activity
20232026
collaborators

5 papers

cs.LG2026

Can Bayesian Optimization Efficiently Find a Strong Single Expert in Neural Thickets?

Nigel Bastian Cendra, Abdelhamid Ezzerg, Fernando Julio Cendra +2

Gradient-free post-training has emerged as a compelling alternative to gradient-based optimization for large language models (LLMs), but existing approaches remain costly. We ask w…

cs.CV2025

PartCo: Part-Level Correspondence Priors Enhance Category Discovery

Fernando Julio Cendra, Kai Han

Generalized Category Discovery (GCD) aims to identify both known and novel categories within unlabeled data by leveraging a set of labeled examples from known categories. Existing…

cs.CV2025

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

Fernando Julio Cendra, Kai Han

The inherent ambiguity in defining visual concepts poses significant challenges for modern generative models, such as the diffusion-based Text-to-Image (T2I) models, in accurately…

cs.CV2024

Effective Prompt Pool Learning for Continual Category Discovery

Fernando Julio Cendra, Xinghui Li, Kai Han

This paper studies effective prompt pool learning for Continual Category Discovery (CCD), a challenging open-world setting where a model must discover novel categories from a conti…

cs.CV2023

Histopathology Whole Slide Image Analysis with Heterogeneous Graph Representation Learning

Tsai Hor Chan, Fernando Julio Cendra, Lan Ma +2

Graph-based methods have been extensively applied to whole-slide histopathology image (WSI) analysis due to the advantage of modeling the spatial relationships among different enti…