Homanga Bharadhwaj

@mangahomanga

Assistant Professor of CS @JohnsHopkins | Hater of hot takes. Lover of analyses.

following
followers

LEDGER promises 3D object memory without looking back at first-person videos

A post introducing LEDGER says it remembers where objects were, when they moved and what they held.

2 Sources, 12d ago, updated 12d ago

New work explores jointed-object manipulation from single-camera videos

A researcher says the work combines vision models with optimization to explore object reconstruction and dexterous retargeting—transferring manipulation motions.

2 Sources, 31d ago, first seen 31d ago

Announcement of Fall Embodied AI Course with Video Data

An X post announces a fall course on embodied AI drawing from web-scale video data.

2 Sources, 49d ago, first seen 49d ago

Featured in

LEDGER promises 3D object memory without looking back at first-person videos

New work explores jointed-object manipulation from single-camera videos

Announcement of Fall Embodied AI Course with Video Data

Featured in

LEDGER promises 3D object memory without looking back at first-person videos

New work explores jointed-object manipulation from single-camera videos

Announcement of Fall Embodied AI Course with Video Data