AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Do Not Leave a Gap: Hallucination-Free Object Concealment in Vision-Language Models

Amira Guesmi, Muhammad Shafique

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Decoding-time hallucination mitigation · 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
replace attention suppression (VIP) with background-consistent re-encodingVIP · ImageNet, Instruct-BLIPgrounded hallucination rate: 0.43 -> 0.19Improved
replace VIP with BCRVIP · ImageNet, Instruct-BLIPglobal preservation: 0.57 -> 0.81Improved
replace VIP with BCRVIP · ImageNet, LLaVAconcealment success: 0.98 -> 0.98No clear effect
replace VIP with BCRVIP · COCO, Instruct-BLIPconcealment success: 0.80 -> 0.89Improved
replace VIP with BCRVIP · ImageNet, Instruct-BLIPconcealment success: 0.93 -> 0.92No clear effect
add statistical alignment loss (ablation)BCR · ImageNet, Instruct-BLIPhallucination rate: 0.28 -> 0.08Improved
add dictionary projection loss (ablation)BCR · ImageNet, Instruct-BLIPhallucination rate: 0.21 -> 0.08Improved
add background preservation loss (ablation)BCR · ImageNet, Instruct-BLIPglobal preservation: 0.69 -> 0.83Improved
add total variation loss (ablation)BCR · ImageNet, Instruct-BLIPhallucination rate: 0.09 -> 0.08Improved
add background preservation loss (ablation)BCR · ImageNet, Instruct-BLIPhallucination rate: 0.17 -> 0.08Improved
apply losses to late layers instead of early layers (ablation)BCR · Instruct-BLIPconcealment success: 0.22 -> 0.91Improved
apply losses to late layers instead of middle layers (ablation)BCR · Instruct-BLIPconcealment success: 0.41 -> 0.91Improved

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