Publications and Preprints

2025

• Controllable Biophysical Human Faces.
  Minghao Liu, Stephane Grabli, Sébastien Speierer, Nikolaos Sarafianos, Lukas Bode, Matt Jen-Yuan Chiang, Christophe Hery, James Davis, Carlos Aliaga
  EGSR 2025 (Computer Graphics Forum track)
  [paper coming soon] [Category: Biophysical face modeling]

• Human and AI perceptual differences in image classification errors.
  Minghao Liu, Jiaheng Wei, James Davis, and Yang Liu.
  AAAI Conference on Artificial Intelligence, 2025 Oral Presentation (4.6% acceptance rate)
  [paper] [Video] [Category: Human-machine perceptual differences]

2024

• A survey on human-ai teaming with large pre-trained models.
  V Vats, MB Nizam, Minghao Liu, Z Wang, R Ho, MS Prasad, V Titterton, et al.
  arXiv preprint arXiv:2403.04931, 2024
  [paper] [Category: Human-AI collaboration survey]

• Automatic dataset construction (adc): Sample collection, data curation, and beyond.
  Minghao Liu, Z Di, J Wei, Z Wang, H Zhang, R Xiao, H Wang, J Pang, H Chen, et al.
  arXiv preprint arXiv:2408.11338, 2024
  [paper] [Category: Dataset construction methodology]

2023

• Assessing the impact of prompting, persona, and chain of thought methods on chatgpt’s arithmetic capabilities.
  Y Chen, C Wong, H Yang, J Aguenza, S Bhujangari, B Vu, X Lei, Minghao Liu, et al.
  arXiv preprint arXiv:2312.15006, 2023
  [paper] [Category: LLM evaluation]

• Tag-Based Annotation for Avatar Face Creation.
  A Ngo, D Phelps, D Lai, T Wong, L Mathias, A Shivamurthy, M Ajmal, Minghao Liu, et al.
  arXiv preprint arXiv:2308.12642, 2023
  [paper] [Category: Avatar annotation system]

• Tag-based annotation creates better avatars.
  Minghao Liu, Zeyu Cheng, Shen Sang, Jing Liu, James Davis
  arXiv preprint arXiv:2302.07354, 2023
  [paper] [Category: Avatar creation methodology]

2022

• AgileAvatar: Stylized 3D Avatar Creation via Cascaded Domain Bridging.
  Shen Sang, Tiancheng Zhi, Guoxian Song, Minghao Liu, Chunpong Lai, Jing Liu, Linjie Luo, Xiang Wen, and James Davis.
  SIGGRAPH Asia – ACM SIGGRAPH Conference and Exhibition on Computer Graphics and Interactive Techniques in Asia, 2022
  [paper] [Category: Self-supervised avatar creation model]

• DuelGAN: A Duel between Two Discriminators Stabilizes the GAN Training.
  Jiaheng Wei*, Minghao Liu*, Jiahao Luo, Andrew Zhu, James Davis, Yang Liu
  ECCV – European Conference on Computer Vision, 2022
  [paper] [Category: Deep Generative Models]

• How much does input data type impact final face model accuracy?
  Jiahao Luo, Fahim Khan, Issei Mori, Akila de Silva, Eric Sandoval Ruezga, Minghao Liu, Alex Pang, and James Davis.
  CVPR – The IEEE / CVF Computer Vision and Pattern Recognition Conference, 2022
  [paper] [Category: 3D face modeling]

• Low-light Image Enhancement Using Chain-consistent Adversarial Networks.
  Minghao Liu*, Jiahao Luo, Xiaohan Zhang, Yang Liu, and James Davis
  ICPR – 26TH International Conference on Pattern Recognition, 2022
  [paper] [Category: Self-supervised Generative Models]

(*: denotes equal contributions)