AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

A Brain-Inspired Saliency Prediction Framework for Human-AI Cognitive Consistency in AIGC Content via Multi-Region Liquid Neurons

Shibo Wang, Yan Zhao, Shigang Wang, Jian Wei, Shuo Li

AAAI 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Human-like visual cognition in VLMs · 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 V1 and V2 liquid neuron modules (ablation)saliency student model · AIGC-EYENSS: 2.01 -> 2.26Improved
add V4 module (ablation)saliency student model · AIGC-EYENSS: 2.26 -> 2.38Improved
add MT module (ablation)saliency student model · AIGC-EYENSS: 2.38 -> 2.47Improved
add LIP module (ablation)saliency student model · AIGC-EYENSS: 2.47 -> 2.54Improved
add FEF module (ablation)saliency student model · AIGC-EYEHAMCI: 0.31 -> 0.29Improved
add real-gaze teacher distillation (ablation)saliency student model · AIGC-EYENSS: 2.43 -> 2.53Improved
add AIGC cross-attention teacher distillation (ablation)saliency student model · AIGC-EYENSS: 2.43 -> 2.49Improved
use both teachers (DT-Fuse) instead of one (ablation)saliency student model · AIGC-EYEHAMCI: 0.32 -> 0.29Improved

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