Search Results for "visual code"

DeepSeek-OCR-2 is the second-generation optical character recognition system developed to improve document understanding by introducing a “visual causal flow” mechanism, enabling the encoder to reorder visual tokens in a way that better reflects semantic structure rather than strict raster scan order. It is designed to handle complex layouts and noisy documents by giving the model causal reasoning capabilities that mimic human visual scanning behavior, enhancing OCR performance on documents with rich spatial structure. ...

...The project supports single-image parsing as well as multi-page and PDF-style parsing by converting pages into images. It provides inference paths for Hugging Face Transformers, vLLM, and SGLang, which gives users several deployment options. The repository also includes example code for batch inference over image folders or PDF inputs. Overall, it is useful for researchers and developers who need advanced OCR, long-document parsing, and model-based extraction from complex visual documents.

...It achieves state-of-the-art performance on document parsing benchmarks while maintaining a relatively compact model size, demonstrating efficiency without sacrificing accuracy. Beyond standard OCR tasks, it extends its capabilities to parse complex visual elements such as charts, diagrams, and web interfaces, converting them into structured outputs like SVG code.

HunyuanOCR is an open-source, end-to-end OCR (optical character recognition) Vision-Language Model (VLM) developed by Tencent‑Hunyuan. It’s designed to unify the entire OCR pipeline, detection, recognition, layout parsing, information extraction, translation, and even subtitle or structured output generation, into a single model inference instead of a cascade of separate tools. Despite being fairly lightweight (about 1 billion parameters), it delivers state-of-the-art performance across a...