π About Me
Hi there π , I'm Jiajun Liu (εεδΏ), a third-year undergraduate at Gaoling School of Artificial Intelligence, Renmin University of China.
My research interests lie in Spatial Intelligence, World Models, and Embodied AI.
Currently, I focus on robot learning from non-expert data under the supervision of Prof. Mengdi Xu at Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University.
I am proficient in Linux development, Python, C/C++, and PyTorch, and I actively contribute to open-source projects.
I am always open to collaborations, discussions, and new connections. Feel free to reach out!
π₯ News
- 2026.03 Two papers accepted to ICLR 2026 Workshops (World Models & Lifelong Agents)!
- 2026.02 New preprint: Geometry-Aware Rotary Position Embedding for Consistent Video World Model is available now!
- 2026.02 Bronze Medal at the 50-th ICPC East-Asia Continent Final (EC-Final) at Hangzhou.
- 2025.12 Awarded Most Potential Award at Open Source Promotion Plan (OSPP) 2025.
- 2025.09 Honored with National Scholarship (Top 0.4% Nationwide).
- 2025.05 Selected for the Tsinghua College of AI Undergraduate Academic Exchange Program as a sophomore.
π¬ Education & Experiences
Advisor: Guocai Yao, Sen Cui
Advisor: Mengdi Xu
Advisor: Manling Li
Advisor: Chongxuan Li, Jun Zhu
π Publications & Preprints
* denotes equal contribution.
π» 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.
π Selected Awards
- π₯ Silver Medal, International Collegiate Programming Contest (ICPC) East-Asia Continent Final Dec 2024
- π₯ Gold Medal, International Collegiate Programming Contest (ICPC) Asia Regional (Wuhan) Nov 2025
- π₯ Gold Medal, "Xiaomi Cup" China Collegiate Programming Contest (CCPC) Invitational Contest Apr 2025
- π₯ Silver Medal, 2024 CCF Collegiate Computer Systems & Programming Contest (CCSP) Oct 2024
- π Most Potential Award, Open Source Promotion Plan (OSPP) 2025 Dec 2025
π Scholarships
- π National Scholarship Sep 2025
- β¨ "Linghang" Intellectual Excellence Dean's Scholarship Dec 2024
- π Outstanding Student Leader Scholarship Sep 2024
- β¨ Third Prize Scholarship for Excellence in Social Work and Volunteering Sep 2025
π€ Services & Presentations
- Reviewer: ICLR 2026 Workshop on World Models
- 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
π― Interests & Hobbies
Last Updated: April, 2026