collaborators

6 papers

cs.CV2026

ShapKO: Shapley-Adaptive Modality Knockout for Robust Multimodal Learning

Nusrat Binta Nizam, Fengbei Liu, Sunwoo Kwak +3

Multimodal medical models often degrade when inputs are missing, a common scenario in real-world clinical workflows. Separately, even when all modalities are present, modality domi…

cs.LG2026

MAdam: Metric-Aware Multi-Objective Adam

Fengbei Liu, Rachit Saluja, Sunwoo Kwak +5

Multi-objective optimization (MOO) underlies many machine learning problems, yet MOO solvers across the loss-balancing, gradient-balancing, and Pareto-based families almost univers…

cs.CV2026

BackSplit: The Importance of Sub-dividing the Background in Biomedical Lesion Segmentation

Rachit Saluja, Asli Cihangir, Ruining Deng +3

Segmenting small lesions in medical images remains notoriously difficult. Most prior work tackles this challenge by either designing better architectures, loss functions, or data a…

eess.IV2026

HyperCT: Low-Rank Hypernet for Unified Chest CT Analysis

Fengbei Liu, Sunwoo Kwak, Hao Phung +6

Non-contrast chest CTs offer a rich opportunity for both conventional pulmonary and opportunistic extra-pulmonary screening. While Multi-Task Learning (MTL) can unify these diverse…

cs.CV2026

A Unified Perspective on Adversarial Membership Manipulation in Vision Models

Ruize Gao, Kaiwen Zhou, Yongqiang Chen +1

Membership inference attacks (MIAs) aim to determine whether a specific data point was part of a model's training set, serving as effective tools for evaluating privacy leakage of…

cs.LG2025

Knockout: A simple way to handle missing inputs

Minh Nguyen, Batuhan K. Karaman, Heejong Kim +3

Deep learning models benefit from rich (e.g., multi-modal) input features. However, multimodal models might be challenging to deploy, because some inputs may be missing at inferenc…