How? I'm adding new videos, deep dives & behind-the-scenes stories to Talking Climate.
Why? Because climate honesty and hope matter more than ever right now.
Join me on Patreon: bit.ly/47pCLaf
Or Substack: bit.ly/4ntfvhJ
How? I'm adding new videos, deep dives & behind-the-scenes stories to Talking Climate.
Why? Because climate honesty and hope matter more than ever right now.
Join me on Patreon: bit.ly/47pCLaf
Or Substack: bit.ly/4ntfvhJ
Meet Seaweed-APT2: an 8B-param autoregressive GAN that streams 24fps video at 736×416—all in *1 network forward eval*. That’s 1440 frames/min, live, on a single H100 🚀
Project: seaweed-apt.com/2
Meet Seaweed-APT2: an 8B-param autoregressive GAN that streams 24fps video at 736×416—all in *1 network forward eval*. That’s 1440 frames/min, live, on a single H100 🚀
Project: seaweed-apt.com/2
Meanwhile the FTC: www.ftc.gov/news-events/...
Meanwhile the FTC: www.ftc.gov/news-events/...
People are always a bit surprised by that.
People are always a bit surprised by that.
I have equipped it with a @sipmask.bsky.social port so I can drink.
I have equipped it with a @sipmask.bsky.social port so I can drink.
Enter IntrinsicEdit: Precise generative image manipulation in intrinsic space (SIGGRAPH 2025)!
intrinsic-edit.github.io
Enter IntrinsicEdit: Precise generative image manipulation in intrinsic space (SIGGRAPH 2025)!
intrinsic-edit.github.io
Discover MUSt3R & Pow3R, universal encoder DUNE + research in navigation, vizloc, segmentation & human motion understanding!
All our #CVPR2025 papers are here
➡️ tinyurl.com/4z79ujce
Discover MUSt3R & Pow3R, universal encoder DUNE + research in navigation, vizloc, segmentation & human motion understanding!
All our #CVPR2025 papers are here
➡️ tinyurl.com/4z79ujce
Conference papers:
PromptHMR: Promptable Human Mesh Recovery
yufu-wang.github.io/phmr-page/
DiffLocks: Generating 3D Hair from a Single Image using Diffusion Models
radualexandru.github.io/difflocks/
Conference papers:
PromptHMR: Promptable Human Mesh Recovery
yufu-wang.github.io/phmr-page/
DiffLocks: Generating 3D Hair from a Single Image using Diffusion Models
radualexandru.github.io/difflocks/
The paper is rather critical of reasoning LLMs (LRMs):
x.com/MFarajtabar...
The paper is rather critical of reasoning LLMs (LRMs):
x.com/MFarajtabar...
Let's dive in! 👇
Let's dive in! 👇
I just want to emphasize that devs working at Builder .ai most likely did not know about the accounting fraud part. They joined a hot AI startup, and did the best work they could.
I just want to emphasize that devs working at Builder .ai most likely did not know about the accounting fraud part. They joined a hot AI startup, and did the best work they could.
The world’s biggest AI Robotics Hackathon is almost here!
2,000+ builders, coders, dreamers are joining June 14–15
One rule: build, learn and have fun together!
Find your local hackathon & team up
Register now: forms.gle/NP22nZ9knKC...
The world’s biggest AI Robotics Hackathon is almost here!
2,000+ builders, coders, dreamers are joining June 14–15
One rule: build, learn and have fun together!
Find your local hackathon & team up
Register now: forms.gle/NP22nZ9knKC...
Just another reminder: the top-performing countries on climate action all use proportional representation.
It's time to get on board, not just for democracy, but for the future of the planet.
Just another reminder: the top-performing countries on climate action all use proportional representation.
It's time to get on board, not just for democracy, but for the future of the planet.