Jianxin Bi

I am Ph.D. candidate at NUS, 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.

Feel free to reach out — jxbi1010 [at] gmail [dot] com

News

Jun 30, 2026	Heterogeneous Tactile Transformer will be presented at RSS 2026 Workshop on Tactile for FM!
Apr 10, 2026	VLA-Touch is accepted to RA-L!
Feb 01, 2025	KOAP is accpted to ICRA 2025!

Selected Publications

arXiv

Heterogeneous Tactile Transformer

Jianxin Bi, Qiang Wang, Jayaram Reddy, Kelvin Lin, Soibkhon Khajikhanov, Ruihan Gao, and Harold Soh

Under Review, 2026

arXiv Bib Website

@article{bi2026htt,
  title = {Heterogeneous Tactile Transformer},
  author = {Bi, Jianxin and Wang, Qiang and Reddy, Jayaram and Lin, Kelvin and Khajikhanov, Soibkhon and Gao, Ruihan and Soh, Harold},
  journal = {Under Review},
  year = {2026},
  eprint = {2606.29948},
  archiveprefix = {arXiv},
  primaryclass = {cs.RO},
  url = {https://arxiv.org/abs/2606.29948},
}

RA-L

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

IEEE Robotics and Automation Letters (RA-L), 2025

arXiv Bib Code Website

@article{bi2025vlatouch,
  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},
  journal = {IEEE Robotics and Automation Letters (RA-L)},
  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},
}