About Me

Hello!😊 I’m a third-year PhD candidate of The Chinese University of Hong Kong (CUHK) at Computer Science and Engineering, supervised by Prof. James Cheng. My research interests include Reinforcement Learning, Visual Language Model, GUI Agent and Machine Learning Theory.

On the application side, I am interested in building the efficient and effective Visual Language Models, especially in the GUI Agent field using a reinforcement learning approach. On the theory side, I have done research on graph neural networks and attention mechanism supervised by Dr. Yifei Wang at MIT CSAIL. I have also collaborated closely and happily with Dr. Xinyi Wu at MIT IDSS.

Prior to coming to CUHK, I was an undergraduate student at Harbin Institute of Technology, where I have done research intern at SCIR, supervised by Prof. Libo Qin.

If you are seeking any form of academic cooperation, please feel free to email me at wjqkoko@gmail.com.

If you like the template of this homepage, welcome to star and fork Yi Ren’s open-sourced template version AcadHomepage .

🔥 News

• 2025.09: 🎉 Our three papers are accepted by NeurIPS 2025.
• 2025.08: 🎉 Our MLMT is accepted by 2025 IEEE ASRU.
• 2025.05: 🎉 Our TON is accepted by ICML 2025 EXAIT Workshop.
• 2025.04: 🎉 Our PIGDreamer is accepted by ICML 2025.
• 2025.02: 🎉 Our DivIL is accepted by TMLR 2025.
• 2024.09: 🎉 Our Reasoning Boundary is accepted by NeurIPS 2024 (Oral).
• 2024.03: 🎉 Our MISTS is accepted by AAAI 2024 (Oral) .

📝 Publications

† indicates equal contribution.

2025

	Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models Jiaqi Wang†, Kevin QH. Lin†, James Cheng, Mike Z. Shou. NeurIPS, ICML EXAIT Workshop [paper] [code] [huggingface]
	A Signed Graph Approach to Understanding and Mitigating Oversmoothing in GNNs Jiaqi Wang†, Xinyi Wu†, James Cheng, Yifei Wang. NeurIPS [paper]
	Visual Thoughts: A Unified Perspective of Understanding Multimodal Chain-of-Thought Zihui Cheng, Qiguang Chen, Xiao Xu, Jiaqi Wang, Weiyun Wang, Hao Fei, Yidong Wang, Alex Jinpeng Wang, Zhi Chen, Wanxiang Che, Libo Qin. NeurIPS [paper]
	Enhancing Multilingual Speech Generation and Recognition Abilities in LLMs with Constructed Code-switched Data Jing Xu, Daxin Tan, Jiaqi Wang, Xiao Chen. IEEE ASRU [paper]
	PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning Dongchi Huang, Jiaqi Wang, Yang Li, Chunhe Xia, Tianle Zhang, Kaige Zhang. ICML [paper] [code]
	DivIL: Unveiling and Addressing Over-Invariance for Out-of-Distribution Generalization Jiaqi Wang†, Yuhang Zhou†, Zhixiong Zhang†, Qiguang Chen, Yongqiang Chen, James Cheng. TMLR [paper] [code]

2024

	Unlocking the capabilities of thought: A reasoning boundary framework to quantify and optimize chain-of-thought Qiguang Chen, Libo Qin, Jiaqi Wang, Jingxuan Zhou, Wanxiang Che. NeurIPS, Oral [paper] [code]
	Enhancing evolving domain generalization through dynamic latent representations Binghui Xie, Yongqiang Chen, Jiaqi Wang, Kaiwen Zhou, Bo Han, Wei Meng, James Cheng. AAAI, Oral [paper]