Niru Maheswaranathan

here is sora, our video generation model: openai.com/sora today we are starting red-teaming and offering access to a limited number of creators. @_tim_brooks @billpeeb @model_mechanic are really incredible; amazing work by them and the team. remarkable moment.

I'll be in Lisbon along with great team of our scientists including @SussilloDavid @niru_m @CLWarriner @diogo_neuro @DiegoGutnisky @najabam. Long overdue to talk science in person!

Gradients without Backpropagation Presents a method to compute gradients based solely on the directional derivative that one can compute exactly and efficiently via the forward mode, entirely eliminating the need for backpropagation in gradient descent. arxiv.org/abs/2202.08587

New work out on bioRxiv (biorxiv.org/content/10.110…) on the geometry of representational drift in natural and artificial neural networks. Work done with Marina Garrett (@matchings), Shawn Olsen, and Stefan Mihalas (@Stefan_Mihalas) at the @AllenInstitute. 🧵

#tweeprint time for our new work out on arXiv!📖We've been trying to understand how recurrent neural networks (RNNs) work, by reverse engineering them using tools from dynamical systems analysis—with @SussilloDavid. arxiv.org/abs/2004.08013