James Zou

speaker

371 appearances 1 recordings 1 series first heard Dec 2024 last heard Dec 2024

James Zou’s voice in public audio — every appearance, attributed to the second.

Trend

recordings per month · last 12 months

No recordings in the last 12 months.Older appearances are listed below; set an alert to hear about the next one.

Appearances

newest first · ▶ plays the moment

"The Cognitive Revolution" · Breakthroughs in AI for Biology: AI Lab Groups & Protein Model Interpretability with Prof James Zou · 18 Dec 2024 podcast

And thank you for that very nice overview and summary of it.

So we created this website.

interplm.ai, which is actually this interactive website.

So actually we you know, I encourage everybody who's interested, you can just go on there and you can actually sort of explore all these different kinds of motifs yourself.

And you can look at what are these 3D structures that are learned and it's a kind of interactive way to visualize each of the concepts that are learned by this AI model.

And maybe I'll just highlight one thing that you mentioned, which is relates to how do we systematically annotate all these new concepts.

Because some of these might be new concepts and some of these might be extensions of existing ones.

And this is where

I think sort of like a convergence of different technologies, but I also find that um no, we found that actually here this is actually a good use case of our large language model, right?

Uh here we actually use cloud to try to help us to automatically annotate some of these new concepts by pulling relevant information from different databases and comparing what's known about the proteins versus what what's being activated by each of these concepts.

So I think this is actually where.

there could be an interesting convergence of the two things that we talked about, where maybe you can imagine having a virtual lab of different expert agents, right, and can help us to interpret what's going on behind under the hood of this large protein language model.

I think it's

I think we s were sort of expecting that there will be new motifs, new concepts that are learned by this protein language model beyond what we have currently annotated.

I think that was our prior going in and one of the motivations because the models have learned on so much data, right?

And because

We know that there's some existing limitations in our current annotation databases.

Yeah, it's a good question.

I mean, I think for certain domains of proteins and like protein interactions, the small molecules, we're still, let's say, data limited rather than compute limited.

And that's where even like was the Alpha 43 and the latest models, they still make mistakes on some of these let's say just watered proteins or looking at specific interactions domains.

Showing 341–360 of 371 · page 18 of 19