Transferring Visual Explainability from Self-Explaining to Prediction-Only Vision Transformers via Task Arithmetic
Yuya Yoshikawa · Ryotaro Shimizu · Takahiro Kawashima · Yuki Saito
首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。
实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。
Yuya Yoshikawa · Ryotaro Shimizu · Takahiro Kawashima · Yuki Saito
Johannes Kruse · Ryotaro Shimizu · Kasper Lindskow · Jon Tofteskov · Michael Riis Andersen · Julian J. McAuley · Jes Frellsen
In this paper, we present ZoRRO (Zero-Weight Personalized Recommender System), a zero-weight and training-free framework for personalized news recommendation designed for scalable real-world deployment. We show that ZoRRO outperforms strong neural baselines in offline ranking evaluations and deli...
Ryotaro Shimizu · Sai Htaungkham · Shion Sakurai · Yuki Shimizu
We report an evaluation benchmark for assessing the operational suitability of Vision-Language Models (VLMs) in fashion e-commerce. General-purpose benchmarks do not adequately cover fashion-specific attributes or the structured extraction tasks common in e-commerce workflows. We define five task...