PRISM: Learning Design Knowledge from Data for Stylistic Design Improvement

2026-01-16 · Huaxiaoyue Wang, Sunav Choudhary, Franck Dernoncourt, Yu Shen, Stefano Petrangeli arxiv

Graphic design often involves exploring different stylistic directions, which can be time-consuming for non-experts. We address this problem of stylistically improving designs based on natural language instructions. While VLMs have shown initial success in graphic design, their pretrained knowledge on styles is often too general and misaligned with specific domain data. For example, VLMs may associate minimalism with abstract designs, whereas designers emphasize shape and color choices. Our key insight is to leverage design data -- a collection of real-world designs that implicitly capture designer's principles -- to learn design knowledge and guide stylistic improvement. We propose PRISM (PRior-Informed Stylistic Modification) that constructs and applies a design knowledge base through three stages: (1) clustering high-variance designs to capture diversity within a style, (2) summarizing each cluster into actionable design knowledge, and (3) retrieving relevant knowledge during inference to enable style-aware improvement. Experiments on the Crello dataset show that PRISM achieves the highest average rank of 1.49 (closer to 1 is better) over baselines in style alignment. User studies further validate these results, showing that PRISM is consistently preferred by designers.

📄 PDF Abstract BibTeX arXiv:2601.11747

Code (0)

등록된 구현이 없습니다.

PeerPrism: Peer Evaluation Expertise vs Review-writing AI

2026-04-16 · Soroush Sadeghian, Alireza Daqiq, Radin Cheraghi, Sajad Ebrahimi 외 arxiv

Large Language Models (LLMs) are increasingly used in scientific peer review, assisting with drafting, rewriting, expansion, and refinement. However, existing peer-review LLM detection methods largely treat authorship as…

Text Detection

PRISM: Precision-Recall Informed Data-Free Knowledge Distillation via Generative Diffusion

2025-09-21 · Xuewan He, Jielei Wang, Zihan Cheng, Yuchen Su 외 arxiv

Data-free knowledge distillation (DFKD) transfers knowledge from a teacher to a student without access to the real in-distribution (ID) data. While existing methods perform well on small-scale images, they suffer from mo…

Data-free Knowledge Distillation Domain Generalization Prompt Engineering

PRISM: A Promptable and Robust Interactive Segmentation Model with Visual Prompts

2024-04-23 · Hao Li, Han Liu, Dewei Hu, Jiacheng Wang 외

In this paper, we present PRISM, a Promptable and Robust Interactive Segmentation Model, aiming for precise segmentation of 3D medical images. PRISM accepts various visual inputs, including points, boxes, and scribbles a…

Interactive Segmentation Prompt Engineering Segmentation Tumor Segmentation

FedPrism: Adaptive Personalized Federated Learning under Non-IID Data

2026-03-09 · Prakash Kumbhakar, Shrey Srivastava, Haroon R Lone arxiv

Federated Learning (FL) suffers significant performance degradation in real-world deployments characterized by moderate to extreme statistical heterogeneity (non-IID client data). While global aggregation strategies prom…

Personalized Federated Learning

Do LLMs Understand Personality? Rethinking Persona Fidelity Evaluation through Structured Behavioral Inference

2026-08-27 · Mengfan Li, Zesheng Wei, Xuanhua Shi, Yang Deng arxiv

As large language models are increasingly deployed to simulate diverse human characters, ensuring persona fidelity, defined as the extent to which an agent's behavior consistently reflects the psychological and stylistic…