*A community benchmark enables high-resolution, cross-lab quantification of mouse social behavior* Introducing HiDRA: 82 supervised classifier heads for 33 dyadic and solitary behaviors. Works out-of-the-box on new data and outperforms video foundation models. neuroethology.github.io/hidra-site/

Show Post

Looking for a PhD program where you can study vision from different perspectives (computer vision, visual neuroscience, visual perception, image processing)? Consider applying to NYU! visionscience.com/pipermail/vi...

Show Post

Mathematical proof dates back to Euclid in 300 BCE, yet little is known about what happens in the mind when humans solve proofs. This week, an SFI working group brought together mathematicians, cognitive scientists, computer scientists, and philosophers to ask what it means to understand a proof.

Show Post

How much representational diversity exists around a trained network? A lot, it turns out! Moving a ViT’s weights by 1.3% while preserving its predictions, its representations end up less similar to the original than a random-init ViT’s ‼️ New paper: Hessian Null Space Continuation (HNC) 💫🧵 (1/12)

Show Post

Some exciting new work: arxiv.org/abs/2610.12426 On X, I shared some explanation and broader thoughts: x.com/d_g_clark/st... Additionally, an X user made an extremely good 3Blue1Brown-style explainer video. Each step is described accurately and beautifully: x.com/nachilos_/st...

Show Post