Xiaoman Lu

Xiaoman Lu is a PhD Candidate in the Department of Computer Science at the University of Warwick , under the supervision of Dr. Yu Guan. She is a member of Ubiquitous & Visual Computing Lab (UVLab).

Before joining UoW, she obtained her bachelor degree in Mathematics from the Northeastern University (China) in 2024.

Her work is at the intersection of computer graphics, machine learning, and information safety. In Xiaoman's research, she explores methods to implement deepfake detection, with a focus on developing effective, robust and generalised deepFakes detection algorithms.

Email  /  Google Scholar  /  Twitter  /  Github  /  Linkedin

profile photo

Publications

See a full-list of publication at my Google Scholar.

FairReL framework overview with Group-Conditional Wavelet Decorrelation and Subspace-Localised Mean Alignment FairReL: Deepfake Detection using Fairness-Aware Representation Learning
Xiaoman Lu, Jiaqi Li, Shuntian Zheng, Huiping Chen, Yu Guan
British Machine Vision Conference (BMVC), 2026 · Accepted
pdf / arXiv / Code / BibTeX
SemVID framework for frame-level budget allocation and semantic token selection Keeping the Evidence Chain: Semantic Evidence Allocation for Training-Free Token Pruning in Video Temporal Grounding
Jiaqi Li, Shuntian Zheng, Yixian Shen, Jia-Hong Huang, Xiaoman Lu, Minzhe Ni, Yu Guan
European Conference on Computer Vision (ECCV), 2026
pdf / arXiv / Code / Project / BibTeX
ActionVLM framework with language feature generation and debiasing feature aggregation Towards Mitigating Modality Bias in Vision-Language Models for Temporal Action Localization
Jiaqi Li, Guangming Wang, Shuntian Zheng, Minzhe Ni, Xiaoman Lu, Guanghui Ye, Yu Guan
Annual Meeting of the Association for Computational Linguistics (ACL), 2026
pdf / arXiv / Code / BibTeX
PULSE framework for spatial and Doppler tokenization, controlled motion prompting, and pose regression Doppler Prompting for Stable mmWave-based Human Pose Estimation
Shuntian Zheng, Jiaqi Li, Xiaoman Lu, Shuai He, Yu Guan
International Conference on Machine Learning (ICML), 2026
pdf / arXiv / Conference / Code / BibTeX
Paper 1 Image Facial image inpainting for big data using an effective attention mechanism and a convolutional neural network
Xiaoman Lu, Ran Lu, Wenhao Zhao, Erbin Ma
Frontiers in Neurorobotics, 2022
pdf / BibTeX

Teaching Experience

Invited Guest Lecture

Generalization and Fairness in Modern Deepfake Detection

Spring 2026 · CS355: Digital Forensics · University of Warwick

Misc.

During my free time, I enjoy travelling, photography.