Pengchuan Zhang

speaker

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

Pengchuan Zhang’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

And then I want kinda reflections and then I can kinda with the kind of the default kind of threshold, maybe kinda the kinda the model will get an output.

Then another kind of very strong kind of perception model on other kinda

So like kinda gymnastic will then kinda ask we ask Gymnasium whether there's kinda sound reflection there.

And if this yes, then we can then you can see that we can automatically snot kinda move the threshold can lower and gonna ask again gymnastic again and again to see whether kinda the reflection is not included or not.

So somehow this process can possibly should be done kinda completely with AI.

Kind of

see.

Yeah, yeah, exactly.

pretty excited about Yeah, maybe I want to echo kind of what Joseph said.

This is also my experience.

Just different people have quite different kinda

definition of even a visual concept.

For example, for some kind of data set, even hand.

And some people would like to kinda just kinda annotate the palm kind of part as kind of the hand.

And some people will can include the arm kinda also kinda as hand.

Then when we can first test some slowing on kind of some very kind of customized data set, we found okay the performance is not that good.

And when we can finally look into kinda the

kind of performance.

We found okay this is kinda just the user have a def different definition or explanation of the concepts.

But kind of both explanations are okay.

Showing 241–260 of 270 · page 13 of 14