pierrelucbacon.bsky.social
@pierrelucbacon.bsky.social
Reposted
Special thanks to Biogen and CIFAR for the support, and
@proceduralia.bsky.social + @pierrelucbacon.bsky.social
for their valuable supervision, and to the entire Mila community for their feedback, discussions, and support. Code, paper, and models are public: github.com/ddidacus/mol...
GitHub - ddidacus/mol-moe: Repository for: "Training Preference-Guided Routers for Molecule Generation"
Repository for: "Training Preference-Guided Routers for Molecule Generation" - ddidacus/mol-moe
github.com
February 20, 2025 at 7:43 PM
Reposted
Exactly this. So much private innovation is really just repackaged public innovation. So by scrapping public funding, we risk scrapping future economic gains as well.
A *2011* grant from NSERC Research Tools and Instruments, for 60000 CAD, to Geoff Hinton (@geoffreyhinton.bsky.social)

For "Large scale machine learning using GPUs"

Everything you're seeing now started from a pittance of cash given by the Canadian government for fundamental research
February 8, 2025 at 10:15 AM
Again, Sutton said it first: "Verification, The Key to AI" incompleteideas.net/IncIdeas/Key...

The bitter lesson became clear with LLMs, and now verification is all the rage in reasoning models. Sutton's insight (2001 !) was, as always, prescient.
Self-Verification, The Key to AI
incompleteideas.net
January 27, 2025 at 3:13 PM