Lijun Xu

New-media art generation faces costly user-preference collection and diffusion sampling without interpretable guidance. The CART-rule-guided diffusion model first uses a conditional GAN to expand 2,000 real ratings into 10,000 virtual agents and 500,000 preference records, then converts CART decision-tree rules into a differentiable gradient injected into the reverse sampling of Stable Diffusion 1.5. Against five baselines it reaches FID 29.56, preference accuracy 0.734 and Hit Rate@3 0.512, improving over the strongest baseline RF-AIGC by 13.8%, 9.4% and 19.6%.

New-media art generation faces costly user-preference collection and diffusion sampling without interpretable guidance. The CART-rule-guided diffusion model first uses a conditional GAN to expand 2,000 real ratings into 10,000 virtual agents and 500,000 preference records, then converts CART decision-tree rules into a differentiable gradient injected into the reverse sampling of Stable Diffusion 1.5. Against five baselines it reaches FID 29.56, preference accuracy 0.734 and Hit Rate@3 0.512, improving over the strongest baseline RF-AIGC by 13.8%, 9.4% and 19.6%.