Jianxin Bi

I am a Ph.D. candidate at the Dept. of Computer Science, NUS. I am advised by Prof. Harold Soh who leads the CLeAR lab. Previously, I obtained my bachelor degree from EEE, NTU.

My current reasrch focus on data-efficient imitation learning methods for robot manipulation, e.g. learning action from visual demostration and improve VLA models for contact-rich tasks with tactile feedback. I have also worked on constrained reinforcement learning for fair allocation and policy transfer.

In the long run, I aim to build adaptive, reactive and self-explorable robot systems that can work effectively and collaborate seamlessly with humans in daily life scenarios.

news

Jul 24, 2025	VLA-Touch is now avaiable on arxiv!
Feb 01, 2025	KOAP is accpted to ICRA 2025!

selected publications

PrePrint

VLA-Touch: Enhancing Vision-Language-Action Models with Dual-Level Tactile Feedback

Jianxin Bi, Kevin Yuchen Ma, Ce Hao, Mike Zheng Shou, and Harold Soh

2025

arXiv Bib Code Website

@misc{bi2025vlatouchenhancingvisionlanguageactionmodels,
  title = {VLA-Touch: Enhancing Vision-Language-Action Models with Dual-Level Tactile Feedback},
  author = {Bi, Jianxin and Ma, Kevin Yuchen and Hao, Ce and Shou, Mike Zheng and Soh, Harold},
  year = {2025},
  eprint = {2507.17294},
  archiveprefix = {arXiv},
  primaryclass = {cs.RO},
  url = {https://arxiv.org/abs/2507.17294},
}

ICRA

Imitation Learning with Limited Actions via Diffusion Planners and Deep Koopman Controllers

Jianxin Bi, Kelvin Lim, Kaiqi Chen, Yifei Huang, and Harold Soh

In 2025 IEEE International Conference on Robotics and Automation (ICRA), 2024

arXiv Bib Code

@inproceedings{bi2025imitationlearninglimitedactions,
  title = {Imitation Learning with Limited Actions via Diffusion Planners and Deep Koopman Controllers},
  author = {Bi, Jianxin and Lim, Kelvin and Chen, Kaiqi and Huang, Yifei and Soh, Harold},
  booktitle = {2025 IEEE International Conference on Robotics and Automation (ICRA)},
  year = {2024},
  eprint = {2410.07584},
  archiveprefix = {arXiv},
  primaryclass = {cs.RO},
  url = {https://arxiv.org/abs/2410.07584},
}

ICRA

Safety-Constrained Policy Transfer with Successor Features

Zeyu Feng, Bowen Zhang, Jianxin Bi, and Harold Soh

In 2023 IEEE International Conference on Robotics and Automation (ICRA), 2023

arXiv Bib Code

@inproceedings{10161256,
  author = {Feng, Zeyu and Zhang, Bowen and Bi, Jianxin and Soh, Harold},
  booktitle = {2023 IEEE International Conference on Robotics and Automation (ICRA)},
  title = {Safety-Constrained Policy Transfer with Successor Features},
  year = {2023},
  volume = {},
  number = {},
  pages = {7219-7225},
  keywords = {Automation;Reinforcement learning;Markov processes;Safety;Task analysis;Robots;Optimization},
}