From the 3 of 22 linked papers with an AI index.
22 papers
DefaultShift: Auditing Semantic Default Shift in Accelerated Text-to-Image Models
Xuanhua Yin, Chuanzhi Xu, Shunqi Mao +2
Few-step text-to-image models increasingly replace slower generators, yet acceleration can silently change distributions over unspecified attributes even when individual outputs re…
Calibrate What You SHIP: Post-Selection Risk Control for Verifier-Guided Text-to-Image Generation
Xuanhua Yin, Shunqi Mao, Wei Guo +2
Verifier-guided text-to-image systems increasingly use test-time search to select, refine, or stop among multiple candidates, yet release thresholds are often calibrated on individ…
Learning Color Grading, No Photo Sharing: Federated Aesthetic Preference Learning for Personalized Image Enhancement
Chuanzhi Xu, Ziyuan Tao, Jean Julien KNell +5
The paper proposes FedPAIE, a federated learning framework that learns individual aesthetic preferences for color grading and applies lightweight, personalized image enhancement on…
SciFigQual-Bench: A Benchmark for Scientific Figure Quality Assessment with Full-Manuscript Context
Zihan Deng, Chuanzhi Xu, Huiqi Liang +3
The paper introduces SciFigQual-Bench, a benchmark dataset that evaluates the quality of scientific figures within full manuscript context across five dimensions, and presents a cr…
SciFigAlign: Scoring Scientific Figures by Fine-tuned Alignment of Visuals with Manuscript Evidence
Chuanzhi Xu, Zihan Deng, Huiqi Liang +4
The paper introduces SciFigAlign, a multimodal model that scores scientific figures by aligning visual content with manuscript evidence, using fine‑tuned CLIP and SciBERT to predic…
MGDFIS: Multi-scale Global-detail Feature Integration Strategy for Small Object Detection
Yuxiang Wang, Xuecheng Bai, Chuanzhi Xu +2
Small-object detection in Unmanned Aerial Vehicle (UAV) imagery requires preserving weak local evidence while using broader context to separate tiny foreground targets from clutter…