Generative text-to-image models are advancing at an unprecedented pace, continuously shifting the perceptual quality ceiling and rendering previously collected labels unreliable for newer generations. To address this, we present ELIQ, a Label-free Framework for Quality Assessment of Evolving AI-generated Images. Specifically, ELIQ focuses on visual quality and prompt-image alignment, automatically constructs positive and aspect-specific negative pairs to cover both conventional distortions and AIGC-specific distortion modes, enabling transferable supervision without human annotations. Building on these pairs, ELIQ adapts a pre-trained multimodal model into a quality-aware critic via instruction tuning and predicts two-dimensional quality using lightweight gated fusion and a Quality Query Transformer. Experiments across multiple benchmarks demonstrate that ELIQ consistently outperforms existing label-free methods, generalizes from AI-generated content (AIGC) to user-generated content (UGC) scenarios without modification, and paves the way for scalable and label-free quality assessment under continuously evolving generative models. The code will be released upon publication.

翻译：生成式文本到图像模型正以前所未有的速度发展，不断突破感知质量的上限，使得先前收集的标签对于新一代模型不再可靠。为解决此问题，我们提出了ELIQ，一种用于评估演化中AI生成图像质量的无标签框架。具体而言，ELIQ聚焦于视觉质量与提示-图像对齐性，自动构建正样本和面向特定方面的负样本对，以覆盖传统失真模式与AIGC特有的失真模式，从而在无需人工标注的情况下实现可迁移的监督。基于这些样本对，ELIQ通过指令微调将预训练的多模态模型适配为质量感知的评判器，并利用轻量级门控融合与Quality Query Transformer预测二维质量。在多个基准测试上的实验表明，ELIQ持续优于现有的无标签方法，无需修改即可从AI生成内容（AIGC）泛化至用户生成内容（UGC）场景，并为持续演化的生成模型下的可扩展、无标签质量评估开辟了道路。代码将在论文发表时公开。