baidu

Baidu, flush with cash, offers only a 36% discount on its AI model service, sparking discussion among netizens.

vLLM Kunlun is a community-maintained hardware plugin that enables vLLM to run on Baidu Kunlun XPU, supporting 20+ LLMs, quantization, LoRA, and speculative decoding.

Baidu's open-source Unlimited OCR model proposes the Reference Sliding Window Attention (R-SWA) mechanism, achieving continuous parsing of dozens of pages with 3 billion parameters, gaining high attention on GitHub and HuggingFace.

Unlimited-OCR, a new open-source OCR model from a Chinese company, solves the memory growth issue common in AI OCR tools by keeping memory usage flat regardless of document length, enabling single-pass reading of dozens of pages at 32K context. It's MIT-licensed, 3B parameters, multilingual, and already popular on GitHub.

Baidu releases Unlimited-OCR, a 3B parameter open-source model that reads full 100-page PDFs in one go with a 32K context window, achieving 93% accuracy and running locally. It has 1.9 million Hugging Face downloads but little mainstream attention.

Baidu's open source project Unlimited-OCR tops four charts on HuggingFace and GitHub, with stars exceeding 10k in five days. The model uses a MoE architecture (3B total parameters, 570M activated parameters) and excels at continuous recognition of long documents. Inspired by how humans copy books, it also offers new ideas for long-term memory management in large models.

Baidu's Unlimited-OCR model, using Reference Sliding Window Attention, is now supported in vLLM, enabling efficient one-shot parsing of entire books with constant memory usage.

Baidu has released Unlimited-OCR, an optical character recognition service with no usage limits.

This post shows how to serve Baidu's Unlimited-OCR model as a temporary, OpenAI-compatible endpoint on Hugging Face Jobs, enabling multi-page document parsing with features like table-to-HTML and equation-to-LaTeX extraction.

Baidu releases Unlimited-OCR, an open-source model for one-shot long-horizon document parsing, building upon Deepseek-OCR with support for single images, multi-page documents, and PDFs.

Baidu open-sources Unlimited OCR, a 3B parameter model (500M activated) that reads long documents in a single pass using Reference Sliding Window Attention (R-SWA), achieving state-of-the-art results on OmniDocBench.

Baidu has released Unlimited-OCR, which processes entire documents in a single pass without chunking, overcoming a major limitation of current OCR technology.

Baidu has open-sourced the visual language model Unlimited-OCR, upgraded from DeepSeek-OCR, supporting one-shot parsing of extremely long documents, offering two inference modes: gundam (dense text in a single image) and base (multi-page/PDF).

Baidu has open-sourced the Unlimited OCR model, which uses the R-SWA attention mechanism to process hundreds of pages in a single pass without page splitting, with a constant KV Cache. The model innovatively mimics the attention pattern of humans copying books by hand and shares technical lineage with DeepSeek OCR, sparking discussions about talent mobility.

Baidu has open-sourced the Unlimited OCR model, which uses a Reference Sliding Window Attention (R-SWA) mechanism to parse documents up to 32K context in a single pass, eliminating the need for page-by-page inference.

A summary of the LatePost interview, reviewing Baidu US R&D's early AI布局, including investing in Cerebras, nearly investing in OpenAI and Anthropic, and the flow of talent from Baidu to these companies.

Unlimited OCR introduces Reference Sliding Window Attention to eliminate growing memory consumption in long-sequence OCR tasks, enabling efficient transcription of multiple pages in a single forward pass.

Baidu releases Unlimited-OCR, a new model for one-shot long-horizon document parsing, building on Deepseek-OCR. It supports single image and multi-page/PDF parsing via Hugging Face Transformers and SGLang.

The user praised a product launched by Baidu that effectively solves the pain point of dealing with numbers when translating papers, considering it a necessity.

Baidu Wenxin releases PP-OCRv6, offering three model tiers: Tiny, Small, and Medium, supporting over 50 languages. The Tiny version is only 1.5MB and can run locally in a browser, with the fastest single-image inference at 97ms, proving that small specialized models can outperform large models on OCR tasks.