profile photo

Xinyue Zhu

Email: xz3013 [at] columbia [dot] edu

I am an incoming Ph.D. in Computer Science at Berkeley AI Research (BAIR) lab, advised by Prof. Ken Goldberg. I am also a research intern at SceniX. My research is supported by the NSF Graduate Research Fellowship (GRFP). Previously, I received my B.S. in Computer Science from Columbia University, where I worked with Prof. Yunzhu Li and Prof. Matei Ciocarlie.

My research focuses on robot learning and robot manipulation.

Updates

  • Apr 2026: I was awarded the NSF GRFP Fellowship! 🎊
  • Nov 2025: I started my internship as a Robotics Researcher at SceniX!
  • Sep 2025: Our paper Touch in the Wild is accepted to NeurIPS!
  • May 2025: Graduated with my Bachelor's Degree in Computer Science at Columbia. 🎉

Publications

Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper

Xinyue Zhu*, Binghao Huang*, Yunzhu Li

Best Demo Awardat RSS 2025 Workshop on Robot Hardware-Aware Intelligence [Link]

Conference on Neural Information Processing Systems (NeurIPS), 2025

website•paper•code

ReactEMG Stroke: Healthy-to-Stroke Few-shot Adaptation for sEMG-Based Intent Detection

Runsheng Wang, Katelyn Lee, Xinyue Zhu, Lauren Winterbottom, Dawn M. Nilsen*, Joel Stein*, and Matei Ciocarlie*

IEEE RAS/EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob), 2026

website•paper•code

Demo animation
ReactEMG: Zero-Shot, Low-Latency Intent Detection via sEMG

Runsheng Wang*, Xinyue Zhu*, Ava Chen, Jingxi Xu, Lauren Winterbottom, Dawn M. Nilsen, Joel Stein, Matei Ciocarlie

arXiv preprint, 2025

website•paper•code

Tactile-based Object Retrieval from Granular Media

Jingxi Xu*, Yinsen Jia*, Dongxiao Yang*, Patrick Meng, Xinyue Zhu, Zihan Guo, Shuran Song, Matei Ciocarlie

Autonomous Robots Journal, 2025

website•paper•video

DisRNN Architecture
Disentangling Interpretable Cognitive Variables That Support Human Generalization via DisRNN

Xinyue Zhu, Daniel Kimmel

Workshop on Interpreting Cognition in Deep Learning Models, NeurIPS 2025

paper

Knolling Bot: Learning Robotic Object Arrangement from Tidy Demonstrations

Yuhang Hu, Zhizhuo Zhang, Xinyue Zhu, Ruibo Liu, Philippe Wyder, Hod Lipson

Conference on Neural Information Processing Systems (NeurIPS), Creative AI Track, 2025

website•paper•code

GRID: Scene-Graph-based Instruction-driven Robotic Task Planning

Zhe Ni*, Xiaoxin Deng*, Cong Tai*, Xinyue Zhu, Qinghongbing Xie, Weihang Huang, Xiang Wu, Long Zeng

International Conference on Intelligent Robots and Systems (IROS), 2024

website•paper•code

Latin Square
Uniquely Completable And Critical Subsets of the Integer Addition Table

Aurora Callahan*, Emma R Hasson*, Kaethe Minden*, MA Ollis*, Xinyue Zhu*

Australasian Journal of Combinatorics, 2023

paper