AI8/10
World Labs Founders Describe Compute-Driven Scaling of Atlas Model
▶
Fei-Fei Li and Justin Johnson of World Labs discuss scaling laws, compute as the main constraint, and an early result where a camera flew under a NeRF garden table, which convinced them to commit to the Atlas model. Li also announced World Labs is joining AMD.
Original post · 1 min read
World Labs co-founders Dr. Fei-Fei Li and Justin Johnson on compute as the constraint, and the Slack message that convinced them to go all-in on their Atlas model:
Fei-Fei: "I think [we] have total conviction about the scaling law."
"I do think the exact architecture choices and data mixtures is where the devil's in the details. I watched Justin and his team going from 'we really don't know how long this is gonna take,' to 'maybe sign of life,' to 'wow, this is gonna work.'"
Justin: "We're basically at the beginning, and we're basically limited by compute at this point."
"During development, we trained a sequence of models, the first couple rungs of the scaling ladder. Each time we made the model bigger, each time we trained it for longer, each time we put it on more chips, it got significantly better."
Fei-Fei: "Here's a little bit of an insider story... There was one day in early summer... Ben and Justin feed [a smaller model] into the viewpoint generation... Remember that famous garden table from the NeRF paper?... Overnight we all saw the Slack from Ben that our camera flew under the table."
"That morning, the three of us looked at each other in the eyes and said, 'That's it. We're gonna build this.' We made a decision within five seconds. No one has ever seen this result."
@drfeifei @jcjohnss @BenMildenhall @martin_casado
Fei-Fei: "I think [we] have total conviction about the scaling law."
"I do think the exact architecture choices and data mixtures is where the devil's in the details. I watched Justin and his team going from 'we really don't know how long this is gonna take,' to 'maybe sign of life,' to 'wow, this is gonna work.'"
Justin: "We're basically at the beginning, and we're basically limited by compute at this point."
"During development, we trained a sequence of models, the first couple rungs of the scaling ladder. Each time we made the model bigger, each time we trained it for longer, each time we put it on more chips, it got significantly better."
Fei-Fei: "Here's a little bit of an insider story... There was one day in early summer... Ben and Justin feed [a smaller model] into the viewpoint generation... Remember that famous garden table from the NeRF paper?... Overnight we all saw the Slack from Ben that our camera flew under the table."
"That morning, the three of us looked at each other in the eyes and said, 'That's it. We're gonna build this.' We made a decision within five seconds. No one has ever seen this result."
@drfeifei @jcjohnss @BenMildenhall @martin_casado
Fei-Fei Li @drfeifeiTo Seek a Newer World — World Labs is joining @AMD. This is a huge moment for @theworldlabs, our team, and for me, and I wanted to take a moment to share what this means and why I’m so excited for this next chapter.
“Come,
♥ 226 · ⟲ 35 · 👁 42.5KView on X ↗
