Please RT: postdoc positions open in the lab to work on a @ERC_Research -funded project on retinal circuits and computations. Don't hesitate to DM or email me for details. https://t.co/JhNs63DySV
Neural networks might speak English, but they think in shapes.
Understanding their rich *neural geometry* is key to understanding how they work – and to debugging and controlling them with precision.
Starting today, we’re releasing a series of posts on this research agenda. 🧵
Nice point by @TonyZador . AI is certainly a fantastic approximator, but it is unclear if it gives the level of compression necessary for understanding the brain. The question remains how much compression can we afford when trying to understand such a complex system. My take...
Prediction without understanding sustained astronomy through a thousand years of epicycles, writes @TonyZador. AI is now offering neuroscience the same deal.
https://t.co/hcs5EUhlgq
@pfau Most of his PhD work was under Michael Berry supervision, even if Bill was his official advisor. It is too early to talk about Bill legacy but I am sure there will be much more than that. 🙂
New paper: Back into Plato’s Cave
Are vision and language models converging to the same representation of reality? The Platonic Representation Hypothesis says yes. BUT we find the evidence for this is more fragile than it looks.
Project page: https://t.co/aXsm7pY9VV
1/9
In this short piece we make the case for latent equivariant operators methods✨, an alternative to classical and equivariant nets that shows promise for out-of-distrib classif. We lay out the challenges ahead for scaling these methods to larger datasets 🧐
follow @minhinhtrng 👀
Modern vision models lacks robustness when objects appear in unusual poses.
@StphTphsn1 and I study latent equivariant operators as a remedy and discuss caveats of these operators.
Below is a summary of the work, accepted at the GRaM Workshop at ICLR @iclr_conf 2026. 🧵
@_sholtodouglas@iskander@animesh_garg@UNC Hi, late to the party but we may have the same problem in my academic bio lab, happy to hear about the options here (also, if you see @DarioAmodei please say Hi from me, we worked together during his PhD 🙂 ).
How does our visual system process natural scenes ? How can we approach this question ?
Happy to share this recent review written with Samuele Virgili where we ask these questions at the level of the retina.
https://t.co/IKZiCOCy2p
Why do video models handle motion so poorly? It might be lack of motion equivariance.
Very excited to introduce: Flow Equivariant RNNs (FERNNs), the first sequence models to respect symmetries over time.
Paper: https://t.co/dkk43PyQe3
Blog: https://t.co/I1gpam1OL8
1/🧵