AI Paper Atlas

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

Acknowledging Focus Ambiguity in Visual Questions

Chongyan Chen, Yu-Yun Tseng, Zhuoheng Li, Anush Venkatesh, Danna Gurari

ICCV 2025 · Vision-language and multimodal › Visual question answering · approach: Universal VQA models · 7 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 zero-shot chain-of-thought instruction (ablation)Molmo-7B · VQ-FocusAmbiguity recognitionaccuracy: 38.5 -> 56.9Improved
add enhanced chain-of-thought (structured steps) (ablation)Qwen2.5-VL-7B · VQ-FocusAmbiguity recognitionaccuracy: 57.2 -> 65.5Improved
add chain-of-thought prompting (ablation)InternVL2-76B · VQ-FocusAmbiguity recognitionaccuracy: 55.0 -> 56.7No clear effect
add chain-of-thought instruction (ablation)GPT-4o · VQ-FocusAmbiguity recognitionaccuracy: 67.7 -> 69.6Improved
add two few-shot examples (text-described) to zero-shot prompt (ablation)GPT-4o · VQ-FocusAmbiguity recognitionaccuracy: 67.7 -> 60.0Hurt
add two few-shot examples to zero-shot prompt (ablation)Molmo-7B · VQ-FocusAmbiguity recognitionaccuracy: 38.5 -> 41.8Improved
add ECoT step-by-step explanations to few-shot prompt (ablation)Qwen2.5-VL-7B · VQ-FocusAmbiguity recognitionaccuracy: 53.6 -> 59.0Improved
remove the image (question-only input) (ablation)GPT-4o · VQ-FocusAmbiguity recognitionaccuracy: 67.7 -> 44.2Hurt
replace image with self-generated caption at inference (few-shot) (ablation)GPT-4o · VQ-FocusAmbiguity recognitionaccuracy: +1.3% for FS; -2.1% for FS-ECoTNo clear effect
scale Qwen2.5-VL from 3B to 7B (ablation)Qwen2.5-VL · VQ-FocusAmbiguity recognitionaccuracy: 45.0 -> 65.5Improved
fine-tune on VQ-FocusAmbiguity (ablation)Qwen2.5-VL-7B · VQ-FocusAmbiguity recognitionaccuracy: +1.6 percentage points to 58.8%Improved
add enhanced CoT to zero-shot prompt (ablation)GLaMM · VQ-FocusAmbiguity localizationmAP: 13.01 -> 10.21Hurt

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