Maoqi Liu「刘茂琦」

Graduate Student @ BUPT · Research Intern @ ByteDance Data

I am a first-year graduate student at the School of Artificial Intelligence, Beijing University of Posts and Telecommunications, advised by Prof. Fang Quan in the MKC Group. Currently, I am also a Research Intern at ByteDance Data, mentored by He Junwei.

My research interests broadly center on Post-Training and Continual Learning. I am dedicated to exploring alignment algorithms, scalable reinforcement learning, and foundation models that continuously acquire new knowledge and reason robustly.

GitHub OpenReview Email CV

News

All news
Oct 2026
Paper
New preprint ProRubric is now on arXiv, with code on GitHub! 🚀
Sep 2026
Paper
One paper accepted by EMNLP 2026! 🎉🎉🎉 Check out the preprint on arXiv and code on GitHub.
Nov 2025
Paper
One paper accepted by Advanced Engineering Informatics! 🎉🎉🎉
Nov 2025
Paper
One paper accepted by AAAI 2026! 🎉🎉🎉

Selected Publications

All publications
  1. prorubric.png
    Preprint arXiv Code
    Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics
    Maoqi Liu, Junwei He, Bowen Zhang, and 5 more authors
    arXiv preprint arXiv:2609.38847, 2026
  2. code-lora.png
    EMNLP 2026 arXiv Code
    CoDe-LoRA: Mitigating the Orthogonality Dilemma in Continual Learning of LLMs via Knowledge Consolidation and Decoupling
    Maoqi Liu, Quan Fang, and Yufei He
    Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, 2026
  3. notam-evolve.png
    AAAI 2026 arXiv Code
    NOTAM-Evolve: A Knowledge-Guided Self-Evolving Optimization Framework with LLMs for NOTAM Interpretation
    Maoqi Liu, Quan Fang, Yuhao Wu, and 3 more authors
    Proceedings of the AAAI Conference on Artificial Intelligence, 2026
  4. knots.png
    ADVEI 2025 arXiv Code
    Knots: A Large-Scale Multi-Agent Enhanced Expert-Annotated Dataset and LLM Prompt Optimization for NOTAM Semantic Parsing
    Maoqi Liu, Quan Fang, Yang Yang, and 2 more authors
    Advanced Engineering Informatics, 2025

Honors & Awards

2024
Beijing Natural Science Foundation Undergraduate "QiYan" Research Grant.

Experience

2026.06 - Present
Research Intern @ ByteDance Data, mentored by He Junwei.