Fernando Julio Cendra's Homepage

I'm currently an MPhil student at The University of Hong Kong, advised by Prof. Kai Han in Visual AI Lab. Before that, I received my BEng (hons) in Electronic Engineering from HKU.

I'm interested in developing novel algorithms that integrate concepts across multiple abstraction levels to build representations from diverse multimodal data sources, with the goal of creating adaptable and interpretative models that leverage these algorithms to enhance their ability to understand and interact with our environment.

News

[ Feb. 2025 ] One paper about concept learning with diffusion models has been accepted to CVPR 2025 as Highlight.
[ Jul. 2024 ] One paper about continual category discovery has been accepted to ECCV 2024.
[ Feb. 2023 ] One paper about heterogeneous graph representation learning has been accepted to CVPR 2023.
[ Dec. 2022 ] One paper about 3D representation learning has been accepted to NeurIPS Workshop 2022.

Publications

* denotes equal contribution

ICE: Intrinsic Concept Extraction from a Single Image via Diffusion Models

Fernando Julio Cendra and Kai Han

CVPR 2025 (Highlight)

PromptCCD: Learning Gaussian Mixture Prompt Pool for Continual Category Discovery

Fernando Julio Cendra, Bingchen Zhao and Kai Han

ECCV 2024

Histopathology Whole Slide Image Analysis with Heterogeneous Graph Representation Learning

Chan Tsai Hor^*, Fernando Julio Cendra^*, Lan Ma, Guosheng Yin and Lequan Yu

CVPR 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

Academic Services

Conference Reviewer: CVPR 2024,2025; ECCV 2024, NeurIPS 2023,2025, AAAI 2025

Teaching

Programming for Data Sciences (HKU STAT7008)

Teaching Assistant, Fall 2024 & Fall 2023
Applied Data Mining and Text Analytic (HKU ARIN7102)

Teaching Assistant, Spring 2024 & Spring 2023

Design and source code based on this website. Thanks!