🙋🏻‍♂️ About

I am YE, Ke (叶柯) 🔈, a PhD student at HKUST(GZ), advised by Prof. Junwei Liang at the Precognition Lab.

📬 Email 📕 CV 👨🏻‍💻 GitHub

Background

Research

Embodied AI · Robot Learning · Multimodal Intelligence

I study how robots learn manipulation from human demonstrations and generalize to new tasks and noisy observations.

News

• 2026/03 🎉 EgoTraj-Bench accepted to ICRA 2026.
• 2025/09 📄 Super-Mimic released on arXiv.
• 2025/09 🎉 AGNOSTOS accepted to NeurIPS 2025.

Selected Publications

	From Watch to Imagine: Steering Long-horizon Manipulation via Human Demonstration and Future Envisionment Ke Ye, Jiaming Zhou, Yuanfeng Qiu, Jiayi Liu, Shihui Zhou, Kun-Yu Lin, Junwei Liang Under Review 📜 arXiv 🌐 Website 📰 深蓝具身智能
	Exploring the Limits of Vision-Language-Action Manipulations in Cross-task Generalization Jiaming Zhou, Ke Ye, Jiayi Liu, Teli Ma, Zifan Wang, Ronghe Qiu, Kun-Yu Lin, Zhilin Zhao, Junwei Liang NeurIPS 2025 📜 arXiv 🌐 Website
	EgoTraj-Bench: Towards Robust Trajectory Prediction Under Ego-view Noisy Observations Jiayi Liu, Jiaming Zhou, Ke Ye, Kun-Yu Lin, Allan Wang, Junwei Liang ICRA 2026 📜 arXiv
	EGP3D: Edge-guided Geometric Preserving 3D Point Cloud Super-resolution for RGB-D camera Fang Zheng, Ke Ye (co-first), Yaofang Liu, Gongzhe Li, Xianhong Zhao, Jialong Li, Ruxin Wang, Yuchen Zhang, Xiangyang Ji, Qilin Sun 📜 arXiv

Projects & Code

Outside Research

🌐 I enjoy network security, DIY networking, and running servers and self-hosted services. 🛠️ I also tinker with single-board computers, 3D printing, and homelab setups.

Away from the keyboard, I enjoy 🎣 fishing and 🍳 cooking, especially eggs and meat.

🚭 No smoking or drinking. A bit of a Puritan, I know.