arxiv:2305.01579
Jeonghwan Kim
wjdghks950
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 2 hours ago
Pixel-Grounded Retrieval for Knowledgeable Large Multimodal Models upvoted a paper about 2 hours ago
PARTONOMY: Large Multimodal Models with Part-Level Visual Understanding upvoted a paper about 2 hours ago
Mixture of Layers: Dynamic Layer Routing for Visual ReasoningOrganizations
models 14
wjdghks950/vicuna_clip_dinov2_hybrid
Visual Question Answering • 14B • Updated • 34
wjdghks950/vicuna_dinov2_patch
Visual Question Answering • 14B • Updated • 37
wjdghks950/vicuna_dinov2_hybrid
Visual Question Answering • 14B • Updated • 16
wjdghks950/vicuna_clip_patch
Visual Question Answering • 13B • Updated • 27
wjdghks950/vicuna_clip_hybrid
Visual Question Answering • 13B • Updated • 47
wjdghks950/llama3-8b_siglip_patch
Visual Question Answering • Updated • 8
wjdghks950/llama3-8b_siglip_hybrid
Visual Question Answering • Updated • 9
wjdghks950/phi1_5_siglip_patch
Visual Question Answering • Updated • 11
wjdghks950/phi1_5_siglip_hybrid
Visual Question Answering • Updated • 10
wjdghks950/promac-futloc-stage1b-cot-trajectory
Image-Text-to-Text • 4B • Updated • 8
datasets 0
None public yet