Kaiwen Hong

I am a Ph.D. candidate at the University of Illinois Urbana-Champaign, advised by Prof. Katherine Driggs-Campbell. My research interest is to make real-world robot systems more adaptable, deployable, and steerable.

I currently work on diffusion VLM research at Waymo. I also spent time at a Humanoid Stealth company, Amazon Robotics, and XPENG US.

Email Google Scholar LinkedIn
profile photo

Research

SelectedBy date
project image

Self-Labeled Preference Transfer: Bootstrapping Steerable Robot Manipulation on Unlabeled Tasks

Kaiwen Hong, Shaoting Peng*, Xiangyu Zeng*, Pengcheng Wang*, Boyuan Tian, Haonan Chen, Yifan Zhu, Yixiao Wang, Katherine Rose Driggs-Campbell
* Equal contribution

Under review · 2026
project image

DiscreteRTC: Discrete Diffusion Policies are Natural Asynchronous Executors

Pengcheng Wang, Kaiwen Hong, Chensheng Peng, Katherine Driggs-Campbell, Masayoshi Tomizuka, Chenfeng Xu, Chen Tang

Under review · 2026
website ↗
project image

Brick-Composer: Using MLLMs for Assembly with Diverse Bricks

Jiateng Liu, Bingxuan Li, Zhenhailong Wang, Rushi Wang, Kaiwen Hong, Cheng Qian, Jiayu Liu, Denghui Zhang, Katherine Driggs-Campbell, Manling Li, Heng Ji

Under review · 2026
website ↗
project image

Sim-and-Real Co-Training of Graph Neural Dynamics for Long-Horizon Scooping

Kaiwen Hong, Haonan Chen*, Jiaming Xu*, Runxuan Wang*, Kaylan Wang, Mingtong Zhang, Shuijing Liu, Yifan Zhu, Yunzhu Li, Katherine Driggs-Campbell
* Equal contribution

IEEE International Conference on Robotics and Automation (ICRA) · 2026
website ↗
project image

Multi-Modal Manipulation via Multi-Modal Policy Consensus

Haonan Chen, Jiaming Xu*, Hongyu Chen*, Kaiwen Hong, Binghao Huang, Chaoqi Liu, Jiayuan Mao, Yunzhu Li, Yilun Du+, Katherine Driggs-Campbell+
* Equal contribution, + Equal advising

IEEE International Conference on Robotics and Automation (ICRA) · 2026
Best Paper Award, CVPR 2026 Sense of Space Workshop
website ↗
project image

HEIGHT: Heterogeneous Interaction Graph Transformer for Robot Navigation in Crowded and Constrained Environments

Shuijing Liu, Haochen Xia, Fatemeh Cheraghi Pouria, Kaiwen Hong, Neeloy Chakraborty, Zichao Hu, Joydeep Biswas, Katherine Driggs-Campbell

IEEE Transactions on Automation Science and Engineering (T-ASE) · 2025
Best Paper Award, ICRA 2025 Workshop on Advances in Social Navigation
website ↗
project image

Introducing 3D Representation for Dense Volume-to-Volume Translation via Score Fusion

Xiyue Zhu, Dou Hoon Kwark, Ruike Zhu, Kaiwen Hong, Yiqi Tao, Shirui Luo, Yudu Li, Zhi-Pei Liang, Volodymyr Kindratenko

International Conference on Machine Learning (ICML) · 2025
website ↗
project image

Human-Agent Joint Learning for Efficient Robot Manipulation Skill Acquisition

Shengcheng Luo*, Quanquan Peng*, Jun Lv*, Kaiwen Hong, Katherine Rose Driggs-Campbell, Cewu Lu, Yong-Lu Li
* Equal contribution

IEEE International Conference on Robotics and Automation (ICRA) · 2025
Best Paper in Human-Robot Interaction, ICRA 2025Best Conference Paper Finalist, ICRA 2025
website ↗
project image

Predicting Object Interactions with Behavior Primitives: An Application in Stowing Tasks

Haonan Chen, Yilong Niu*, Kaiwen Hong*, Shuijing Liu, Yiqing Wang, Yunzhu Li, Katherine Driggs-Campbell
* Equal contribution

Conference on Robot Learning (CoRL) · 2023
Oral · Best Paper / Best Student Paper Award Finalist, CoRL 2023
website ↗
project image

A Data-Efficient Visual-Audio Representation with Intuitive Fine-tuning for Voice-Controlled Robots

Peixin Chang, Shuijing Liu, Tianchen Ji, Neeloy Chakraborty, Kaiwen Hong, Katherine Driggs-Campbell

Conference on Robot Learning (CoRL) · 2023
website ↗
project image

Intention-Aware Robot Crowd Navigation with Attention-Based Interaction Graph

Shuijing Liu, Peixin Chang, Zhe Huang, Neeloy Chakraborty, Kaiwen Hong, Weihang Liang, D. Livingston McPherson, Junyi Geng, Katherine Driggs-Campbell

IEEE International Conference on Robotics and Automation (ICRA) · 2023
Best Poster Award, IROS 2023 Last-Mile Robotics Workshop
website ↗

Awards

Design and source code from Jon Barron's website