AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Do Vision Language Models Recognize Visual Ambiguity?

Huy Ta, Trang Nguyen, Townim Chowdhury, ANKIT YADAV, Minh-Son To, Zhibin Liao, Johan Verjans, Hieu Phan

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Bias-aware multi-image robustness · 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 image-only perturbation to Semantic Entropy (ablation)SE · AOKVQA (Qwen2.5-VL)AUC: 0.702 -> 0.761Improved
Add image-only perturbation to SNNE (ablation)SNNE · AOKVQA (Gemma3)AUC: 0.651 -> 0.746Improved
Use prototype semantic aggregation instead of SE entropy, with visual perturbation (ablation)VSE · AOKVQA (Qwen2.5-VL)AUC: 0.761 -> 0.783Improved
Use prototype aggregation without visual perturbation (ablation)ProtoSem · AOKVQA (Qwen2.5-VL)AUC: 0.711 -> 0.783Improved
Perturb image only rather than text and image (VL-Uncertainty)VSE · AOKVQA (Qwen2.5-VL)AUC: 0.756 -> 0.783Improved
Use VSE instead of SE on adversarial VILPVSE · VILP (Qwen2.5-VL)AUC: 0.535 -> 0.650Improved
Use VSE instead of best baseline on VLM-are-biasedVSE · VLM-are-biased (Qwen2.5-VL)AUC: 0.783 -> 0.826Improved
Use VSE instead of SE on MMVetVSE · MMVet (Qwen2.5-VL)AUC: 0.716 -> 0.781Improved
Use VSE instead of SE on OKVQAVSE · OKVQA (Qwen2.5-VL)AUC: 0.758 -> 0.767Improved
Text paraphrasing vs image perturbation as source of output variabilityJoint perturbation · VILP (Qwen2.5-VL)cluster purity: PT 54.3 vs PI 38.8Mixed
Stochastic decoding alone on visually confident samplesSemantic Entropy · VILP (Qwen2.5-VL)semantic entropyHurt
Use VSE vs strongest baseline on Gemma3 VILPVSE · VILP (Gemma3)AUC: 0.660 -> 0.665No clear effect

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