Baidu open-sources Unlimited OCR 2: near-constant latency on documents of any length
Baidu_Inc · x · 2026-10-27
Baidu released Unlimited OCR 2, an open-source model for long-document parsing. To curb the attention compute blowup as documents grow, a new SR-SWA mechanism condenses text-visual attention interactions into a fixed-size set of working references.
Results: parses documents of virtually any length within a finite context window; near-constant per-step decoding latency and memory as documents grow; state-of-the-art on MPDocBench and MarathonDocBench, covering documents from dozens to hundreds of pages.
Related event: Baidu Open-Sources Unlimited OCR 2 for Arbitrarily Long Documents(3 posts)→
More from Models
- Models spontaneously run internal expert debates when solving hard problems, nobody designed it — profjamesevans · 2026-10-27
- Speculation: xAI's announcement is likely Index, not Fable 5.5 — ChrisGPT · 2026-10-27
- AMD and vLLM team release open 27B multimodal decision model d3-ultra, #2 on Jev Decision Index — vllm_project · 2026-10-27
- Reasoning is signed: building a universal LLM gateway hits encrypted CoT walls — respan-81 · 2026-10-27
- Gemini 4 Argon reportedly beats GPT-6 Astra on a new CS research benchmark — Saboo_Shubham_ · 2026-10-27
- LlamaIndex releases OCRia-1, a 4B document parsing VLM topping ParseBench at 87.4 — llama_index · 2026-10-27