AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Enhancing prompt-image alignment evaluations via cyclic mutual information maximization

Xingran Liao, Duanyu Feng, Mingliang Zhou, Sam Kwong, Weisi Lin

ECCV 2026 · Image generation › Text-to-image diffusion · approach: Personalized and region-controlled generation · 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 forward and backward MIM over the fusion baseline (ablation)CMIM-AIGIQA · AGIQA-3K alignmentSRCC: 0.7731 -> 0.8546Improved
add forward MIM (alignment) (ablation)CMIM-AIGIQA · AGIQA-3K alignmentSRCC: 0.8415 -> 0.8546Improved
add forward MIM (quality) (ablation)CMIM-AIGIQA · AGIQA-3K qualitySRCC: 0.8432 -> 0.8755Improved
add backward MIM (ablation)CMIM-AIGIQA · AIGCIQA2023 alignmentSRCC: 0.7655 -> 0.8263Improved
add textual entropy H(Y) (ablation)CMIM-AIGIQA · AGIQA-3K alignmentSRCC: 0.8502 -> 0.8546Improved
add textual entropy H(Y) (ablation)CMIM-AIGIQA · PKU-AIGIQA-4k alignmentSRCC: 0.8094 -> 0.8223Improved
use NCE loss instead of MSE in backward phase (ablation)CMIM-AIGIQA · AGIQA-3K alignmentSRCC: 0.8156 -> 0.8546Improved
use NCE loss instead of MSE in backward phase (ablation)CMIM-AIGIQA · AIGCIQA2023 alignmentSRCC: 0.7892 -> 0.8263Improved
add cross-attention (CSA) fusion (ablation)CMIM-AIGIQA · PKU-AIGIQA-4k alignmentSRCC: 0.7984 -> 0.8223Improved
use BLIP backbone instead of CLIP ViT-L/14 (alignment) (ablation)CMIM-AIGIQA · AGIQA-3K alignmentSRCC: 0.8214 -> 0.8546Improved
use BLIP backbone instead of CLIP ViT-L/14 (quality) (ablation)CMIM-AIGIQA · AGIQA-3K qualitySRCC: 0.8931 -> 0.8755Hurt
use CMIM-AIGIQA instead of MoE-AGIQA in cross-dataset transferCMIM-AIGIQA vs MoE-AGIQA · PKU-AIGIQA-4k to AIGCIQA2023SRCC: 0.5646 -> 0.6305Improved

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