← Search

Thanh Trung Huynh

3 accepted papers

2025

Federated Prompt-Tuning with Heterogeneous and Incomplete Multimodal Client Data

ICCV 2025poster

This paper introduces a generalized federated prompt-tuning framework for practical scenarios where local datasets are multi-modal and exhibit different distributional patterns of missing features at the input level. The proposed framework bridges the gap between federated learning and multi-modal p…

Cited by 0SourcePDFScholar
2025

Learning Reconfigurable Representations for Multimodal Federated Learning with Missing Data

NeurIPS 2025poster

Multimodal federated learning in real-world settings often encounters incomplete and heterogeneous data across clients. This results in misaligned local feature representations that limit the effectiveness of model aggregation. Unlike prior work that assumes either differing modality sets without mi…

Cited by 0SourcecodeScholar
2024

CARER - ClinicAl Reasoning-Enhanced Representation for Temporal Health Risk Prediction

EMNLP 2024main

The increasing availability of multimodal data from electronic health records (EHR) has paved the way for deep learning methods to improve diagnosis accuracy. However, deep learning models are data-driven, requiring large-scale datasets to achieve high generalizability. Inspired by how human experts…