Durk Kingma
@dpkingma.bsky.social
Research scientist at Anthropic. Prev. Google Brain/DeepMind, founding team OpenAI. Computer scientist; inventor of the VAE, Adam optimizer, and other methods. ML PhD. Website: dpkingma.com
Reposted by Durk Kingma
In arxiv.org/abs/2303.00848, @dpkingma.bsky.social and @ruiqigao.bsky.social had suggested that noise augmentation could be used to make other likelihood-based models optimise perceptually weighted losses, like diffusion models do. So cool to see this working well in practice!
December 2, 2024 at 6:36 PM
In arxiv.org/abs/2303.00848, @dpkingma.bsky.social and @ruiqigao.bsky.social had suggested that noise augmentation could be used to make other likelihood-based models optimise perceptually weighted losses, like diffusion models do. So cool to see this working well in practice!
It's 2024 and microwave ovens still heat food unevenly. I need a phased array microwave oven that warms food evenly, adaptively. Who is building this?
November 26, 2024 at 5:08 PM
It's 2024 and microwave ovens still heat food unevenly. I need a phased array microwave oven that warms food evenly, adaptively. Who is building this?
I don't usually talk about politics, but if I could change one thing in the US democracy, it might be replacing winner-takes-all representation with proportional representation. Would fix a lot of issues. Agree or disagree that this would be a net positive change?
November 20, 2024 at 8:27 PM
I don't usually talk about politics, but if I could change one thing in the US democracy, it might be replacing winner-takes-all representation with proportional representation. Would fix a lot of issues. Agree or disagree that this would be a net positive change?