Kuai (Clara) Yu 俞快
Hi! I’m Kuai. My name means happiness and speed in Chinese, two things I bring to both my research and my daily life. I’m a first year PhD student in MEMS from Duke Engineering. I obtained my Master degree in Computer Science from Columbia Engineering. I am super honored to be advised by Prof. Boyuan Chen. I was very fortunate to be supervised by Prof. Hod Lipson in Creative Machines Lab from Columbia University.
My research interests include Modeling in Dynamic Systems, VLA and Web Agents.
I’m thrilled to be joining GRL’s group at Duke University as a PhD student in Fall2026!!
Publications
How do Visual Attributes Influence Web Agents? A Comprehensive Evaluation of User Interface Design Factors
Kuai Yu, Naicheng Yu, Han Wang, Rui Yang, Huan Zhang
ACL 2026
We propose VAF, a comprehensive evaluation framework that systematically generates CSS-based webpage variants to analyze how visual design elements such as color, layout, and typography influence web agents’ decision-making, revealing human-like visual biases and vulnerabilities in multimodal web agents.
LyTimeT: Towards Robust and Interpretable State-Variable Discovery
Kuai Yu, Crystal Su, Xiang Liu, Judah Goldfeder, Mingyuan Shao, Hod Lipson
2026 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP26) Oral
Paper Link
We propose LyTimeT, a vision-transformer-based framework that integrates Lyapunov-theoretic regularization with time-series modeling to discover interpretable and robust state variables from visual dynamical systems, enabling stable trajectory prediction and physically consistent variable extraction across diverse temporal domains.
POLAR: Policy-based Layerwise Reinforcement Method for Stealthy Backdoor Attacks in Federated Learning
Kuai Yu, Xiaoyu Wu, Peishen Yan, Yang Hua, Hao Wang, Tao Song, Linshan Jiang, Haibing Guan
Under Review
Paper Link
We propose POLAR, a reinforcement learning-based method that formulates layer-wise selection for efficient and stealthy backdoor attacks in federated learning. POLAR dynamically adapts to defenses and balances attack success rate with stealthiness.
Services
Reviewers for AAAI2026, ACL2026.