AI Paper Atlas

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

VisualScore: Learning Holistic Visual Quality Scores via Multi-Task Reasoning

Yiting Lu, Fengbin Guan, Yixin Gao, Yan Zhong, Xinge Peng, Jiakang Yuan, Yihao Liu, Bo Zhang, Xin Li, Zhibo Chen, Weisi Lin

ICML 2026 · Image generation › Text-to-image diffusion · approach: Fairness and bias in generative models

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 cold-start rejective sampling tuning before GRPO (ablation)GRPO · EvalMusePLCC: 0.640 -> 0.689Improved
replace binary reward with Gaussian reward (ablation)VisualScore · EvalMusePLCC: 0.689 -> 0.764Improved
replace binary reward with Gaussian reward (ablation)VisualScore · AVAPLCC: 0.737 -> 0.763Improved
add entropy gating in stage 1 training (ablation)VisualScore · KADIDPLCC: 0.672 -> 0.645Hurt
add entropy gating in stage 1 training (ablation)VisualScore · EvalMuse-50kPLCC: 0.764 -> 0.742Hurt
add entropy gating in stage 2 training (ablation)VisualScore · KADIDPLCC: 0.671 -> 0.735Improved
add STD filtering on top of entropy gating in stage 2 (ablation)VisualScore · KADIDPLCC: 0.735 -> 0.745Improved
add STD filtering on top of entropy gating in stage 2 (ablation)VisualScore · TAD66kPLCC: 0.450 -> 0.461Improved
add entropy gating and STD filtering to multi-task training (ablation)VisualScore · EvalMusePLCC: 0.640 -> 0.764Improved
train jointly on three tasks instead of single task (with method) (ablation)VisualScore · EvalMusePLCC: 0.731 -> 0.764Improved
set Gaussian reward sigma to 1 instead of 0.8 (ablation)GRPO with Gaussian reward · EvalMuse-50kPLCC: 0.764 -> 0.724Hurt
use sigma 0.6 instead of 0.8 (ablation)GRPO with Gaussian reward · EvalMuse-50kPLCC: 0.764 -> 0.734Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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