Selective Training for Large Vision Language Models via Visual Information Gain
Paper • 2602.17186 • Published • 3
Sangheum Hwang
beopst
AI & ML interests
None yet
Organizations
None yet
authored a
paper 3 months ago
submitted a
paper to Daily Papers 3 months ago
authored 4
papers about 1 year ago
Enhanced OoD Detection through Cross-Modal Alignment of Multi-Modal Representations
Paper • 2503.18817 • Published • 3
Few-shot Fine-tuning is All You Need for Source-free Domain Adaptation
Paper • 2304.00792 • Published
Self-Knowledge Distillation with Progressive Refinement of Targets
Paper • 2006.12000 • Published • 1
Reflexive Guidance: Improving OoDD in Vision-Language Models via Self-Guided Image-Adaptive Concept Generation
Paper • 2410.14975 • Published