Efficient LLaMA-3.2-Vision by Trimming Cross-attended Visual Features
Paper • 2504.00557 • Published • 15
Ki-Ung song
sk851
AI & ML interests
Generative model / Multimodal
Recent Activity
updated a Space 2 days ago
sk851/TerraFin published a Space 3 days ago
sk851/TerraFin upvoted a collection 18 days ago
Qwen3.5Organizations
authored a
paper about 1 year ago