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

Yeah, yeah.

I think

Definitely gonna I would say data engine is the gonna the qu the critical component that we achieve sensory performance like now.

So maybe we can go to the data engine picture.

I think we have uh kinda illustrations there.

Yeah, yeah, yeah.

So you can see that this is our annotation kind of pipeline.

So we first source the kind of the images and kinda generate the non-phases.

So this is the input of this task.

Source images and generates kind of non-phases from for example, kind of Nama generate caption and we pass the caption to get the non-phases.

This is the kind of input distribution.

Then we use

kind of sensory model in the loop to generate kind of candidates kind of masks that we kinda oh that that should be the candidate, but it's not perfect, especially in the beginning.

Then we go to kind of you can say go to the next step is verification.

So sensory give you this mask, then we need to first do mass verification to verify each mask whether it's good or not.

And then kinda

After we can filter all the bad mass, we can uh there are some good mass mass left and we verify whether this can this good mass are exhaustive or not.

Like your mark example.

So for example, the kind of bad model do not predict that kinda that partial mark, then the exhaustivity check will be uh kinda uh filling there.

Showing 61–80 of 270 · page 4 of 14