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

Re-post 🔁 is appreciated! #neurojobs: we’re looking for new team members to join us @cmc-unit.bsky.social!
If you’d like to study decision-making in naturalistic & embodied contexts (integrating RL, RNNs & cross-species data analysis) in a cool & collaborative research environment 😎, check 👇

Show Post

🚨 Calling all brains — biological, artificial, and everything in between! Abstract submissions are now open for the UCL NeuroAI Annual Conference 2026 🧠🤖 ⏰ Abstract deadline: 16 Oct, 12pm Come share your work with the UCL NeuroAI community! forms.cloud.microsoft/Pages/Respon...

Show Post

…if one was interested in brains to build intelligent systems, that interest may fade away as the current AI paradigm becomes more and more powerful.

Show Post

I suspect that we may all have to move towards cognitive science too some extent. Questions in the intersection or neuroscience, ML, philosophy, etc. The neuroscience questions may not make sense on their own without this context.

Show Post