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.
[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
Research
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.
A Stereo Matching Method for Three-Dimensional Eye Localization of Autostereoscopic
Display
Bangpeng Xiao,
Shenyuan Ye,
Xicai Li,
Min Li,
Lingyu Zhang,
Yuanqing Wang
International Conference on Image and Graphics, 2021
paper
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