I obtained my M.Phil. and B.Eng. degrees from The University of Hong Kong, where I worked on open-world visual concepts and representation learning with Kai Han at Visual AI Lab.
News
Apr 2026One paper about category discovery with part-level correspondence priors has been accepted to ICML 2026.
Mar 2026Obtained my M.Phil. degree at The University of Hong Kong.
Jan 2026Started my research internship at NVIDIA.
Jun 2025Our work ICE, CVPR 2025 was featured by HKU Graduate School News Letter, Awards & Achievements.
Feb 2025One paper about concept learning with diffusion models has been accepted to CVPR 2025 as Highlight.
Jul 2024One paper about continual category discovery has been accepted to ECCV 2024.
Oct 2023Honored to receive the Excellent Research Award from my department.
Jun 2023Our CVPR 2023 work was featured by RSIP Vision Magazine.
Feb 2023One paper about heterogeneous graph representation learning has been accepted to CVPR 2023.
Dec 2022One paper about 3D representation learning has been accepted to NeurIPS Workshop 2022.
Publications
* denotes equal contribution
Open-World Visual Concept Discovery and Extraction
@mastersthesis{cendra2026mphil,
author = {Fernando Julio Cendra},
title = {Open-World Visual Concept Discovery and Extraction},
school = {The University of Hong Kong},
year = {2026},
}
@inproceedings{Cendra2026PartCo,
author = {Fernando Julio Cendra and Kai Han},
title = {PartCo: Part-Level Correspondence Priors Enhance Category Discovery},
booktitle = {International Conference on Machine Learning (ICML)},
year = {2026},
}
Can Bayesian Optimization Efficiently Find a Strong Single Expert in Neural Thickets?
Nigel Bastian Cendra, Abdelhamid Ezzerg, Fernando Julio Cendra, Jeremias Knoblauch and Jakob Zeitler
@article{Cendra2026BO,
author = {Nigel Bastian Cendra and Abdelhamid Ezzerg and Fernando Julio Cendra and Jeremias Knoblauch and Jakob Zeitler},
title = {Can Bayesian Optimization Efficiently Find a Strong Single Expert in Neural Thickets?},
journal = {arXiv preprint arXiv:2608.10867},
year = {2026},
}
Effective Prompt Pool Learning for Continual Category Discovery
Fernando Julio Cendra, Xinghui Li and Kai Han
arXiv preprint 2026(extended version of PromptCCD)
@article{Cendra2026PromptPool,
author = {Fernando Julio Cendra and Xinghui Li and Kai Han},
title = {Effective Prompt Pool Learning for Continual Category Discovery},
journal = {arXiv preprint arXiv:2407.19001},
year = {2026},
}
@inproceedings{Cendra2024promptccd,
author = {Fernando Julio Cendra and Bingchen Zhao and Kai Han},
title = {PromptCCD: Learning Gaussian Mixture Prompt Pool for Continual Category Discovery},
booktitle = {European Conference on Computer Vision (ECCV)},
year = {2024}
}
ICE: Intrinsic Concept Extraction from a Single Image via Diffusion Models
@inproceedings{Cendra2025ICE,
author = {Fernando Julio Cendra and Kai Han},
title = {ICE: Intrinsic Concept Extraction from a Single Image via Diffusion Models},
booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2025},
}
PromptCCD: Learning Gaussian Mixture Prompt Pool for Continual Category Discovery
@inproceedings{Cendra2024promptccd,
author = {Fernando Julio Cendra and Bingchen Zhao and Kai Han},
title = {PromptCCD: Learning Gaussian Mixture Prompt Pool for Continual Category Discovery},
booktitle = {European Conference on Computer Vision (ECCV)},
year = {2024}
}
Histopathology Whole Slide Image Analysis with Heterogeneous Graph Representation Learning
Chan Tsai Hor*, Fernando Julio Cendra*, Lan Ma, Guosheng Yin and Lequan Yu
@inproceedings{Chan2023histopathology,
author = {Chan Tsai Hor and Fernando Julio Cendra and Lan Ma and Guosheng Yin and Lequan Yu},
title = {Histopathology Whole Slide Image Analysis with Heterogeneous Graph Representation Learning},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2023},
}
SL3D: Self-supervised-Self-labeled 3D Recognition
Fernando Julio Cendra, Lan Ma, Jiajun Shen and Xiaojuan Qi
NeurIPS Workshop on “Self-supervised Learning: Theory & Practice” 2022
@inproceedings{Cendra2022sl3d,
author = {Fernando Julio Cendra and Lan Ma and Jiajun Shen and Xiaojuan Qi},
title = {SL3D: Self-Supervised Self-Labeled 3D Recognition},
booktitle = {NeurIPS Workshop on Self-Supervised Learning: Theory and Practice (NeurIPS Workshop)},
year = {2022},
}