Here's the thing. We have **NO IDEA** how to pick good graduate students. I served on admission committees for 10+ years, and chaired a few, and what I learned is that all the spreadsheets of grades and test scores and recommendations and essays and publications and interview

WeatherMesh-2, a record-breaking new AI forecasting model, predicting weeks of forecast in seconds! WM-2 uses a 3-D transformer with neighborhood attention. Very happy to see NATTEN in application. Congratulations to WindBorne Systems and John Dean !

Question: For #CVPR what constitutes "highly irresponsible"? Would it be "highly irresponsible" for a reviewer to list under "Major Weaknesses": "symbols are not defined, e.g. ∑" I am having a hard time processing this. This can't be a serious complaint.

Sometimes unpopular things need to be said out loud. In an electoral reform landscape where Ranked Choice Voting has long been the emperor with no clothes, Equal Vote was one of the first organizations to speak out. 1/7 🧵

It indicates a fundamental limitation.

I shared a controversial take the other day at an event and I decided to write it down in a longer format: I’m afraid AI won't give us a "compressed 21st century". The "compressed 21st century" comes from Dario's "Machine of Loving Grace" and if you haven’t read it, you probably

Over 4 years into our journey bridging Convolutions and Transformers, we introduce Generalized Neighborhood Attention—Multi-dimensional Sparse Attention at the Speed of Light: github.com/SHI-Labs/NATTEN A collaboration with the best minds in AI and HPC. 🐝🟩🟧 Georgia Tech Computing NVIDIA

You can now call me Doctor. You don't have to, but you /can/

Got the #CVPR outstanding reviewer award! There's a lot of noise in the reviewing process, so write the review you wish you received. Finding flaws is easy, but review is about the progress and making the work the best it can be. Remember, we're all on the same team.