Ankit Gupta
speaker
237 appearances
1 recordings
1 series
first heard Jul 2026
last heard 17 Jul
Ankit Gupta’s voice in public audio — every appearance, attributed to the second.
Trend
recordings per month · last 12 monthsRecordings per month over the last 12 months — 1 in all, peaking in Jul 2026 with 1.
Appearances
And it's an idea that comes back over and over and then has this various tricks that it actually takes to get it to work in practice.
Okay, now we have a pretty good sense for how world models work.
We have a pretty good sense for what the state of the art looks like.
If we trust this paper, and it seems like these kind of work on robots too.
This paper is only from the end of last year, this year, and it seems like they have various methods that allow you to train on relatively small amounts of data that's tractable and pre-trained on data diffusion models.
So are we good?
Or does it all work?
What are one or two?
Cause there's lots of open problems remaining.
What are like a few open problems?
Maybe we can emphasize here that the community can go emphasize working.
It basically needs like a ton of data not to do that either from simulation for that to not happen.
It's really challenging.
And then I guess there's like the practical speed elements of these, right?
A lot of these are doing some sort of expensive planning step.
And we're doing some sort of like, we're kind of hacking around it with this retraining process and synthetic data.
But even so, like to really get maximum performance right now, you'd want to do something that's closer to like the AlphaGo style rollout.
But on the flip side now, we talked in the past video about the squint test and how we felt that autoregressive LLMs maybe don't pass the squint test.
Why don't we reintroduce what the squint test was for a second?
And then maybe let's think about whether this passes the squint test despite all those limitations.
Showing 201–220 of 237 · page 11 of 12
← Previous
Next →