dmusingu/diffvqa-qwen3-0.6b-multiobjective-regsteps
Visual Question Answering • Updated
Denis Musinguzi
dmusingu
AI & ML interests
Multi-modal learning, computer vision and robotics
Recent Activity
updated a model 2 days ago
dmusingu/diffvqa-qwen3-0.6b-multiobjective-regsteps published a model 2 days ago
dmusingu/diffvqa-qwen3-0.6b-multiobjective-regsteps updated a model 5 days ago
dmusingu/diffvqa-online-qwen3-0p6bOrganizations
dmusingu/diffvqa-online-qwen3-0p6b
Visual Question Answering • Updated
dmusingu/diffvqa-online-gpt3medium
Visual Question Answering • Updated
dmusingu/diffvqa-online-gpt2medium-pretrained
Visual Question Answering • Updated
dmusingu/diffvqa-online-gpt2medium-prefix
Visual Question Answering • Updated
dmusingu/cxr-vitl14-global-local-cap
Image Feature Extraction • Updated
dmusingu/cxr-vitl14-multiobjective-regsteps
Image Feature Extraction • Updated
dmusingu/cxr-vitl14-multiobjective
Image Feature Extraction • Updated
dmusingu/cxr-vitl14-region-contrastive
Image Feature Extraction • Updated
dmusingu/cxr-vitl14-localized
Image Feature Extraction • Updated
dmusingu/cxr-vitl14-siglip
Image Feature Extraction • Updated
dmusingu/cxr-vitl14-clip-infonce
Image Feature Extraction • Updated
dmusingu/cxr-vitl14-captioning-50ep
Image Feature Extraction • Updated
dmusingu/cxr-vitl14-captioning
Image Feature Extraction • Updated
dmusingu/lapvqa-pretrain-captioning
Updated
dmusingu/lapvqa-ad
Object Detection • Updated
dmusingu/lapvqa-pg
Updated
dmusingu/lapvqa-rrg-native
Updated
dmusingu/lapvqa-rrg-pretrain-captioning
Updated
dmusingu/lapvqa-diffvqa-pretrain-captioning
Visual Question Answering • Updated
dmusingu/lapvqa-rrg
Updated
dmusingu/lapvqa-vqa-pretrain-captioning
Visual Question Answering • Updated
dmusingu/lapvqa-diffvqa
Visual Question Answering • Updated
dmusingu/lapvqa-diffvqa-native
Visual Question Answering • Updated
dmusingu/lapvqa-vqa-native
Visual Question Answering • Updated
dmusingu/lapvqa-vqa
Visual Question Answering • Updated
dmusingu/lapvqa-pretrain-sigmoid
Updated
dmusingu/lapvqa-pretrain-contrastive
Updated
dmusingu/qwen3-vl-8b-mimic-cxr-sft
Image-Text-to-Text • 9B • Updated • 4
dmusingu/Qwen3-VL-2B-RRG-SFT
Image-Text-to-Text • 2B • Updated • 1