Columbia University in the City of New York
M.S. in Computer Engineering
ql2505(at)columbia.edu
Education
Visitors
I am Qingyuan Liu (刘庆远), a research assistant at the UCLA NLP Lab, advised by Prof. Violet Peng. Previously, I received my M.S. in Computer Engineering at Columbia University in the City of New York in May 2025 and B.E. in Computer Science and Technology from Huazhong University of Science and Technology in 2023. I am working closely with Jiachen Gu and Yunzhi Yao.
I study knowledge mechanisms and editing for agentic systems, with a focus on how knowledge evolves and interacts for LLMs, and how to design effective methods for memory/reasoning manipulation. Learn more about my research here.
Research keywords include: lifelong learning, model editing, agentic systems.
Warning
Problem: The current name of your GitHub Pages repository ("Solution: Please consider renaming the repository to "
http://".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}" in index.html.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "News
Research Highlights
Energy-Regularized Sequential Model Editing on Hyperspheres
Qingyuan Liu*, Jiachen Gu*, Yunzhi Yao, Hong Wang, Nanyun Peng
In The Fourteenth International Conference on Learning Representations (ICLR). 2026.
Top-1.1% in Transfer/Meta/Lifelong Learning track
[TL;DR] [Paper] [Code] [EasyEdit] [Project Page]
Developed SPHERE (Sparse Projection for Hyperspherical Energy-Regularized Editing), projecting new knowledge onto sparse hyperspherical subspaces to preserve uniformity and editing stability with rigorous proof, achieving +16.4% higher editing capability while best preserving general performance on LLaMA3-8B and Qwen2.5-7B.
# Model Editing # Knowledge Mechanisms # Lifelong Learning
Energy-Regularized Sequential Model Editing on Hyperspheres
Qingyuan Liu*, Jiachen Gu*, Yunzhi Yao, Hong Wang, Nanyun Peng
In The Fourteenth International Conference on Learning Representations (ICLR). 2026.
Top-1.1% in Transfer/Meta/Lifelong Learning track
[TL;DR] [Paper] [Code] [EasyEdit] [Project Page]
Developed SPHERE (Sparse Projection for Hyperspherical Energy-Regularized Editing), projecting new knowledge onto sparse hyperspherical subspaces to preserve uniformity and editing stability with rigorous proof, achieving +16.4% higher editing capability while best preserving general performance on LLaMA3-8B and Qwen2.5-7B.
# Model Editing # Knowledge Mechanisms # Lifelong Learning
Turns Out I’m Not Real: Towards Robust Detection of AI-Generated Videos
Qingyuan Liu, Pengyuan Shi, Yun-Yun Tsai, Chengzhi Mao, Junfeng Yang
IEEE / CVF Computer Vision and Pattern Recognition Conference, GenAI Workshop. 2024
Columbia Engineering Research Highlight
Developed a Diffusion Reconstruction Error (DIRE) method for AI-generated video detection, leveraging video generation models with temporal cues to achieve up to 93.7% accuracy on Stable Video Diffusion, Sora, Pika, and Gen-2 datasets.
# AI-Synthetic
Turns Out I’m Not Real: Towards Robust Detection of AI-Generated Videos
Qingyuan Liu, Pengyuan Shi, Yun-Yun Tsai, Chengzhi Mao, Junfeng Yang
IEEE / CVF Computer Vision and Pattern Recognition Conference, GenAI Workshop. 2024
Columbia Engineering Research Highlight
Developed a Diffusion Reconstruction Error (DIRE) method for AI-generated video detection, leveraging video generation models with temporal cues to achieve up to 93.7% accuracy on Stable Video Diffusion, Sora, Pika, and Gen-2 datasets.
# AI-Synthetic