Lingyu Zhang 张凌宇

PhD Student
Duke University
lingyu.zhang@duke.edu

I am a PhD student at the General Robotics Lab @ Duke University, advised by Prof. Boyuan Chen .

Previously, I graduated from Columbia with an MS EE degree. At Columbia, I worked on robust computer vision models with Prof. Junfeng Yang and Prof. Carl Vondrick, and worked closely with PhD student Chengzhi Mao. I was also a research assistant in Prof. Shih-Fu Chang's DVMM lab, where I worked on multimodal learning, under the supervision of Dr. Mingyang Zhou.

Prior to Columbia, I earned my Bachelor's degree at Nanjing University, China, where I did my undergraduate thesis on neural image compression, advised by Prof. Qiu Shen.

CV  /  Scholar  /  Linkedin  /  X  /  Github

[1/2025] Our paper on single human guiding multiple robots is accepted to ICRA 2025

[11/2024] Our paper CREW is accepted to TMLR 11/2024

[9/2024] Our paper GUIDE is accepted at Neurips 2024

[8/2024] Our platform for Human-AI teaming CREW is released

I am broadly interested in machine learning for decision making and perception. In particular, finding inspiration from humans for advancing real-world agents by improving the robustness and generalization of ML models.

Enables multi-robot collaboration from single-human guidance. Inspired by the human theory-of-mind, we leverage human-robot interface that allows a single human to guide multiple robots simultaneously, through which collaborative behavior can be learned.

Real-time human-guided RL with dense continuous rewards and a learned feedback model to reduce human input and enable continual training. We also provide insights on what makes a good human trainer for agents.

We introduce a platform for Human-AI teaming research. CREW offers extensible environment design, enables real-time human-AI communication, supports hybrid Human-AI teaming, parallel sessions, multimodal feedback, and physiological data collection, and features ML community-friendly algorithm design.

We introduce a framework that uses the dense intrinsic constraints in natural images to robustify inference, allowing the model to adjust dynamically to each individual image's unique and potentially novel characteristics at inference time.

We find that adversarial attacks generated for fooling video classifiers also collaterally corrupt motion. We propose to defend against attacks at test time by restoring disrupted motion.

We improve and optimize the ZNCC stereo matching algorithm for three-dimensional eye localization. We improve operation logic of the matching and optimize the scanning strategy based on the application scenarios. algorithm

Webpage template from Jon Barron