In his RSS keynote talk, Trevor Darrell predicted that 4D particle will be the most effective representation for visual pretraining. Exciting to see this vision align with the core design of our work PGND: learning (4D) particle dynamics from real-world RGB-D videos. 👀

ask not what you can do for ai, ask what ai can do for you

Brutal truth: Your inability to focus on one thing for an extended amount of time will hurt you far greater than your lack of intellect.

can it trump peer-based learning?

the world is always against the robots

the deepmind demo felt underwhelming in person at RSS. Not sure if Russ Tedrake was too much out of distribution #RSS2025

somehow you know this deep down but you need a certain segery levine to tell you 'the real thing'

quantization-aware doge

thanks for the invite Yutori- going to be testing it on over this next week- might update here. Impressed with the UI so far- and shows early promises of digital zen.

👀

pretty much on the trajectory they promised but one can't be blamed for wanting to see more productized version of it.

Yutori is so real ❤️ Yutori