Ann Huang

annhuang42.bsky.social

14 October 2026 17:42

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)

David G. Clark

david-g-clark.bsky.social

10 October 2026 21:22

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...

UniReps

unireps.bsky.social

06 October 2026 16:43

🔵🔴 Join us for the 4th edition of UniReps on December 12, 2026, in Paris! Working on these or similar topics? Submit your paper by the extended deadline: October 10 (AoE) Submit at: t.co/lA6ci1epeF full CFP: t.co/EvBFdvZfLu

Eric Maugendre

data.yt

05 October 2026 08:30

System thinking and inference with context (continued) For statisticians, here is a nice video that promotes double descent: www.youtube.com/watch?v=z64a... For statisticians then, here is a beautiful "Escape Dimensions Theory":

Shahab Bakhtiari

shahabbakht.bsky.social

04 October 2026 12:37

I had a feeling recently that seems to be corroborated by chats with colleagues, so I decided to share it here. A lot of systems neuroscientists driven by algorithmic-level questions are going through what looks and feels like a research depression. 🧵 (1/n) 🧠📈 #NeuroAI