arXiv Machine Learning

Fashion Outfit Generation via Unified Sequential Composition Models

arXiv:2608. 13888v1 Announce Type: new Abstract: The task of synthesizing stylistically coherent fashion outfits from massive item libraries, known as fashion outfit generation, remains a non-trivial challenge, primarily due to the non-monotonic and implicit nature of aesthetic compatibility, coupled with the exponentially large combinatorial search space.

Hugging Face Trending Papers
6d ago

Fashion Outfit Generation via Unified Sequential Composition Models

The task of synthesizing stylistically coherent fashion outfits from massive item libraries, known as fashion outfit generation, remains a non-trivial challenge, primarily due to the non-monotonic and implicit nature of aesthetic compatibility, coupled with the exponentially large combinatorial search space. In this paper, we formalize this task as Constrained Ensemble Generation (CEG) and model it as a finite-horizon deterministic Markov Decision Process.

arXiv Machine Learning
Jun 2

SurrogateSHAP: Training-Free Contributor Attribution for Text-to-Image (T2I) Models

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.

By Mingyu Lu, Soham Gadgil, Chris Lin, Chanwoo Kim, Su-In Lee
arXiv AI
Jun 3

TASTE: A Designer-Annotated Multi-Dimensional Preference Dataset for AI-Generated Graphic Design

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.

By Haonan Zhu, Elad Hirsch, Alexandria Minetti, Allison Nulty, Purvanshi Mehta
arXiv AI
Jun 16

LLM-Powered Virtual Population for Demand Simulation and Pricing

arXiv:2606. 16183v1 Announce Type: cross Abstract: We develop an LLM-powered virtual population model that simulates demand for pricing decisions, in settings where products are described by rich unstructured information, such as text descriptions and images, and where decision makers need not only mean-demand predictions but also uncertainty estimates for counterfactual prices.

By Chengpiao Huang, Kaizheng Wang