Biography

Hi, I am Yubo Dong, a Master’s student at the College of Computer Science and Technology, Zhejiang University (2023–2028), where I am advised by Prof. Yi Yang.

My research primarily focuses on advancing Large Language Models (LLMs), with a strong emphasis on Multi-Agent Systems, structured reasoning, and model efficiency. I am passionate about building AI systems that can collaborate, reason efficiently, and solve highly complex dependencies—ranging from autonomous agents in Minecraft to highly efficient video diffusion models and hierarchical token pruning.

Research Interests

  • Multi-Agent Systems (LLMs): Graph-based coordination, agent collaboration, and benchmarking.
  • Reasoning & Generation: Structured reasoning frameworks to enhance LLM capabilities and explainability.
  • Efficiency & Acceleration: Token pruning, temporal compression, and efficient video diffusion generation.

Education

  • M.S. in Computer Science and Technology Zhejiang University | 2023 – 2026
    Advisor: Prof. Yi Yang

Publications & Preprints

  • Super Research: Answering Highly Complex Questions with Large Language Models though Super Deep and Super Wide Research Yubo Dong, Nianhao You, Yuxuan Hou, Zixun Sun, Yue Zhang, LiangZhang, Siyuan Zhao, Wu Xinyue, Junle Li, Hehe Fan
    ICML 2026 Conference Submission

  • Structured Reasoning for LLMs: A Unified Framework for Efficiency and Explainability Yubo Dong, Hehe Fan, Linchao Zhu, Yi Yang
    ICLR 2026 (Poster)

  • Hi-Lo Prune: Look at What You’ll Lose before Pruning with Hierarchical Token Selection Yubo Dong, Zixun Sun, Hehe Fan, Yi Yang
    CVPR 2026 Conference Submission

  • Enhancing Large Language Models through Structured Reasoning Yubo Dong, Hehe Fan, Yi Yang
    Submitted to NeurIPS 2025

  • MTC-VAE: Multi-Level Temporal Compression with Content Awareness Yubo Dong, Linchao Zhu, Yi Yang
    arxiv

  • VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in Minecraft Yubo Dong, Xukun Zhu, Zhengzhe Pan, Linchao Zhu, Yi Yang
    ACL 2024 (Findings)

Contact