I am currently a first-year Ph.D. student at The Hong Kong University of Science and Technology (Guangzhou), where I am fortunate to be advised by Prof. Chengwei Qin. Before joining HKUST(GZ), I obtained my B.S. degree in Automation from Xiamen University. During my research internship at MiroMind.ai, I had the privilege of working closely with Dr. Lidong Bing and Dr. Xingxuan Li, an experience that greatly shaped my research perspective. My research interests lie at the intersection of computer vision and natural language processing. Specifically, I focus on Multimodal Large Language Models (MLLMs), with a particular emphasis on interpretability, complex reasoning, and agentic tool use. My goal is to build more transparent and capable AI systems that can effectively reason through real-world tasks.

🔍 I am currently looking for research internship opportunities on LLM/MLLM post-training, with a focus on RLVR, agentic tool use, and on-policy distillation (OPD). If you have a relevant opening, please feel free to reach out via email — I’d be happy to chat!

News

• 2026.05 - One paper was accepted by ICML 2026.
• 2026.02 - One paper was accepted by CVPR 2026.
• 2025.06 - One paper was accepted by ICCV 2025.
• 2025.03 - One paper was accepted by CVPR 2025.

Publications

_{(* denotes equal contribution)}

• LongVT: Incentivizing “Thinking with Long Videos” via Native Tool Calling [Paper] [Project Page] [Code] [HF Daily]
  Zuhao Yang*, Sudong Wang*, Kaichen Zhang*, Keming Wu, Sicong Leng, Yifan Zhang, Bo Li, Chengwei Qin, Shijian Lu, Xingxuan Li, Lidong Bing
  CVPR 2026  ·  🤗 #2 Paper of the Day on Hugging Face

• Resource-Efficient Reinforcement for Reasoning Large Language Models via Dynamic One-Shot Policy Refinement [Paper]
  Yunjian Zhang*, Sudong Wang*, Yang Li, Peiran Xu, Conghao Zhou, Xiaoyue Ma, Jianing Li, Yao Zhu
  ICML 2026

• PRISM: Beyond SFT-to-RL — Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL [Paper] [Project Page] [Code] [HF Daily]
  Sudong Wang, Weiquan Huang, Xiaomin Yu, Zuhao Yang, Hehai Lin, Keming Wu, Chaojun Xiao, Chen Chen, Wenxuan Wang, Beier Zhu, Yunjian Zhang, Chengwei Qin
  arXiv preprint  ·  🤗 #3 Paper of the Day on Hugging Face

• SHIFT: Smoothing Hallucinations by Information Flow Tuning for Multimodal Large Language Models [Paper]
  Sudong Wang, Yunjian Zhang, Yao Zhu, Enci Liu, Jianing Li, Yanwei Liu, Xiangyang Ji
  ICCV 2025

• Towards Understanding How Knowledge Evolves in Large Vision-Language Models [Paper] [Code]
  Sudong Wang, Yunjian Zhang, Yao Zhu, Jianing Li, Zizhe Wang, Yanwei Liu, Xiangyang Ji
  CVPR 2025

Co-authored Work

• SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognition [Paper]
  Peiran Xu, Sudong Wang, Yao Zhu, Jianing Li, Gege Qi, Yunjian Zhang
  arXiv preprint

• Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling [Paper]
  Keming Wu, Zuhao Yang, Kaichen Zhang, Shizun Wang, Haowei Zhu, Sicong Leng, Zhongyu Yang, Qijie Wang, Sudong Wang, et al.
  arXiv preprint

• Interactive Learning for LLM Reasoning [Paper]
  Hehai Lin, Shilei Cao, Sudong Wang, Haotian Wu, Minzhi Li, Linyi Yang, Juepeng Zheng, Chengwei Qin
  ACL 2026 Findings

• AMA: Adaptive Memory via Multi-Agent Collaboration [Paper]
  Weiquan Huang, Zixuan Wang, Hehai Lin, Sudong Wang, Bo Xu, Qian Li, Beier Zhu, Linyi Yang, Chengwei Qin
  ACL 2026 Findings

• Unified-MAS: Universally Generating Domain-Specific Nodes for Empowering Automatic Multi-Agent Systems [Paper]
  Hehai Lin, Yu Yan, Zixuan Wang, Bo Xu, Sudong Wang, Weiquan Huang, Ruochen Zhao, Minzhi Li, Chengwei Qin
  arXiv preprint

• Training Multi-Turn Search Agent via Contrastive Dynamic Branch Sampling [Paper]
  Yubao Zhao, Weiquan Huang, Sudong Wang, Ruochen Zhao, Chen Chen, Yao Shu, Chengwei Qin
  arXiv preprint

Educational Background

• 2025.08 - Present: Doctor of Philosophy, Thrust of Artificial Intelligence, Hong Kong University of Science and Technology (Guangzhou)
• 2024.08 - 2025.06: Master in Computer Control and Automation, School of Electrical and Electronic Engineering, Nanyang Technological University
• 2020.09 - 2024.06: Bachelor in Automation, College of Aeronautics and Astronautics, Xiamen University

🧑‍⚖️ Working Experiences

• 2025.06 - 2026.02: AI Scientist Intern, Shanda AI Research Institute & MiroMind.ai, Singapore
• 2024.03 - 2024.11: AI Research Intern, Qiyuan National Lab