创新的DeepEncoder V2方法，让AI能够根据图像的含义动态重排图像的各个部分，而 不再只是机械地从左到右扫描。这种方式更接近人类的视觉编码逻辑。最终，该模型在处理布局复杂的图片时，表现优于传统的视觉-语言模型，实现了 更智能、更具因果推理能力的视觉理解。 编辑|程鹏 杜波 校对|许绍航 封面图片来源：视觉中国（资料图） 每日经济新闻综合自每经AI快讯 ...

Core Viewpoint - The DeepSeek team has released a paper titled "DeepSeek-OCR2: Visual Causal Flow" and has open-sourced the DeepSeek-OCR2 model, which utilizes an innovative DeepEncoder V2 method to enable AI to dynamically rearrange parts of an image based on its meaning, aligning more closely with human visual encoding logic [1]. Group 1 - The DeepSeek-OCR2 model represents a significant advancement in AI's ability to interpret and manipulate visual information [1]. - The innovative DeepEncoder V2 method is a key feature that enhances the model's performance in visual tasks [1]. - The open-sourcing of the model allows for broader access and potential collaboration within the AI research community [1].

Core Insights - DeepSeek has launched its new model, DeepSeek-OCR 2, which utilizes the innovative DeepEncoder V2 method to dynamically rearrange image components based on their meaning, enhancing visual encoding logic similar to human perception [1] - The release of DeepSeek-OCR 2 comes approximately four months after the first version, indicating a rapid development cycle [1] - DeepSeek's approach contrasts traditional OCR by converting text information into visual images for efficient understanding, addressing challenges in processing long texts [1] Model Developments - The core component of DeepSeek's technology, the visual encoder, is believed to simulate the human brain's forgetting mechanism, providing a clear technical path for integrating optical and quantum computing in large language models (LLMs) [2] - Following the release of the V3 model in late 2024, DeepSeek is expected to unveil its next flagship model, DeepSeek V4, in February 2025, although the company has not confirmed this [2] - The DeepSeek-V3.1 upgrade features a hybrid reasoning architecture that supports both thinking and non-thinking modes, improving response efficiency and agent capabilities through post-training optimization [2] Performance Metrics - DeepSeek-V3.2 and its enhanced version, DeepSeek-V3.2-Speciale, reportedly achieve reasoning capabilities comparable to GPT-5, significantly reducing output length and computational costs compared to competitors [3] - DeepSeek-R1, launched on January 20, 2025, claims performance on par with OpenAI's models while maintaining a remarkably low inference cost of $294,000, with total training costs still below those of major international competitors [3] Market Impact - On January 27, 2025, DeepSeek topped the free app download charts in both the U.S. and China, surpassing ChatGPT, which has led to a significant revaluation of Chinese assets in the stock market [4] - Following DeepSeek's rise, indices related to computing power and cloud computing in the A-share market surged over 40%, with several stocks experiencing substantial gains [4] - The potential for DeepSeek to replicate its previous success in the market remains a point of interest for investors and analysts [4]

Core Insights - DeepSeek has launched the new DeepSeek-OCR2 model, which utilizes the innovative DeepEncoder V2 method to dynamically rearrange image components based on their meaning, enhancing visual understanding beyond traditional left-to-right scanning methods [1][2] - The model significantly outperforms traditional visual-language models (VLM) in processing complex layouts, achieving a score of 91.09% on the OmniDocBench v1.5 benchmark, which is a 3.73% improvement over its predecessor [1] Group 1 - The DeepSeek-OCR2 model maintains high accuracy while controlling computational costs, with visual token counts limited between 256 and 1120, aligning with Google’s Gemini-3Pro [2] - In practical applications, the model shows a reduction in repetition rates of 2.08% for online user logs and 0.81% for PDF pre-training data, indicating high practical maturity [2] Group 2 - The release of DeepSeek-OCR2 represents not only an upgrade in OCR performance but also significant architectural exploration, validating the potential of using language model architectures as visual encoders [2] - The DeepEncoder V2 architecture inherits advancements from the LLM community, such as mixture of experts (MoE) architecture and efficient attention mechanisms [2]

Group 1 - DeepSeek team released a paper titled "DeepSeek-OCR 2: Visual Causal Flow" and open-sourced the DeepSeek-OCR 2 model, which utilizes the innovative DeepEncoder V2 method to enable AI to dynamically rearrange parts of an image based on its meaning, aligning more closely with human visual encoding logic [1] Group 2 - DeepSeek concept stocks experienced a short-term surge, with YunSai ZhiLian hitting the daily limit, Hongjing Technology reaching a 20% increase, and KaiPu Cloud, Shiji Hengtong, and Parallel Technology also seeing short-term gains [3]