Don’t ever judge a book by its cover 📚

🤖While recent works tackle the memory efficiency at the expense of time (GaLore), or time efficiency at the expense of performance (BAdam), our work which tracks the gradient subspace using the Gradsmannian geometry to get you BOTH memory AND time efficiency while being performant!

🌱 Watching the exponential rise in the attendance at Women in Engineering (WiE) socials over the past few months is so heartwarming, and a testament to the strong #WiE community at the University of Waterloo

🤖 I often talk to companies and organizations who want to use #AI/#ML in their workflows. But before they can leverage these powerful tools, they need to become #data-centric, and what I call — #AIReady

💭Okay, I have to say this. NYT (and I am sure some other news outlets) coming out NOW with articles and opinion pieces titled “How does tyranny begin?” is so jarring and infuriating. #Canadian media — I am also looking at you.

🚨 Early Career Researchers @neuripsconf.bsky.social

Continuing the tradition from #icml, if you are an early career researcher looking to meet, use #whova for #neurips to join or DM me, let’s catch-up 🙌

Even if you are not at NeurIPS, feel free to post (here) which superpower you would like!

🚨Postdoc Position Alert

I am looking for a postdoc in the area of #ML and #CV for an #AI for manufacturing project with a large electronics device company.
We have a very talented group of students, and you will be working with real data, making real impact.

I’ll be at #NeurIPS. DM for details ✌️