arxiv:2602.07274
William Li PRO
williamium
AI & ML interests
Learning AI efficiently and robustly in interactive, multi-modal and embodied environment.
Recent Activity
updated a model about 5 hours ago
xvreason/video-reasoning-generalization-diffsyn published a dataset about 9 hours ago
williamium/zwz-37k published a dataset about 9 hours ago
williamium/vision-opd-6kOrganizations
models 10
williamium/ttground-r1-ckpts
Updated
williamium/indirect_caption
Updated • 15
williamium/indirect_rag
Updated
williamium/vigorl-ckpts
Updated
williamium/video-reasoning-generalization
Updated
williamium/deepeyes
Updated
williamium/co-learning-models
Updated
williamium/AdaptRL
Updated
williamium/embodied-video-rl
Updated
williamium/llava-factory-test
Text Generation • 9B • Updated • 2
datasets 10
williamium/zwz-37k
Viewer • Updated • 111k • 1
williamium/finevision80k
Viewer • Updated • 79.8k • 20
williamium/vision-opd-6k-open
Viewer • Updated • 6.24k • 16
williamium/vision-opd-6k
Viewer • Updated • 6.24k • 24
williamium/embodied-video-rl
Viewer • Updated • 1.36k • 5
williamium/CoreCognition
Viewer • Updated • 2.94k • 254 • 8
williamium/llava
Updated • 61
williamium/EgoPrivacy
Viewer • Updated • 731 • 23 • 1
williamium/llava-eval
Updated • 4
williamium/llava-sft
Updated • 4