{"ID":2830955,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.11883","arxiv_id":"2512.11883","title":"Position: Universal Aesthetic Alignment Narrows Artistic Expression","abstract":"Over-aligning image generation models to a generalized aesthetic preference conflicts with user intent, particularly when \"anti-aesthetic\" outputs are requested for artistic or critical purposes. This adherence prioritizes developer-centered values, compromising user autonomy and aesthetic pluralism. We test this bias by constructing a wide-spectrum aesthetics dataset and evaluating state-of-the-art generation and reward models. This position paper finds that aesthetic-aligned generation models frequently default to conventionally beautiful outputs, failing to respect instructions for low-quality or negative imagery. Crucially, reward models penalize anti-aesthetic images even when they perfectly match the explicit user prompt. We confirm this systemic bias through image-to-image editing and evaluation against real abstract artworks. Our code, fine-tuned models, and datasets are available on our meta-expression intentionally anti-aesthetics webpage: https://weathon.github.io/icml2026_position/.","short_abstract":"Over-aligning image generation models to a generalized aesthetic preference conflicts with user intent, particularly when \"anti-aesthetic\" outputs are requested for artistic or critical purposes. This adherence prioritizes developer-centered values, compromising user autonomy and aesthetic pluralism. We test this bias...","url_abs":"https://arxiv.org/abs/2512.11883","url_pdf":"https://arxiv.org/pdf/2512.11883v3","authors":"[\"Wenqi Marshall Guo\",\"Qingyun Qian\",\"Khalad Hasan\",\"Shan Du\"]","published":"2025-12-09T00:24:29Z","proceeding":"cs.CY","tasks":"[\"cs.CY\",\"cs.AI\",\"cs.CV\"]","methods":"[]","has_code":false}