Publications

My research interests lies in general robotic manipulation, foundation models in robotics, multi-agent system and small-scale computer vision models. Below are my publications (* denotes equal contribution). You can also find my articles on my Google Scholar profile.

Conference Papers

GPT-Fabric: Smoothing and Folding Fabric by Leveraging Pre-Trained Foundation Models

Published in International Symposium of Robotics Research (ISRR), 2024

Propose GPT-Fabric for fabric folding and smoothing, achieve comparable and even better folding and smoothing performance comparing to previous methods with no training data required.

Recommended citation: Vedant Raval*, Enyu Zhao*, Hejia Zhang, Stefanos Nikolaidis, and Daniel Seita. (2024). "GPT-Fabric: Smoothing and Folding Fabric by Leveraging Pre-Trained Foundation Models." International Symposium of Robotics Research (ISRR).
Download Paper

Journal Articles

SDI: A tool for speech differentiation in user identification

Published in Expert Systems with Applications, 2024

This paper proposed a speech differentiator with integrated SVM (SDI-SVM) by implementing threshold checking and frequency matching mechanisms.

Recommended citation: Muhammad Abdul Basit, Chanjuan Liu, Enyu Zhao. (2024). "SDI: A tool for speech differentiation in user identification." Expert Systems with Applications. Volume 243, 122866.
Download Paper

Time-aware MADDPG with LSTM for multi-agent obstacle avoidance: a comparative study

Published in Complex & Intelligent Systems, 2024

This paper addresses the limitations of MADDPG in multi-agent navigation and obstacle avoidance tasks, providing insights for developing intelligent agents and multi-agent systems.

Recommended citation: Enyu Zhao, Ning Zhou, Chanjuan Liu, Houfu Su, Yang Liu & Jinmiao Cong. (2024). "Time-aware MADDPG with LSTM for multi-agent obstacle avoidance: a comparative study." Complex & Intelligent Systems. Volume 10, pages 4141–4155.
Download Paper

Preprints

Instant Photorealistic Style Transfer: A Lightweight and Adaptive Approach

Published in arXiv, 2023

This paper proposes an Instant Photorealistic Style Transfer (IPST) approach, designed to achieve instant photorealistic style transfer on super-resolution inputs without the need for pre-training on pair-wise datasets or imposing extra constraints.

Recommended citation: Rong Liu, Enyu Zhao, Zhiyuan Liu, Andrew Feng, Scott John Easley. (2023). "Instant Photorealistic Style Transfer: A Lightweight and Adaptive Approach." arXiv preprint arXiv:2309.10011.
Download Paper

Enyu Zhao / 赵恩宇