Nikhila Ravi

speaker

227 appearances 1 recordings 1 series first heard Dec 2025 last heard 18 Dec

Nikhila Ravi’s voice in public audio — every appearance, attributed to the second.

Trend

recordings per month · last 12 months

Recordings per month over the last 12 months — 1 in all, peaking in Dec 2025 with 1.

Appearances

newest first · ▶ plays the moment

Latent Space: The AI Engineer Podcast · SAM 3: The Eyes for AI — Nikhila & Pengchuan (Meta Superintelligence), ft. Joseph Nelson (Roboflow) · 18 Dec 2025 podcast

Yeah, and I think from maybe just to add to that from like meta side, like we don't usually get as much visibility into all of these real world use cases.

So, you know, being able to kind of hear that from Roboflow and having these models available on the platform is like so valuable for us.

It's also, you know, we get we get to know how these models actually work in the real world, which is, you know, ultimately the best eval for a model.

So I

I think, you know, it's definitely awesome to hear about all these things that were empowering.

Probably something like the best eval is if it works in the real world.

And that's like the ultimate goal for all of our models, like SAM one, SAM two, SAM three.

We want to people to use it out of the box as much as possible.

And I think, you know, with language in SAM three specifically, there there does need to be, in some cases, some domain adaptation.

But we have sort of tried to make that easy.

I don't know, Penguin, you wanna talk a little bit about that, like the fine-tuning aspect.

Yeah, this is actually one thing something something we get asked a lot is like, what's the minimum amount of data I need to fine tune?

And, you know, being able to do that with just sort of ten data points is hopefully will unlock a lot more than we can do ourselves.

Yeah, the other place where negatives play a big role is just is it in the image or not?

And that was one of the things that we did was really separate the problem into a recognition problem and a localization problem.

So first can you answer the question, is this object or is this concept in the image?

And then if it's in the image, where is it in the image?

And so to really uh to really build in that capability, we had to annotate a lot of negative um phrases in images.

So basically a lot of phrases that don't exist in the image, in addition to the concepts that exist in the image with the corresponding mask pair.

So we have, you know, if you look at our uh

Showing 81–100 of 227 · page 5 of 12