I'm an Assistant Professor in Statistics and Data Science at Northwestern University. Prior to joining Northwestern, I obtained my Ph.D. degree in Computer Science at Arizona State University in 2023 under the supervision of Prof. Huan Liu.

‪Assistant Professor of Stats & Data Science, Northwestern University‬ - ‪‪Cited by 3,908‬‬ - ‪Reliable Machine Learning‬ - ‪Data-Efficient Learning‬ - ‪Anomaly/OOD Detection‬ - ‪LLMs and GNNs‬

2017年1月13日 · In this paper, we propose a novel active learning framework, which is capable of building a competitive classifier with optimal feature representation via a limited amount of labeled training instances in an incremental learning manner. Our approach advances the existing active learning methods in two aspects.

We developed a rational yet cost-effective pipeline to significantly decrease the amount of user annota-tions for improving large-scale visual recognition (e.g., face identification and object detection).

王可泽老师分别于2012年和2017年在中山大学获得学士和博士学位，随后前往美国加州大学洛杉矶分校做博士后研究员。 他于2019年获得香港理工大学哲学博士学位。 他长期致力于视觉计算与推理的基础研究，提出“引导-自步-协同”长效自主学习等基础学习范式，对混乱数据的自主学习等关键难题提出了有效的解决方案，并取得具有一定影响力的学术成果。

2024年3月24日 · To address these issues, we propose an Adaptive Prompt Routing (APR) framework to adaptively route prompts from a human-readable prompt set for various input texts and given styles. Specifically, we first construct a candidate prompt set of diverse and human-readable prompts for the target style.

We proposed several methods to accomplish a real-time and high-accuracy system to predict 2D/3D human poses from depth or common RGB cameras. This system works efficiently and properly on mobile devices, e.g., MiBox 3.

ing data have different distributions. Inspired by the fact that humans can recognize novel concepts by composing ex-isted concepts and capsule network’s ability of representing part-whole hierarchies, we propose to use capsules to repre-sent parts and introduce “Linguistically Routing” to merge parts with human-prior hierarchies.

关于我们. 百度学术集成海量学术资源，融合人工智能、深度学习、大数据分析等技术，为科研工作者提供全面快捷的学术服务。

Keze Wang (王可泽) Sun Yat-sen University. Verified email at mail.sysu.edu.cn - Homepage. Deep representation learning self-supervised learning object detection image saliency. Articles Cited by Public access Co-authors. Title. Sort. Sort by citations Sort by year Sort by title. Cited by.