Andy Keller
@t_andy_keller
Postdoctoral Fellow at The Kempner Institute at Harvard University -- Somewhere between Brains & Bits. PhD at UvA, Intern @ Apple MLR, Prev @ Intel AI & Nervana
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: arxiv.org/abs/2507.14793 Blog: kempnerinstitute.harvard.edu/research/deepe… 1/🧵
Equivariance meets RNNs. An exciting research direction!
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: arxiv.org/abs/2507.14793 Blog: kempnerinstitute.harvard.edu/research/deepe… 1/🧵
New in the #DeeperLearningBlog: #KempnerInstitute research fellow @t_andy_keller introduces the first flow equivariant neural networks, which reflect motion symmetries, greatly enhancing generalization and sequence modeling. bit.ly/451fQ48 #AI #NeuroAI
General relativity 🤝 neural fields This simulation of a black hole is coming from our neural networks 🚀 We introduce Einstein Fields, a compact NN representation for 4D numerical relativity. EinFields are designed to handle the tensorial properties of GR and its derivatives.
Our new ICML 2025 oral paper proposes a new unified theory of both Double Descent and Grokking, revealing that both of these deep learning phenomena can be understood as being caused by prime numbers in the network parameters 🤯🤯 🧵[1/8]
'Origins of Creativity in Attention-Based Diffusion Models' Emma Finn, @t_andy_keller, @manos_theo, @dunbar_ba doi.org/10.48550/arXiv… (7/21)