AI Paper Atlas

Research map / Large language models / AI and society

From Imitation to Innovation: The Emergence of AI's Unique Artistic Styles and the Challenge of Copyright Protection

Zexi Jia, Chuanwei Huang, Yeshuang Zhu, Hongyan Fei, Ying Deng, Zhiqiang Yuan, Jiapei Zhang, Jinchao Zhang, Jie Zhou

ICCV 2025 · Large language models › AI and society · approach: Human-centered trust and agency · 2 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 description-guided cross-modal distillation on top of CLIP featuresCLIP k-means · Artist style clustering, WikiARTACC: 36.09 -> 41.45Improved
raise alpha (cluster entropy weight) from 2 to 3 (ablation)DGC · Artist style clustering, WikiARTACC: 35.38 -> 41.45Improved
raise alpha from 3 to 5 (ablation)DGC · Artist style clustering, WikiARTACC: 41.45 -> 40.29Hurt
raise neighbor count N from 5 to 10 (ablation)DGC · Artist style clustering, WikiARTACC: 39.78 -> 41.45Improved
raise neighbor count N from 10 to 15 (ablation)DGC · Artist style clustering, WikiARTACC: 41.45 -> 40.73Hurt
use CLIP instead of BLIP-2 features (ablation)DGC · Artist style clustering, WikiARTACC: 1.78% dropImproved
use CLIP instead of SigLip features (ablation)DGC · Artist style clustering, WikiARTACC: 2.54% decreaseImproved
add MLLM chain-of-thought reasoning (ArtBulb) over DGC clustering resultsDGC · AICD copyright judgment (average)accuracy: 0.81 -> 0.86Improved
add MLLM chain-of-thought reasoning (ArtBulb) over DGC clustering resultsDGC · AICD copyright judgment (average)F1: 0.79 -> 0.88Improved
guide the MLLM with DGC clustering resultsGPT-4o · AICD explanation quality (AHR)expert rating: 2.05 -> 3.70Improved
guide the MLLM with DGC clustering resultsQwen2-VL · AICD explanation quality (AHR)expert rating: 1.80 -> 3.55Improved
use GPT-4o instead of Qwen2-VL or DeepSeek-VL as the MLLM (ablation)ArtBulb · AICD test setaverage accuracy: 0.86 vs 0.81 and 0.74Improved

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