cd/entity/OmniDocBench· home entities OmniDocBench
grep -l @omnidocbench /news/*.json | wc -l → 4

OmniDocBench

mentions 4 type Organization feed RSS

// recent coverage 4 mentions

03:11
2026-06-24
byteiota.com
large-language-models

Baidu Unlimited-OCR: One-Shot PDF Parsing Is Here

Baidu released Unlimited-OCR, a new model that uses Reference Sliding Window Attention to parse up to 40 PDF pages in a single inference pass, eliminating the linear memory growth of traditional LLM-b…

// co-occurs with top 8 entities
// topics top 6 topics