UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations
Paper
•
2505.08787
•
Published
•
14
•
2
Hanjung Kim
HanjungKim
AI & ML interests
Video Understanding, Robot Learning
Recent Activity
upvoted
a
paper
13 days ago
K-EXAONE Technical Report
upvoted
a
paper
13 days ago
mHC: Manifold-Constrained Hyper-Connections
upvoted
a
paper
about 2 months ago
Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning
Segmentation
Organizations
None yet
Improve model card
#2 opened 8 months ago
by
nielsr
Set pipeline tag to robotics
#1 opened 8 months ago
by
nielsr
commented
a
paper
8 months ago