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 monthsRecordings per month over the last 12 months — 1 in all, peaking in Dec 2025 with 1.
Appearances
We have Perception Encoder.
We have a D detector.
We use STAM two.
Um, we also use Llama in our data engine.
So we really like using all the components from um
Yeah, well if it'll work, you gotta s continue using it.
Each of the d w it scales of the number of detected objects.
Yeah, maybe I can just do a quick intro and and I'll hand it over to Penguan to to do the deep dive.
But essentially, as is mentioned, Sam three, we constrain the text input to these atomic visual concepts like, you know, yellow school bus or yellow watering can.
But obviously people want to interact with the model with natural language and we want to enable that as well.
And so that really
uh become segues into being able to use SAM3 as this like visual agent for an MLLM.
And so I'll hand over to Penktron.
Maybe you can explain how about the SAM3 agent setup and then talk through some of the results that we got there.
And I think the speed actually is a
is a huge factor for many use cases.
I I think like even Meta we're using SAM3 for various different product use cases and fast inference speed is very critical to to enable that.
And so I think that's something that I think in many cases you don't even need an MLM for.
It's it's kind of overkill to use an MLM for some application.
Yeah, I mean exhaustivity, like finding every instance is something we
Showing 141–160 of 227 · page 8 of 12
← Previous
Next →