|
I am an MPhil student at the Hong Kong University of Science and Technology (HKUST), Guangzhou, where I am advised by Prof. Hui Xiong (IEEE, ACM, AAAI, AAAS and CCF Fellow) in the AI+ Lab. My second supervisor is Prof. Haoang Li. I received my bachelor's degree from the School of Artificial Intelligence and Automation, Huazhong University of Science and Technology (HUST AIA). I have conducted research at the VDI Center of ShanghaiTech University, working with Prof. Jingyi Yu and Yuexin Ma. I also work with Prof. Zhiyuan Ma at HUST. Previously, I was a research intern at Shanghai AI Lab, working with the AI Bench team led by Prof. Guangtao Zhai. I will join WeChat Group as an incoming research intern in July 2026. My research interests lie broadly in 3D vision, multimodal large language models, generative world models, and their applications to embodied intelligence and robotics. My long-term goal is to develop generalizable intelligent agents that can perceive, reason about, and interact with the physical world. [Note] I am actively seeking Fall 2027 CS Ph.D. opportunities. |
Contact me: wanghanqing0424@gmail.com |
RedNote / Google Scholar / Github
RedNote
|
merged in 
!!!
|
AIBench Team@ShangHai AI Lab Zicheng Zhang, Junying Wang, Yijin Guo, Farong Wen, Zijian Chen, Paper / Project Display, JCR Q1, CAS Q2, 2025 We present AIBench, a flexible and rapidly updating platform that aggregates evaluation results from commercial platforms, popular open-source leaderboards, and internal evaluation benchmarks. |
|
Founder & Project Leader Project page We offers a comprehensive and up-to-date collection of research papers on Affordance Learning. |
|
Contributor Project page Embodied-AI-Guide |
|
My research interest is broadly in MLLMs Generative World Models, 3D Computer Vision, and their application in Robotics currently. My primary objective is to develop an intelligent agent endowed with robust, generalizable capabilities to perceive and interact with the real world. Representative works are highlighted. |
|
|
|
|
(*equal contribution) Arxiv / Project / Code / ECCV 2026 We unleash the powerful affordance knowledge within the diffusion model for 3D affordance grounding. |
|
Zixin Zhang*, Kanghao Chen*, Arxiv / Project / Code ECCV 2026 |
|
Yifan Han, Pengfei Yi, Junyan Li, Arxiv IROS 2026 |
|
(*equal contribution) Arxiv / Project / Code AAAI 2026, Oral We introduce Affordance-R1, which is capable of generating explicit reasoning alongside the final answer. With the help of the proposed affordance reasoning reward, it achieves robust zero-shot generalization and exhibits emergent test-time reasoning capabilities. |
|
Chulin Yu*, (*equal contribution) Paper / Project / Code CVPR, 2025 We endow MLLM with Sequential Affordance Reasoning ability which is significant for Embodied-AI |
|
|
|
|
Arxiv / Code AAAI 2026 We design a dynamic evaluation protocol for MLLM safety evaluation. |
|
Jiahao Yuan, Zhiqing Cui, Arxiv / Code WWW 2026 |
|
Zhiqing Cui*, Jiahao Yuan*, Paper / Code ACM MM, 2025 Oral We introduce DWT, a training free framework for MLLMs to perform awesome scientific diagram generation |
|
|
|
|
|
|
This template is a modification to Yiran Geng's and Jon Barron's website. |