@NielsRogge: The new Suyra OCR 2 model is top trending on http://paperswithcode.co Also can you spot the new "Conferences" tab?
Summary
The new Suyra OCR 2 model is trending on Papers with Code, and a new Conferences tab has been added to the site.
View Cached Full Text
Cached at: 06/01/26, 03:06 AM
The new Suyra OCR 2 model is top trending on https://t.co/tOqTY2ZA6h
Also can you spot the new “Conferences” tab? 👀 https://t.co/n6G7EqCmCT
Similar Articles
@vista8: Baidu's technical strength is still impressive. Recently, this Unlimited OCR has even caught the attention of Yann LeCun! Unlimited OCR proposes Reference Sliding Window Attention (R-SWA)...
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.
@VikParuchuri: Marker is powered by the new Surya OCR 2 model (https://github.com/datalab-to/surya…), which is the highest-scoring mod…
Datalab announces Surya OCR 2, a 650M parameter OCR model that achieves top accuracy under 1B parameters on olmOCR benchmarks, with high speed and multilingual support.
@VikParuchuri: Get marker here - https://github.com/datalab-to/marker… . Quickstart: pip install marker-pdf, then marker /path/to/fold…
Marker is an open-source tool that converts PDFs, images, and other document formats to markdown, JSON, chunks, and HTML quickly and accurately, with optional LLM enhancement.
DocOCR-Eval: A Correction-Based Framework for OCR Tool Selection Without Ground Truth
DocOCR-Eval proposes an annotation-free framework that uses a correction and ranking strategy to evaluate and select OCR tools without ground truth labels, showing that aggregating multiple multimodal large language models improves alignment with human rankings.
@denziideng: Say goodbye to manual screenshot translation! overlay-translator: one-tap floating window real-time translation, boosting efficiency in games and manga. Stuck by language when playing Japanese games or reading manga? Want real-time understanding of dialogue and UI without rooting your phone? Manual screenshot translation is cumbersome and breaks immersion. Today I'm sharing a game-changer: overlay-t…
Overlay-translator is an open-source Android real-time screen translation tool that requires no root. It overlays Chinese translations onto the original screen via a floating window, supporting games, manga, visual novels, and more. It integrates multiple OCR and translation engines and works offline.