About Me

I am a master's student in the School of Automation Science and Engineering at Xi'an Jiaotong University, China, and a member of the research group led by Prof. Feng Lian. Prior to this, I received my B.E. degree from Xi'an Jiaotong University, China.

My current research interests include native multimodal large language models, representation learning, and world models. More broadly, I am interested in understanding how we should define the fundamental questions behind intelligence, and how such questions can guide us toward building truly intelligent models with richer perception, reasoning, memory, and world understanding.

I am always happy to connect and collaborate 😆. If you are interested in discussing research questions, exploring potential collaborations, or offering suggestions, please feel free to reach out to me via email anytime.

Education

Sept. 2024 - Present

Xi'an Jiaotong University

M.Eng. Student, Control Science and Engineering

Sept. 2020 - Jul. 2024

Xi'an Jiaotong University

B.Eng. Student, Automation Science and Engineering

News

  • Jun. 2026: Started as an AI Model Engineer intern in the Foundation Model Department at Huawei, working on multimodal large language models.
  • 2025: Received Excellent Graduate Student, Top Grade Scholarship, and Baotong Scholarship.
  • Sept. 2025: Completed HA-PointAE for airfoil generation and aerodynamic shape optimization.

Publications

Research Interests

  • Native multimodal large language models
  • World models
  • Representation learning

Research Experience

  • Oct. 2025 - Apr. 2026: Explored new architectures for latent-space prediction in large language models.
  • Nov. 2025 - Mar. 2026: JEPA Alignment for Detailed Perception in Multimodal LLMs. Designed a JEPA alignment scheme for TextVQA and improved TextVQA accuracy from 79.3% to 81.65%.
  • Sept. 2024 - Sept. 2025: HA-PointAE for Airfoil Generation and Aerodynamic Shape Optimization. Proposed a PointNet-based autoencoder with SCA encoder blocks and an AttenRes decoder.

Selected Honors and Awards

  • Oct. 2025: Excellent Graduate Student, Top Grade Scholarship, and Baotong Scholarship
  • Jul. 2025: Regional 2nd Prize, China Graduate Electronics Design Contest; Team Leader
  • Jun. 2025: National 2nd Prize, MathorCup Mathematical Contest in Modeling; Team Leader; ranked in the top 5%
  • Jan. 2025: National 1st Prize, Asia and Pacific Mathematical Contest in Modeling; Team Leader; ranked in the top 5%
  • Dec. 2024: National 2nd Prize, China Post-Graduate Mathematical Contest in Modeling; Team Leader; ranked in the top 1.5%

Internship

Jun. 2026 - Present: Huawei, Foundation Model Department, Shanghai, China. AI Model Engineer intern working on native multimodal large language models and unified MLLM frameworks.

Patent

Sept. 2023: "Home-Based Attention Training System Using EEG Feedback", CN116764065A, authorized. Xu J, Wu M, Yu Q, Zhou Y, Pu J, An B, Wang Y, Li X.