•   When: Friday, October 03, 2025 from 11:00 AM to 12:00 PM
  •   Speakers: Kostas Daniilidis
  •   Location: JC George's
  •   Export to iCal

Recent generalist robot systems rely on vision-language-action models without making any use of perception capabilities like 3D or 4D representations encoded in vision foundation models. 

They increasingly rely on scaling up the number of examples needed for behavior cloning, not only to capture the distribution of tasks but also basic perceptual skills. We argue that a robot should be an active observer that selects the best views required for scene representation and the affordances involved in the task at hand. Such an exploration can rely on information-theoretic principles that guide the robot towards unpredictable views. We show how this paradigm can be used in Gaussian splatting and in predicting grasp via energy models. 

Our second principle, that of symmetry, enables better generalization and learning dynamics. We propose a general framework for equivariant light field learning by design, and a framework of equivariance by canonicalization that we apply on neural odometry and trajectory prediction. 
 

Bio:

 Kostas Daniilidis is the Ruth Yalom Stone Professor of Computer and Information Science at the University of Pennsylvania, where he has been faculty since 1998. He is an IEEE Fellow. He was the director of the GRASP laboratory from 2008 to 2013, Associate Dean for Graduate Education from 2012 to 2016. He obtained his undergraduate degree in Electrical Engineering from the National Technical University of Athens in 1986 and his PhD in Computer Science from the University of Karlsruhe in 1992. He received the Best Conference Paper Award at the 2017 IEEE International Conference on Robotics and Automation (ICRA 2017). He is the recipient of the 2025 Provost’s Award for Distinguished PhD Mentoring and Teaching. He was Program co-Chair at ECCV 2010 and 3DPVT (now 3DV) 2006. His most cited works are on event-based vision, equivariant learning, 3D human and object pose, and hand-eye calibration.

 

Posted 4 weeks ago