Latent Space / episode intelligence
Speakers in the public record
Claim mix
Evidence policy
Every row below preserves an exact excerpt. Identified speakers are linked; unresolved voices are labeled and excluded from people counts.
Claim ledger
23 published records
01 / evaluation
“It's a really encouraging trend for not thinking about only the new model capability, but what sort of applications folks want to build with models as a result of that downstream.”
02 / evaluation
“it makes sense to like very narrowly do something very well. And that's, I think, proven to be well accomplished.”
03 / prediction
“It's set a new standard. And with the release of SAM 2, I think we're about to see an acceleration of those capabilities for a lot of reasons.”
04 / belief
“I think that could definitely unlock some of these edge use cases that we were able to make a compelling web demo without having to do that.”
05 / belief
“In SAM 2 you dropped that in the web demo. And I think that's because you made some notable improvements to the rate at which encoding happens.”
06 / belief
“I think we're not really exposed to that. Maybe you are at Roboflow because you get to see all the users of these tools.”
07 / belief
“I think that's not a direction we'll go in, but as you said, like the model is an annotation tool to improve the model. And so I think that's definitely the approach we want to take is we provide the tools for you to improve the model as well as the model itself.”
08 / belief
“There's many different approaches to tracking, I think I would encourage people to think about like what actually they need for their use case and then try to find something that that fits versus, yeah, maybe SAM2 is too much, you know, maybe you don't even need the full mask.”
09 / belief
“I think so. If one wanted to be really precise with how literature refers to object re identification, object re identification is not only what SAM does for identifying that an object is similar across frames, It's also assigning a unique ID.”
10 / belief
“We, you know, need it to be real time and. Those requirements really are very core to how we think about these models.”
11 / belief
“One thing that I think is really notable here, there's two things. One is that like, I'd love to have a little bit of a discussion about how the models keeping track of the embedded scene to keep track of the ball and the cup in different places.”
12 / belief
“I want to talk about more about things from the paper, but I think we're still in this sort of demo section.”
13 / belief
“There's different lighting conditions. They can deform, but I think a difference to language models is probably the amount of context that you need is significantly less than maintaining a long multi time conversation.”
14 / recommendation
“You need to, like, a priori ensure that the objects of interest can be correctly segmented and maybe collect data to do that. But even if you had, like, a perfect SAM, like an omniscient SAM that could see every segment in every domain with all pixels perfectly outlined, in production, you would still need some way to Almost like signal to the model what you care about like to paint this picture if you are like a retailer and you are providing Photos of models wearing your clothing on your retail site You may care about you know only the shirt and Sam by default might segment the full person And so there's you know visual prompting that you can do to ensure that you only outline Maybe the shirt for the purposes of swapping in and out different shirts for displaying a given model on a retail page You And so I think what's interesting is that's where, like I wouldn't call it domain adaptation, but that's where, like, when you apply to industry, like, one thing that's particularly important with tooling and enabling SAM to reach its full potential.”
15 / prediction
“It's weird because like, I guess with segment anything too, it's like 4D because you solve time, you know, you started with 3D and now you're solving the 4D.”
16 / prediction
“I showed an example where, like, screenshots, where Sam isn't yet super great at screenshots, so maybe that's, like, in the messy middle or in the longer tails for now. But what's going to happen is there needs to be systems of validating the point of view that I think about, like, tooling to also validate that models are doing what we want them to do, adapting to datasets that we want them to adapt to.”
17 / prediction
“Being able to run on a higher wide array of problems with zero or multi shot capability on a faster, a faster rate. And I think the architecture innovations and things like SAM2 of memory, of increasingly like transformers making their way into division and probably blended architectures increasingly too.”
18 / uncertainty
“People in the community help us address, but one definitely challenging case is where there are multiple similar looking objects, especially if that's like a crowded scene with multiple similar looking objects, keeping track of the target object is a challenge. That's still something that I don't know if we've solved perfectly, but again, the ability to provide refinement clicks.”
19 / prediction
“Which actually takes me to A separate point of something that I predict that's probably going to happen and Nikhil, I'm actually kind of interested why maybe your team made a conscious decision to not do this initially with SAM2.”
20 / recommendation
“Use the demo as a way to improve our annotation tool. And so then it becomes very natural to invest in building a good demo because it speeds up your annotation and improves the data quality and that will improve the model quality.”
21 / evaluation
“For example, the t shirt of a person, SAM2 can track the t shirt effectively across the entire video, whereas these baselines might actually start tracking the entire person, because that's what they're used to doing, and isolating it to just one part of the person is not something they were ever trained to do, and so those are sort of some of the limitations.”
22 / evaluation
“That looked like it, but we didn't have to label it. And so that means that even when you use SAM for applications that it wasn't really trained for, because we didn't restrict it to a certain set of categories, you can actually use it out of the box without custom adaptation.”
23 / prediction
“separate point of something that I predict that's probably going to happen and Nikhil, I'm actually kind of interested why maybe your team made a conscious decision to not do this initially with SAM2.”