| CARVIEW |
About Me
I am a Research Scientist at NVIDIA Research, where I focuses on efficient decision-making and optimization with LLMs. I obtained my Ph.D. degree at UC San Diego in the CSE department under the supervision of Xiaolong Wang. Before joining NVIDIA, I was also a Student Researcher at Google DeepMind, hosted by Kuang-Huei Lee. In the past, I've worked with Hao Su at UCSD and Masashi Sugiyama at RIKEN-AIP.
I received my B.S. in Electrical Engineering and a M.S. in Computer Science from National Taiwan University. My research interests lie in the fields of reinforcement learning, robotics, and computer vision. Specifically, I am devoted to developing innovative methods for real-world applications. My primary focus is on enhancing robust object manipulation techniques and learning from 3D structures. Additionally, I am keen on utilizing foundational models as effective tools for facilitating the learning process in these domains.
Please see my CV for more information. If you would like to know more about my research, please contact me via email, kriswu [at] nvidia.com.
Education
Publications
-
Unified Reinforcement and Imitation Learning for Vision-Language Models [website]
Byung-Kwan Lee, Ryo Hachiuma, Yu-Chiang Frank Wang, Yong Man Ro, and Yueh-Hua Wu
In Advances in Neural Information Processing Systems (NeurIPS), 2025 -
ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning [website]
Chi-Pin Huang, Yueh-Hua Wu, Min-Hung Chen, Yu-Chiang Frank Wang, Fred Yang
In Advances in Neural Information Processing Systems (NeurIPS), 2025 -
GenRecal: Generation after Recalibration from Large to Small Vision-Language Models [website]
Byung-Kwan Lee, Ryo Hachiuma, Yu-Chiang Frank Wang, Yong Man Ro, and Yueh-Hua Wu
under submission, 2025 -
Evolving Deeper LLM Thinking
Kuang-Huei Lee, Ian Fischera, Yueh-Hua Wu, Dave Marwood, Shumeet Baluja, Dale Schuurmans, and Xinyun Chen
Preprint arXiv:2501.09891, 2025 -
VLsI: Verbalized Layers-to-Interactions from Large to Small Vision Language Models [website]
Byung-Kwan Lee, Ryo Hachiuma, Yu-Chiang Frank Wang, Yong Man Ro, and Yueh-Hua Wu
In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025 -
DNAct: Diffusion Guided Multi-Task 3D Policy Learning [website]
Ge Yan*, Yueh-Hua Wu*, and Xiaolong Wang
In International Conference on Intelligent Robots and Systems (IROS), 2025 -
Open X-Embodiment: Robotic Learning Datasets and RT-X Models
[website]
Best Paper Award
Open X-Embodiment, [...], Yueh-Hua Wu, [...] (173 authors)
In IEEE International Conference on Robotics and Automation (ICRA), 2024 -
Elastic Decision Transformer [website] [code]
Yueh-Hua Wu, Xiaolong Wang*, and Masashi Hamaya*
In Advances in Neural Information Processing Systems (NeurIPS), 2023 -
GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields (Oral) [code] [website]
Yanjie Ze*, Ge Yan*, Yueh-Hua Wu*, Annabella Macaluso, Yuying Ge, Jianglong Ye, Nicklas Hansen, Li Erran Li, and Xiaolong Wang
In Proceedings of the Conference on Robotic Learning (CoRL), 2023 -
CoTransporter: Offline Multi-Agent Reinforcement Learning for Object Manipulation [website]
Yueh-Hua Wu, Takayoshi Takayanagi, Xiaolong Wang, and Hirotaka Suzuki
under submission, 2023 -
Learning Generalizable Dexterous Manipulation from Human Grasp Affordance [website]
Yueh-Hua Wu*, Jiashun Wang*, and Xiaolong Wang
In Proceedings of the Conference on Robotic Learning (CoRL), 2022 -
DexMV: Imitation Learning for Dexterous Manipulation from Human Videos [website]
Yuzhe Qin*, Yueh-Hua Wu*, Shaowei Liu, Hanwen Jiang, Ruihan Yang, Yang Fu, and Xiaolong Wang
In Proceedings of the European Conference on Computer Vision (ECCV), 2022 -
CSPNet: A New Backbone that can Enhance Learning Capability of CNN [code]
Chien-Yao Wang, Hong-Yuan Mark Liao, I-Hau Yeh, Yueh-Hua Wu (corresponding author), Ping-Yang Chen, and Jun-Wei Hsieh
In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR Workshops), 2020 -
Model Imitation for Model-Based Reinforcement Learning
Yueh-Hua Wu*, Ting-Han Fan*, Peter J. Ramadge, and Hao Su
ICLR 2020 Submission (Scores: 6, 6, 6)
Preprint arXiv:1909.11821, 2019 -
Imitation Learning from Imperfect Demonstration (Oral) [code] [slides] [poster]
Yueh-Hua Wu, Nontawat Charoenphakdee, Han Bao, Voot Tangkaratt, and Masashi Sugiyama
In Proceedings of the 36th International Conference on Machine Learning (ICML), 2019 -
A Regulation Enforcement Solution for Multi-agent Reinforcement Learning
Fan-Yun Sun, Yen-Yu Chang, Yueh-Hua Wu, and Shou-De Lin
In Proceedings of the 18th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2019 -
A Low-Cost Ethics Shaping Approach for Designing Reinforcement Learning Agents (Oral) [code]
Yueh-Hua Wu and Shou-De Lin
In Proceedings of the 32nd AAAI conference on Artificial Intelligence (AAAI), 2018 -
Designing Non-greedy Reinforcement Learning Agents with Diminishing Reward Shaping (Oral)
Fan-Yun Sun, Yen-Yu Chang, Yueh-Hua Wu, and Shou-De Lin
In Proceedings of the 1st AAAI/ACM conference on Artificial Intelligence, Ethics, and Society (AIES), 2018
Work Experiences
Awards
- J. Yang Scholarship, UC San Diego Institute of Engineering in Medicine, 2020 - 2021
- Graduate Student Scholarship, the Ministry of Education, 2017 - 2019
- Winner, ACM WSDM Cup 2016, 2016