3 papers
cs.LG2026
RAPTOR: Role-Aware Private Training for Mixture-of-Experts
Duc Dm, Khai Le-Duc, Nguyen Do +18
Differentially private (DP) fine-tuning methods treat sparse Mixture-of-Experts (MoE) models as a single dense block, ignoring that shared layers see all data while experts only se…
cs.CV2026
FreqOrtho-SR: Frequency-Guided Orthogonal Expert Learning for Real-World Image Super-Resolution
Minh Son Hoang, Dinh Phu Tran, Quyen Nguyen Duc +2
Diffusion prior-based methods have shown impressive results in real-world image super-resolution (ISR), yet two key challenges persist: balancing pixel-level fidelity with semantic…
cs.LG2026
FIBER: A Differentially Private Optimizer with Filter-Aware Innovation Bias Correction
Duc Dm, Thao Do, Minh Son Hoang +3
Differentially private (DP) training protects individual examples by adding noise to gradients, but the injected noise interacts nontrivially with adaptive optimizers. Recent DP me…