Jiajun Liu

Jiajun Liu

Undergraduate at Renmin University | GPA: 3.87 / 4.00 (Rank 3 / 58)

πŸ™‹ About Me

Hi there πŸ‘‹ , I'm Jiajun Liu (εˆ˜ε˜‰δΏŠ), a third-year undergraduate at Gaoling School of Artificial Intelligence, Renmin University of China.

My research interests lie in Spatial Intelligence, World Model, and Embodied AI.

I am proficient in Linux development, Python, C/C++, and PyTorch. I am an active open-source contributor.

I am always open to collaborations, discussions, and making new friends. Feel free to reach out!

πŸ”¬ Research Experience

Research Intern, Xu-Lab, Tsinghua IIIS & Qizhi Institute, China
Oct 2025 - Present

Advisor: Mengdi Xu

Topic: In-context robot learning.

Research Intern, MLL-Lab, Northwestern University, USA
Jun 2025 - Sep 2025

Advisor: Manling Li

Topic: VLM agents with tool-use for active novel-view synthesis on spatial intelligence tasks, in collaboration with Microsoft.

Research Intern, GSAI-ML Group, Renmin University, China
Jan 2025 - Aug 2025

Advisor: Chongxuan Li

Topic: 3D world model for explorable scene generation from a single image or text prompt.

πŸ“ Publications & Preprints

Sorted by recency. * denotes equal contribution.

ViewRoPE
Geometry-Aware Rotary Position Embedding for Consistent Video World Model
Chendong Xiang*, Jiajun Liu*, Jintao Zhang*, Xiao Yang, Zhengwei Fang, Shizun Wang, Zijun Wang, Yingtian Zou, Hang Su, Jun Zhu
Preprint
Embodied Reasoner
Embodied Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks
Wenqi Zhang*, Mengna Wang*, Gangao Liu, Huixin Xu, Yiwei Jiang, Yongliang Shen, Guiyang Hou, Zhe Zheng, Hang Zhang, Xin Li, Jiajun Liu, Weiming Lu, Peng Li, Yueting Zhuang
Preprint

πŸ’» Selected Open-Source Projects

Embodied Reasoner (With OSPP's funding)

Main Contributor

Embodied-Reasoner (ER.) is a multimodal model designed for deep reasoning and long-horizon interaction. Through OSPP, similar to GSoC, I was selected by the AGIROS Community as the contributor responsible for ER. I took charge of benchmarking ER. on ALFRED and contributed to resolving two key bottlenecks: ambiguity in distinguishing identical object instances and imprecise targeting of large objects, thereby improving spatial accuracy and interaction robustness.

RAGEN & VAGEN: Training Agents by Reinforcing Reasoning

Contributor

This twin of projects empower agents with RL to operate effectively in interactive and stochastic environments by handling multi-turn interactions and environmental uncertainty. I contributed to developing more environments and mask functions to compute the loss only for the parts generated by the model, which actually made training more stable.

πŸ† Selected Awards

  • πŸ₯ˆ Silver Medal, International Collegiate Programming Contest (ICPC) East-Asia Continent Final Dec 2024
  • πŸ₯‡ Gold Medal, International Collegiate Programming Contest (ICPC) Asia Regional (Wuhan) Nov 2025
  • πŸ₯‡ Gold Medal, "Xiaomi Cup" China Collegiate Programming Contest (CCPC) Invitational Contest Apr 2025
  • πŸ₯ˆ Silver Medal, 2024 CCF Collegiate Computer Systems & Programming Contest (CCSP) Oct 2024
  • πŸ… Most Potential Award, Open Source Promotion Plan (OSPP) 2025 Dec 2025

πŸŽ“ Scholarships

  • 🌟 National Scholarship Sep 2025
  • ✨ "Linghang" Intellectual Excellence Dean's Scholarship Dec 2024
  • 🌟 Outstanding Student Leader Scholarship Sep 2024
  • ✨ Third Prize Scholarship for Excellence in Social Work and Volunteering Sep 2025

🎀 Services & Presentations

  • Reviewer: ICLR 2026 World Models Workshop
  • Video: "My Experience Using AI+ Tools to Create Videos"
    Invited by CCF for China National Computer Conference (CNCC) Super Forum
  • Talk: "Algorithm and Artificial Intelligence"
    Invited by Gaoling School of AI & School of Information, Renmin University of China

🎯 Interests & Hobbies

Last Updated: February, 2026