Ethan He
speaker
722 appearances
1 recordings
1 series
first heard Jun 2026
last heard 1 Jun
Ethan He’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 Jun 2026 with 1.
Appearances
So I still remember in Cosmos, I generated a happy sheep.
Without any rewriting, it looks so CGI.
And after rewriting, it looks so beautiful.
Without any joint training?
Yeah, actually without any joint training.
With rewriting, it's already much better.
A very interesting thing, I guess, will happen is video agents, mostly language models, will call these generative models, either it's a separate model or a diffusion head or whatever, as a tool.
So this model can iteratively refine the results or even generate longer content through a very long trend of thought.
It's actually very similar to how humans create art.
So we don't generate the pixels directly.
We iteratively draw something.
And I think through this process, these models not only use
diffusion as one of the tool.
It can also use traditional tool.
It can also use image editing tools from Photoshop.
You can use video editor, FFmpeg, whatever to take combination of these and the generative AI technology as a set of tool and they can
they can iteratively create a much better video for production-grade quality.
If you look at existing professional creators, they don't end up generating a video from these models.
They will take this video to their editor and edit here and there.
So much post-production.
Showing 581–600 of 722 · page 30 of 37
← Previous
Next →