SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers
Paper • 2411.09420 • Published • 1
Shravan Venkatraman
shravvvv
·
AI & ML interests
None yet
Recent Activity
authored a paper 1 day ago
Paying More Attention to Visual Tokens in Self-Evolving Large Multimodal Models updated a model about 2 months ago
shravvvv/VISEOrganizations
None yet