# Decoupling Semantics from Distortions: Multi-Scale Two-Stream Vision-Language Alignment for AI-Generated Image Quality Assessment

arXiv: https://arxiv.org/abs/2606.16799 · HTML: https://mlsanity.com/paper/2606.16799/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Image editing and quality assessment, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 24 of its 31 references that are in the map.
- First posted on arXiv 15 Jun 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Image editing and quality assessment](https://mlsanity.com/mllm/image-editing-and-quality-assessment/)

## Builds on (most cited first, 24 of 24)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)
- [MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2204.08958/) (2022)
- [Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective](https://mlsanity.com/paper/2303.14968/) (2023)
- [TOPIQ: A Top-down Approach from Semantics to Distortions for Image Quality Assessment](https://mlsanity.com/paper/2308.03060/) (2023)
- [AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment](https://mlsanity.com/paper/2306.04717/) (2023)
- [AIGCIQA2023: A Large-scale Image Quality Assessment Database for AI Generated Images: from the Perspectives of Quality, Authenticity and Correspondence](https://mlsanity.com/paper/2307.00211/) (2023)
- [A Perceptual Quality Assessment Exploration for AIGC Images](https://mlsanity.com/paper/2303.12618/) (2023)
- [Norm-in-Norm Loss with Faster Convergence and Better Performance for Image Quality Assessment](https://mlsanity.com/paper/2008.03889/) (2020)
- [AIGIQA-20K: A Large Database for AI-Generated Image Quality Assessment](https://mlsanity.com/paper/2404.03407/) (2024)
- [Quality-Aware Image-Text Alignment for Opinion-Unaware Image Quality Assessment](https://mlsanity.com/paper/2403.11176/) (2024)
- [Large Multi-modality Model Assisted AI-Generated Image Quality Assessment](https://mlsanity.com/paper/2404.17762/) (2024)
- [CLIP-AGIQA: Boosting the Performance of AI-Generated Image Quality Assessment with CLIP](https://mlsanity.com/paper/2408.15098/) (2024)
- [Bringing Textual Prompt to AI-Generated Image Quality Assessment](https://mlsanity.com/paper/2403.18714/) (2024)
- [Adaptive Mixed-Scale Feature Fusion Network for Blind AI-Generated Image Quality Assessment](https://mlsanity.com/paper/2404.15163/) (2024)
- [SynPo: Boosting Training-Free Few-Shot Medical Segmentation via High-Quality Negative Prompts](https://mlsanity.com/paper/2506.15153/) (2025)
- [ARGUS: Stacked Multi-View Identity Mosaic Injection for Subject-Preserving Video Generation](https://mlsanity.com/paper/2606.11670/) (2026)
- [OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data](https://mlsanity.com/paper/2606.13432/) (2026)
- [ATTIQA: Generalizable Image Quality Feature Extractor using Attribute-aware Pretraining](https://mlsanity.com/paper/2406.01020/) (2024)

## Built on by (most cited first, 4 of 4)

- [OmniDrive: An LLM-Choreographed Multi-Agent World Model with Unified Latent Co-Compression for Multi-View Driving Video Generation](https://mlsanity.com/paper/2606.17536/) (2026)
- [TRIDENT: Breaking the Hybrid-Safety-Physics Coupling for Provably Safe Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2606.18308/) (2026)
- [Binding Multiple Modalities via Multimodal Wasserstein Barycenter](https://mlsanity.com/paper/2609.33800/) (2026)
- [Bridging Adversarial and Collaborative Learning for AI-Generated Image Quality Assessment](https://mlsanity.com/paper/2608.24372/) (2026)

## Abstract (arXiv)

Existing vision-language model (VLM)-based AI-generated image quality assessment (AIGIQA) methods suffer from a fundamental semantic-distortion dimensional conflict: monolithic representations optimized for semantic discrimination inherently entangle compositional understanding with low-level perceptual sensitivity, rendering them blind to fine-grained quality degradations. We introduce MST-CLIPIQA, a multi-scale two-stream framework that achieves hierarchical vision-language alignment through explicit representational decoupling. Our architecture leverages dual CLIP encoders with complementary patch granularities: coarse-grained streams capture global semantic coherence while fine-grained streams preserve textural signatures and artifact patterns. An information bottleneck-inspired gated fusion mechanism performs adaptive cross-scale distillation, with optional cross-attention enabling prompt-anchored correspondence evaluation when generation prompts are available. Extensive experiments across five benchmarks establish new state-of-the-art results, achieving average improvements of 1.11 percent SRCC on quality and 2.35 percent SRCC on text-image correspondence prediction, while maintaining efficiency with only 0.8M trainable parameters. Our project is available at https://github.com/YMlinfeng/MST-CLIPIQA.