AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

REAL: Resolving Knowledge Conflicts in Knowledge-Intensive Visual Question Answering via Reasoning-Pivot Alignment

Kai Ye, Xianwei Mao, Sheng Zhou, Zirui Shao, Ye Mo, Liangliang Liu, Haikuan Huang, Bin Li, Jiajun Bu

ICML 2026 · Vision-language and multimodal › Visual question answering · approach: Attention and prior-robust VQA · 0 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 RPGD contrastive decoding on top of RPA-SFT (ablation)REAL (Qwen3-VL-8B) · InfoSeek Allaccuracy: 38.7 -> 44.1Improved
add RPGD contrastive decoding on top of RPA-SFT (ablation)REAL (Qwen3-VL-8B) · E-VQA Allaccuracy: 38.1 -> 41.4Improved
add RPGD contrastive decoding on top of RPA-SFT (ablation)REAL (InternVL3.5-8B) · InfoSeek Allaccuracy: 36.2 -> 43.8Improved
add RPGD contrastive decoding on top of RPA-SFT (ablation)REAL (LLaVA-1.5-7B) · E-VQA Allaccuracy: 28.5 -> 30.9Improved
use accurate Stage 1 conflict signal instead of uniform signal (ablation)RPGD (Qwen3-VL-8B) · InfoSeek Allaccuracy: 39.0 -> 44.1Improved
use accurate Stage 1 conflict signal instead of random signal (ablation)RPGD (Qwen3-VL-8B) · E-VQA Allaccuracy: 39.3 -> 41.4Improved
add patch shuffle (ablation)RPGD (Qwen3-VL-8B) · E-VQA Allaccuracy: 39.2 -> 41.4Improved
add adaptive gating (ablation)RPGD (Qwen3-VL-8B) · E-VQA Allaccuracy: 39.5 -> 41.4Improved
add Gram-Schmidt orthogonalization (ablation)RPGD (Qwen3-VL-8B) · E-VQA Allaccuracy: 38.9 -> 41.4Improved
use patch shuffle instead of blank image as perturbation (ablation)RPGD (Qwen3-VL-8B) · InfoSeek Allaccuracy: 37.4 -> 44.1Improved
use patch shuffle instead of Gaussian blur (ablation)RPGD (Qwen3-VL-8B) · E-VQA Allaccuracy: 38.1 -> 41.4Improved
use RPGD instead of VCD decoding (ablation)RPA-SFT (LLaVA-1.5-7B) · E-VQA Allaccuracy: 26.0 -> 30.9Improved

Later papers that compared with this method

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

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