knightnemo/nanowm-l2-rt1-abl-scale-l2-50k
0.6B • Updated • 4
knightnemo
knightnemo
AI & ML interests
World Models, World Action Models, VLA Models, Test-time Adaptation & Self-Improvement, Dexterous Manipulation.
Recent Activity
updated a dataset 26 days ago
knightnemo/furniturebench_lamp_delta published a dataset 26 days ago
knightnemo/furniturebench_lamp_delta upvoted a paper 27 days ago
On the Geometry of On-Policy DistillationOrganizations
knightnemo/nanowm-b2-dino-wm-pusht-100k
0.2B • Updated • 109
knightnemo/nanowm-b2-dino-wm-point-maze-30k
0.2B • Updated • 18
knightnemo/nanowm-b2-dino-wm-granular-15k
0.2B • Updated • 8
knightnemo/nanowm-b2-dino-wm-wall-15k
0.2B • Updated • 9
knightnemo/nanowm-b2-dino-wm-rope-15k
0.2B • Updated • 15
knightnemo/nanowm-s2-rt1-abl-scale-s2-50k
39.8M • Updated • 3
knightnemo/nanowm-b2-rt1-abl-inj-cross-attention-50k
0.2B • Updated • 4
knightnemo/nanowm-b2-rt1-abl-inj-film-50k
0.2B • Updated • 1
knightnemo/nanowm-b2-rt1-abl-inj-adaln-fuse-50k
0.2B • Updated • 2
knightnemo/nanowm-b2-rt1-abl-inj-adaln-50k
0.2B • Updated • 6
knightnemo/nanowm-b2-rt1-abl-pred-epsilon-50k
0.2B • Updated • 3
knightnemo/nanowm-b2-rt1-abl-pred-x-50k
0.2B • Updated • 1
knightnemo/nanowm-b2-rt1-abl-pred-v-50k
0.2B • Updated • 3
knightnemo/wuji-hand-gesture-vam
Robotics • Updated
knightnemo/mlsbench-jepa-planning-ac-jepa-two-rooms
Reinforcement Learning • Updated
knightnemo/dummy_repo_id
Updated