My name is Tangzheng Lian, and I am currently a final-year PhD candidate in the Social AI & Robotics Lab (SAIR), led by Dr. Oya Celiktutan, in the Department of Engineering at King’s College London. I am fortunate to be fully funded by the competitive Natural, Mathematical & Engineering Sciences (NMES) Faculty PhD Studentship at King’s. During my PhD, I have also had the opportunity to work with Dr Dimitrios Kollias at Queen Mary University of London (QMUL). My research interests include Trustworthy/Responsible AI, Algorithmic Fairness, Out-of-Distribution (OOD) Generalization, Vision-Language Models (VLMs), and Affective Computing.

Prior to King’s, I was a Research Assistant at the Computing and Informatics Research Center (CIRC) at Nottingham Trent University, where I worked with Dr. Doratha Vinkemeier. I completed my MSc in Computer Science (Distinction) at the University of Birmingham and a BEng in Telecommunication Engineering at Beijing University of Posts and Telecommunications (BUPT).

I am always keen to discuss exciting ideas in broader CV/ML topics. If you work on similar topics and would like to connect and collaborate, feel free to drop me an email for a chat online or in person (London).

News

2026-06
✈️ Traveled to Paris to attend CVPR@Paris and present my poster.
2026-05
✈️ Traveled to Kyoto to attend FG and present my poster.
2026-04
🎯 One first-author paper was accepted at IEEE International Conference on Automatic Face and Gesture Recognition (FG) 2026!
2026-02
🎯 One first-author paper was accepted at CVPR 2026!
2026-01
🎯 One first-author paper was accepted at IEEE Transactions on Affective Computing!
2026-01
🗣️ I gave an oral presentation at AAAI 2026 in Singapore (available online).
2025-11
🏆 One first-author paper was accepted at AAAI as an Oral presentation!
2025-07
🗣️ I gave an invited talk at the BMVA Symposium on AI Security in London (video online).
2023-11
✈️ Traveled to Aberdeen to attend BMVC and present my poster.
2023-07
🎯 My first first-authored paper was accepted at BMVC 2023!
2023-06
🚀 Thrilled to start my PhD at King’s College London in the Social AI & Robotics Lab (SAIR), fully funded by the NMES scholarship!

Featured Publications

A Closed-Form Solution for Debiasing Vision-Language Models with Utility Guarantees Across Modalities and Tasks
Authors: Tangzheng Lian, Guanyu Hu, Yijing Ren, Dimitrios Kollias, Oya Celiktutan
Status: In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026.
Keywords: Fairness, VLM, Debiasing
Paper · Code
Fair Domain Generalization: An Information-Theoretic View
Authors: Tangzheng Lian, Guanyu Hu, Dimitrios Kollias, Xinyu Yang, Oya Celiktutan
Status: In Proceedings of the AAAI Conference on Artificial Intelligence (Oral Presentation), 2026.
Keywords: Domain Generalization, Fairness, OOD
Paper · Code
A Feature-level Framework for Evaluating Demographic Biases in Facial Expression Recognition Models
Authors: Tangzheng Lian, Oya Celiktutan
Status: IEEE Transactions on Affective Computing, 2026.
Keywords: Affective Computing, Demographic Bias, FER
Paper · Code
Towards Pareto Efficiency in Fair Facial Expression and Action Unit Recognition
Authors: Tangzheng Lian, Oya Celiktutan
Status: In Proceedings of the IEEE International Conference on Automatic Face and Gesture Recognition (FG), 2026.
Keywords: Fairness, Pareto Optimization, FER, Action Units
Paper · Code
Supervised Contrastive Learning with Identity-Label Embeddings for Facial Action Unit Recognition
Authors: Tangzheng Lian, David Adama, Pedro Machado, Doratha Vinkemeier
Status: In Proceedings of the British Machine Vision Conference (BMVC), 2023.
Keywords: Contrastive Learning, Facial Action Units
Paper · Code
Attention-guided Soft Ranking Loss for Resource-constrained Head Pose Estimation
Authors: Wenqi Xu, Tangzheng Lian, Wei Liu, Kaili Zhao
Status: In Proceedings of the IEEE International Conference on Network Intelligence and Digital Content (IC-NIDC), 2021.
Keywords: Head Pose Estimation, Lightweight Models
Paper · Code
Causalaffect: Causal discovery for facial affective understanding
Authors: Guanyu Hu, Tangzheng Lian, Dimitrios Kollias, Oya Celiktutan, Xinyu Yang
Status: arXiv preprint, 2025
Keywords: Causal Discovery, Affective Computing, Facial Analysis
Paper · Code
Fairmt: Fairness for heterogeneous multi-task learning
Authors: Guanyu Hu, Tangzheng Lian, Na Yan, Dimitrios Kollias, Xinyu Yang, Oya Celiktutan, Siyang Song, Zeyu Fu
Status: arXiv preprint, 2025
Keywords: Fairness, Multi-task Learning, Optimization
Paper · Code

Teaching Assistant

Sensing and Perception - King’s College London
Spring 2024
Engineering Mathematics - King’s College London
Fall 2023
Applied Maths and Graphics - Nottingham Trent University
Spring 2023

Professional Services

Conference Reviewer
CVPR, AAAI, WACV, BMVC
Journal Reviewer
IEEE Transactions on Affective Computing; IEEE Transactions on Big Data