Congratulations to @LingjieLiu1 for receiving the ACM SIGGRAPH Significant New Researcher Award! We are thrilled and so proud of you!
siggraph.org/awards/signifi…
Some summer fun with Claude artifacts. An author-centered view of papers at ECCV, click on the author and you will see their papers on the right:
cis.upenn.edu/~kostas/eccv26…
I am sure it has several mistakes with namesakes etc.
Congratulations to Nadia Figueroa and @GRASPlab co-authors for winning the ICRA 2026 Best Conference Paper!!!!! and Best Paper in Planning and Control.
Nadia: "paradigm towards #physicalintelligence that unifies SE(3) dynamical systems with symbolic planning and learning to
@GeorgiaChal@jon_barron@vincesitzmann@anand_bhattad#bitterlesson
The low-dimension of the action space does not make the problem easy. What matters is the structure of the latent manifold and what this encodes. 3D representations are efficient because they are invariant to
You’ve put your finger on the real question there… where structure enters, modular vs end-to-end... That’s exactly what we’re debating, so I’ll save the long response for the panel. 🙂
Last Thursday, @stefanos_pert Stefanos Pertigkiozoglou defended his PhD. Stefanos is one of the deepest and most thorough thinkers I worked with. He is the definition of quiet power. His key insight was that enforcing exact equivariance throughout optimization can unnecessarily
