15 posts analyzed over the last 12 weeks
Over the last 12 weeks
Average across all posts
This month vs. previous
Growth slope (6 weeks)
Best week: 30 mars (2644 avg. likes)
Yann LeCun
Executive Chairman, AMI Labs - Prof NYU
Selfies with enthusiastic ICLR participants.
Yann LeCun
Executive Chairman, AMI Labs - Prof NYU
I gave the Lemley Lecture at Brown University yesterday: a 30-minute talk followed by a fireside chat+Q&A with Provost Francis Doyle. It was fun to catch up with former AT&T colleagues Chris Rose and Michael Littman who…
Yann LeCun
Executive Chairman, AMI Labs - Prof NYU
Our VL-JEPA poster at ICLR with Delong Chen and Pascale Fung Paper: https://lnkd.in/eMAhMibv
Yann LeCun
Executive Chairman, AMI Labs - Prof NYU
A catalog of JEPAs https://lnkd.in/eZnq688H
Yann LeCun
Executive Chairman, AMI Labs - Prof NYU
Position paper with Emmanuel Dupoux and Jitendra MALIK on how to get machines to learn like humans and animals.
Yann LeCun
Executive Chairman, AMI Labs - Prof NYU
Our VL-JEPA poster at ICLR with Delong Chen and Pascale Fung Paper: https://lnkd.in/eMAhMibv
Yann LeCun
Executive Chairman, AMI Labs - Prof NYU
A regularizer to train JEPAs so that trajectories in representation space have minimum curvature. This helps gradient-based planning.
Yann LeCun
Executive Chairman, AMI Labs - Prof NYU
BADAS 2.0 predicts collision in all kinds of situations, widely different from what's in the training set. BADAS 2.0 uses V-JEPA 2 as a foundation model.
Yann LeCun
Executive Chairman, AMI Labs - Prof NYU
Excellent article de Guillaume Grallet dans Le Point sur AMI Labs et son équipe de choc. https://lnkd.in/eXGh6iDE
Yann LeCun
Executive Chairman, AMI Labs - Prof NYU
Awesome essay byy former Bell Labs colleague Roberto Pieraccini on the historical failures of large companies with top research lab to pick up on promising innovations. Industry keeps making the same mistake: investing …