arXiv:2605. 20731v2 Announce Type: replace-cross Abstract: Text-to-image models now generate graphic design at production scale, yet their supervision still comes primarily from photo-style preference datasets with a single overall verdict per comparison.
arXiv:2606. 31711v1 Announce Type: new Abstract: Faithfulness -- how precisely a generated image aligns with its prompt -- is increasingly central to the real-world utility of text-to-image (T2I) models.
arXiv:2603. 13312v2 Announce Type: replace-cross Abstract: Interior design is a requirements-to-visual-plan generation process that must simultaneously satisfy verifiable spatial feasibility and comparative aesthetic preferences.
arXiv:2602. 15278v2 Announce Type: replace-cross Abstract: The web is littered with images, once created for human consumption and now increasingly interpreted by agents using vision-language models (VLMs).
AesCanvas is a new dataset and benchmark that evaluates image aesthetic models on two fronts: CritiqueCanvas, which contains 519,136 instruction–response pairs for long‑form, multi‑dimensional critique across photography, painting, and virtual imagery, and ContextCanvas, which offers 301 expert‑reviewed use scenarios to assess contextual aesthetic suitability. The benchmark tests closed‑source, open‑weight general, and aesthetic‑specific multimodal large language models, revealing that models excel at critique generation but lag in context‑sensitive judgment. The study shows that aesthetic specialization does not reliably transfer to contextual suitability and highlights the need for culturally situated, evidence‑grounded suitability as a distinct objective for aesthetic modeling.
The study audits four image aesthetic scorers—LAION-Aesthetics, PickScore, ImageReward, and HPSv2—using pixel‑level interventions on skin tone and body type in both synthetic and real images. It finds that most scorers exhibit a fidelity preference: unaltered images receive the highest scores, while perturbations in either direction are penalized in an inverted‑U pattern, and this effect is largely independent of the skin operator. Synthetic‑only audits are misleading, as the apparent preference for darker skin in synthetic faces reverses or weakens when evaluated on real faces, and cross‑scorer results vary widely, underscoring the need for real‑data, within‑image causal isolation to accurately assess demographic bias.
arXiv:2606. 05478v1 Announce Type: cross Abstract: Diffusion Models (DM) have revolutionized text-driven generation by enabling the synthesis of high-quality, photorealistic visual content from user prompts.
arXiv:2609.24228v1 Announce Type: new Abstract: Text-to-image (T2I) models are typically evaluated for bias using slot-based templates such as ``a photo of a [profession]''. Such templates probe only...
arXiv:2601. 22276v2 Announce Type: replace Abstract: As Text-to-Image (T2I) diffusion models are increasingly used in real-world creative workflows, a principled framework for valuing contributors who provide a collection of data is essential for fair compensation and sustainable data marketplaces.
The paper introduces a method for learning heterogeneous, individually conditioned utility functions—termed individuated utility—by leveraging rational choice theory. It presents a multi-stage architecture that estimates these functions from multimodal data and evaluates it on a large dataset of aesthetic judgments about automotive wheel designs. Results show that individuated models outperform universal utility models and foundation baselines, indicating that annotator disagreement reflects meaningful preference diversity.
The paper presents a post‑training approach for text‑to‑image models that combines a preference reward, trained on large human preference data, with rubric‑based rewards that assess prompt faithfulness and other desirable traits. The authors show that a simple reward composition strategy outperforms a naive weighted average, leading to significant Elo gains on the Arena leaderboard for models like Flux2dev and Ideogram‑4. They also release Arena‑T2I‑Training, a 1K subset of data to aid reproducible research in post‑training.
The study investigates bias in large language model (LLM) judges by having ten LLMs evaluate narrative constraint selections rather than generated text. Results show that self-preference largely disappears under blind evaluation when quality and evaluator severity are controlled, but self- and other-labels alone shift scores bidirectionally when quality is matched. The authors conclude that authorship attribution drives evaluation bias and that open-ended, ground‑truth‑free tasks can effectively study LLM judge behavior.
The paper "Efficient Personalization of Generative User Interfaces" addresses the challenge of tailoring generative user interfaces (GenUIs) to individual users when interface screens are not pre‑defined. By collecting judgments from 20 participants on 600 GenUI pairs, the authors show low agreement (Krippendorff's alpha = 0.25) and diverse rationales for UI preferences. They propose a sample‑efficient personalization method that leverages a few pairwise judgments to weight prior users’ preferences, outperforming a pretrained UI evaluator and a larger multimodal model offline and outperforming all baselines in an online study with 12 new users. "whyItMatters":"The study demonstrates a practical approach to personalizing on‑demand interfaces, showing that even sparse, subjective feedback can be effectively used to improve user satisfaction with generative UI designs."