Check out the Department of Computer Science website to apply. The application deadline is December 1. web.cs.toronto.edu/graduate/pro...

We are affiliated with @vectorinstitute.ai, the Schwartz Reisman Institute, @uoftdsi.bsky.social, the Acceleration Consortium, and the Robotics Institute. There is a vibrant AI community around U of T, and we have a fantastic set of collaborators. 4/n

Admittedly, Toronto winters can be cold ❄️, but we have access to multiple GPU clusters that help us stay warm 🔥. And we have a growing set of robots to keep us busy 🦾🦿🚘. 3/n

This involves exciting topics such as control techniques for generative models 🎮, editing techniques for scene representations ✂️, physical dynamics learning ⚙️, planning in learned models 🗺️, policy learning 🧠, and real-world robot deployment 🦾. 2/n

Agree with all of the above. There is also a version of this among researchers, i.e., people knowingly defending the continued existence of likely unfruitful research directions to protect their own careers. Ultimately, each insight needs to be evaluated on its own merits.

The hat looks great, and our jobs are safe: if solving robotics doesn't work out, we can still pursue a career in fashion! 🧢👒🎩 I hope @dieworkwear.bsky.social would agree. 2/2

But that’s not specific to the U.S. It’s the default spice in many places.

If you ever tried to vectorize code in Matlab (I know, that was a long time ago), you'll probably remember how ease of use and speed can be at odds.

Chicago manual of style is next. ^^

Thank you, Jonathan Kelly, for being a fantastic co-advisor. Thank you also to the entire thesis and final exam committee consisting of @davelindell.bsky.social, Ben Liang, Steven Waslander, and our external member, Katerina Fragkiadaki! 4/4

Ashkan was drowning in offers, and I hope the folks at Snap know how lucky they are to have him join. I am sure Sergey Tulyakov will take good care of him, and I look forward to continuing to collaborate in new ways. 3/4

Ashkan has done some of the pioneering work on scene editing of 3d representations for novel view synthesis. While my motivation for this work was mainly for robotics 🦾, it has applications far beyond this domain. 2/4

Is there a preprint on this?