AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Models

Wenwen Yu, Zhibo Yang, Jianqiang Wan, Sibo Song, Jun Tang, Wenqing Cheng, Yuliang Liu, Xiang Bai

TPAMI 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Instruction-tuned multimodal assistants · 38 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add spatial-window prompting in pre-training (ablation)OmniParser V2 · Total-TextE2E None F1: 82.5 -> 83.8Improved
add prefix-window prompting in pre-training (ablation)OmniParser V2 · Total-TextE2E None F1: 82.5 -> 83.2Improved
add both spatial- and prefix-window prompting (ablation)OmniParser V2 · Total-TextE2E None F1: 82.5 -> 84.3Improved
replace naive shared decoder with token-router decoder (ablation)OmniParser V2 · Total-Text / ICDAR 2015text spotting average: +1.72% over naive shared decoderImproved
use token-router decoder instead of OmniParser's non-shared decoder (ablation)OmniParser V2 · Total-Text / ICDAR 2015FPS and params: 2.6 -> 8.2 FPS, 144 -> 110 params (M)Improved
increase C-decoder length from 200 to 300 and S-decoder length from 1,500 to 2,000 (ablation)OmniParser V2 · PubTabNetTEDS: 88.9 -> 89.0No clear effect
shorten S-decoder length from 1,500 to 1,124 (ablation)OmniParser V2 · PubTabNetTEDS: 88.9 -> 88.2Hurt
add layout analysis SPOT to native text spotting SPOT (ablation)OmniParser V2 · SignaTR6Kmean F1: 69.8 -> 82.1Improved
add layout analysis SPOT (handwritten text) (ablation)OmniParser V2 · SignaTR6KHT F1: 61.5 -> 79.3Improved
add SPOT prompting to Qwen2.5-VL-3BQwen2.5-VL-3B · HallusionBenchaccuracy: 63.8 -> 68.5Improved
add SPOT prompting to InternVL2.5-2BInternVL2.5-2B · CORDF1: 74.5 -> 83.7Improved
add SPOT prompting to InternVL2.5-2BInternVL2.5-2B · SROIEF1: 71.9 -> 77.8Improved

Later papers that compared with this method

1 later accepted paper reports OmniParser V2 as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy