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 monthsRecordings per month over the last 12 months — 1 in all, peaking in Dec 2025 with 1.
Appearances
Yeah yeah.
The second thing is video.
I would say that we video is f still far from I w would say have a big gap from human performance.
Right now, there's kinda still kinda a lot of research needs to be done there how to do end to end training with video we do not have and kinda we have this kinda decoupled approach, but we do not end to end train this model and we expect definitely.
kinda it will be kinda uh a benefit from kinda entertain training and also as we dis kinda on video side learning kinda how to scale up the data engine we need kinda definitely kinda AI annotators for video.
We tried that but yeah we can I I think that's that's something and definitely worthwhile to do.
The third one we also discussed about that how sensory how perception fit into ATI.
this big landscape.
Now we have the eye, how the eye work with the brain to do to solve real kind of reasoning tasks.
Not only output segmentation, but really kinda answer how many cases are here or even answer the question, okay, I can I have an example of kinda bio um biology naps.
Kind of the robots need to decide whether can they can liquid in the can test tube is uh can add
they kinda crack never or not.
You can see that this is kinda involved perception but also involves reasoning.
How to kinda solve this more kinda kinda visual reasoning task with sun is kinda a very big direction.
Can you imagine such kinda s such pipeline coming, for example, as kinda Swick said that maybe kinda the reflection is exactly what I want, then you need some kinda iterations with the kinda the interface or the model or to kinda to get finally what you need.
So you need to specify the concept kinda more clearly.
through kinda multiple iterations.
Can human not be involved in this iteration, but just kinda models e i uh in uh just kinda do it automatically.
I think that's kinda something kinda definitely gonna it's
I would see I'm quite interested in that you can imagine this workflow.
Showing 221–240 of 270 · page 12 of 14
← Previous
Next →