I’m a 3rd-year direct Ph.D. student of artificial intelligence at Xi’an Jiaotong University, advised by Prof. Badong Chen. I am currently serving as a visiting student at the MiLab at Westlake University, advised by Prof. Donglin Wang. Previously, I obtained my bachelor’s degree from School of autamation in Chongqing University in 2022.

🔭 My research interests lie in generalization in computer vision and vision-language models. I’m also currently learning robotics, including generalization in robot learning and vision language action models.

✉️ Welcome to contact me for any discussion and cooperation!

💻 I am actively seeking academic and industrial exchange opportunities for Fall 2025, specifically focusing on joint Ph.D. programs and internship projects. I would greatly appreciate any information regarding potential opportunities that match my research interests and career aspirations.

🔥 News

• [2025/03]: One paper on causal discovery got accepted by Neural Networks 2025.
• [2025/01]: One paper (VLAS)) on vision-language-action model with speech instructions got accepted by ICLR 2025.
• [2024/12]: One paper (PromptTA) on VLM-based source-free domain generalization got accepted by ICASSP 2025.
• [2024/10]: The GitHub repository Awesome-Robotics-Manipulation is now public! Let’s work together to build a comprehensive and valuable resource for the robotics and AI community!
• [2024/07]: One paper (SPG) on VLM-based domain generalization got accepted by ECCV 2024.
• [2024/05]: One paper (JRNGC) on causal discovery got accepted by ICML 2024.
• [2023/12]: One paper (PDA) on VLM-based unsupervised domain adaptation got accepted by AAAI 2024, and one Paper on cross-domain few-shot classification got accepted by ICASSP 2024.

📝 Publications

An Information-Theoretic Approach for Heterogeneous Differentiable Causal Discovery

Wanqi Zhou, Shuanghao Bai, Qibin Zhao, Badong Chen

Neural Networks 2025

Paper | Code

Rethinking Latent Representations in Behavior Cloning: An Information Bottleneck Approach for Robot Manipulation

Shuanghao Bai, Wanqi Zhou, Pengxiang Ding, Wei Zhao, Donglin Wang, Badong Chen

arXiv 2025

arXiv| Project | Code

VLAS: Vision-Language-Action Model with Speech Instructions for Customized Robot Manipulation

Wei Zhao, Pengxiang Ding, Zhang Min, Zhefei Gong, Shuanghao Bai, Han Zhao, Donglin Wang

ICLR 2025

arXiv | Code

PromptTA: Prompt-driven Text Adapter for Source-free Domain Generalization

Haoran Zhang*, Shuanghao Bai*, Wanqi Zhou, Jingwen Fu, Badong Chen

ICASSP 2025

Paper | arXiv | Code

Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective

Wanqi Zhou*, Shuanghao Bai*, Qibin Zhao, Badong Chen

arXiv 2024

arXiv | Code

Soft Prompt Generation for Domain Generalization

Shuanghao Bai*, Yuedi Zhang*, Wanqi Zhou, Yicong He, Zhirong Luan, Badong Chen

ECCV 2024

Paper | arXiv | Code | Chinese Intro

Jacobian Regularizer-based Neural Granger Causality

Wanqi Zhou, Shuanghao Bai, Shujian Yu, Qibin Zhao, Badong Chen

ICML 2024

Paper | arXiv | Code

Prompt-based Distribution Alignment for Unsupervised Domain Adaptation

Shuanghao Bai, Min Zhang, Wanqi Zhou, Siteng Huang, Zhirong Luan, Donglin Wang, Badong Chen

AAAI 2024

Paper | arXiv | Code

Improving Cross-domain Few-shot Classification with Multilayer Perceptron

Shuanghao Bai, Wanqi Zhou, Zhirong Luan, Donglin Wang, Badong Chen

ICASSP 2024

Paper | arXiv | Code

* denotes equal contribution.

🏅 Honors and Awards

• National Scholarship, 2024
• Outstanding Undergraduate Thesis of College of Automation, Chongqing University, 2022
• National Scholarship, 2019
• Outstanding Student of Chongqing University, 2019