3 papers
cs.AI2026
Cross-Modal Knowledge Distillation without Paired Data: Theoretical Foundation and Algorithm
Trong Khiem Tran, Anh Duc Chu, Quang Hung Pham +2
Cross-modal knowledge distillation (CMKD) studies how a (large) teacher model trained on one type of data (e.g., images) can guide a (smaller) student model building on another typ…
cs.LG2026
FedKDX: Federated Learning with Negative Knowledge Distillation for Enhanced Healthcare AI Systems
Quang-Tu Pham, Hoang-Dieu Vu, Dinh-Dat Pham +1
This paper introduces FedKDX, a federated learning framework that addresses limitations in healthcare AI through Negative Knowledge Distillation (NKD). Unlike existing approaches t…
cs.LG2025
Smooth-Distill: A Self-distillation Framework for Multitask Learning with Wearable Sensor Data
Hoang-Dieu Vu, Duc-Nghia Tran, Quang-Tu Pham +3
This paper introduces Smooth-Distill, a novel self-distillation framework designed to simultaneously perform human activity recognition (HAR) and sensor placement detection using w…