Andrew Gordon Wilson

andrewgwils.bsky.social

05 March 2025 15:38

My new paper "Deep Learning is Not So Mysterious or Different": arxiv.org/abs/2503.02113. Generalization behaviours in deep learning can be intuitively understood through a notion of soft inductive biases, and formally characterized with countable hypothesis bounds! 1/12

Eugene Vinitsky 🍒

eugenevinitsky.bsky.social

01 March 2025 20:57

Tbc, it cannot.

Eugene Vinitsky 🍒

eugenevinitsky.bsky.social

01 March 2025 20:57

Burning all of OpenAI’s compute to write a seven page essay about whether “burrata pizza can be reheated in the oven.” DeepResearch is so fun.

angela zhou

angelamczhou.bsky.social

28 February 2025 12:57

briefly back in nyc for a collab visit. crawling into the subway in the morning w a giant coffee and one- handed shoving a giant cardamom bun in my mouth like a small feral animal. True Freedom

Itzik Ben Shabat

sitzikbs.bsky.social

27 February 2025 23:21

1/ Please, please stop the trend of tweeting "X papers accepted to CVPR." This practice creates a harmful sense of self-worth for PhD students who didn’t make it in. It’s demoralizing and does more harm than good for our community.