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.
Exactly.
For example, you can see that we already kinda in our sensory agents or kinda in our AI annotator we even demonstrate this approach.
And kinda for simple cases, the model can do it by itself that okay, I can detect, for example, ten people here.
And then the natural m language model can even the AI annotator can even know that okay, this ten people is not exhaustive.
Okay, there are more people there.
So if you want to do kind of
well, then maybe kinda you need to do more step.
For example, kinda to call an extra model.
So you can see that this is a very, very kinda native kind of true uh kind of reasoning process for for more advanced or complicated vision questions.
I have a related but maybe
Maybe can I can first talk something and then Nikina can add.
First definitely kinda I think even it's not some four, it's science three something and science three point something like small models.
Science three currently only have really kinda one model, uh kinda one size model, kinda more kinda efficient model that's kinda fit for kinda eight cases and also kinda m a more efficient model for video.
I think currently kinda they
video model is not efficient.
You either you can't achieve very good kind of throughput, but you need GPUs to do that.
So first kind of small and efficient models, that's one kind of big thing.
The second big thing is definitely kind of radio.
RoboFood can do that for you.
Showing 201–220 of 270 · page 11 of 14
← Previous
Next →