KeumgangCha
KevinCha
AI & ML interests
representation learning, vision language, multi modal
Recent Activity
published a model about 22 hours ago
sia-vlm/flexbox-deta-base-pretrained updated a model 1 day ago
sia-vlm/flexbox-deta-base-pretrained updated a collection 1 day ago
IOD-Dataset-CollectionOrganizations
models 19
KevinCha/Qwen3-VL-4B-Thinking-BoxSpecialToken
Image-Text-to-Text • 4B • Updated • 41
KevinCha/dinov2-giant-register
1B • Updated • 12
KevinCha/dinov2-large-register
0.3B • Updated • 48
KevinCha/dinov2-base-register
86.6M • Updated • 96
KevinCha/dinov2-small-register
22.1M • Updated • 7
KevinCha/dinov2-Million-AID-Skyscript-lrft
Image Feature Extraction • 0.3B • Updated • 9
KevinCha/dinov2-Million-AID-Skyscript-hrft
Image Feature Extraction • 0.3B • Updated • 5
KevinCha/dinov3-large-low-batch-low-lr
Updated
KevinCha/dinov2-official
Updated
KevinCha/dinov2-vit-base-remote-sensing
0.3B • Updated • 51
datasets 0
None public yet