AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

From Illusion to Intention: Visual Rationale Learning for Reliable Evidence Acquisition

Changpeng Wang, Liu Junhan, Xi Chen, Haozhe Wang, Donglian Qi, Yunfeng Yan

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Reinforcement learning for visual reasoning · 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 rationale fidelity reward instead of answer-only reward (ablation)ViRL · V*answer accuracy: 87.6 -> 90.1Improved
add rationale fidelity reward instead of answer + tool-call bonus (ablation)ViRL · V*answer accuracy: 85.3 -> 90.1Improved
add fine-grained credit assignment (ablation)ViRL · V*answer accuracy: 88.9 -> 90.1Improved
add fine-grained credit assignment (ablation)ViRL · V*rationale accuracy: 78.2 -> 87.4Improved
use signed plus refinement reward instead of raw IoU reward (ablation)ViRL · V*answer accuracy: 84.3 -> 89.8Improved
use signed plus refinement reward instead of raw IoU reward (ablation)ViRL · V*rationale accuracy: 50.8 -> 83.7Improved
raise soft threshold h0 from 0.2 to 0.3 (ablation)ViRL · V*rationale accuracy: 75.5 -> 77.3Improved
raise soft threshold h0 to 0.4 or higher (ablation)ViRL · V*answer accuracy: 88.4 -> 86.6Hurt
replace Visual-CoT data with evidence-seeking QA (ablation)ViRL · VLindaccuracy: 47.3 -> 55.3Improved
add consistency verification to data pipeline (ablation)ViRL · V*rationale accuracy: 55.3 -> 87.6Improved
add zoom-in dependency filtering (ablation)ViRL · MMStar (4 core categories)accuracy: 66.8 -> 67.1Improved
apply ViRL to Qwen2.5-VL-7BQwen2.5-VL-7B · VLindaccuracy: +8.7Improved

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