← Search

Luong Tran

2 accepted papers

2026

CLIP-FMoE: Scalable CLIP via Fused Mixture-of-Experts with Enforced Specialization

ICLR 2026poster

Mixture-of-Experts (MoE) architectures have emerged as a promising approach for scaling deep learning models while maintaining computational efficiency. However, existing MoE adaptations for Contrastive Language-Image Pre-training (CLIP) models suffer from significant computational overhead during s…

Cited by 0SourceScholar
2025

More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning

ICCV 2025poster

Multi-label learning is a challenging computer vision task that requires assigning multiple categories to each image. However, fully annotating large-scale datasets is often impractical due to high costs and effort, motivating the study of learning from partially annotated data. In the extreme case…

Cited by 0SourcePDFScholar