Sotabase

Career

· CEO, Radical Numerics2021–
· PhD Student, Stanford University2021–2025
· Founding Scientist, Liquid AI2018–2020

Publications (60)

Hyena Hierarchy: Towards Larger Convolutional Language Models
International Conference on Machine Learning · 2023
437
cited
HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution
Neural Information Processing Systems · 2023
423
cited
Dissecting Neural ODEs
Neural Information Processing Systems · 2020
238
cited
Graph Neural Ordinary Differential Equations
arXiv.org · 2019
199
cited
Monarch: Expressive Structured Matrices for Efficient and Accurate Training
International Conference on Machine Learning · 2022
116
cited
Effectively Modeling Time Series with Simple Discrete State Spaces
International Conference on Learning Representations · 2023
71
cited
Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture
Neural Information Processing Systems · 2023
67
cited
Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective
International Conference on Learning Representations · 2021
62
cited
Deep Latent State Space Models for Time-Series Generation
International Conference on Machine Learning · 2022
53
cited
Hypersolvers: Toward Fast Continuous-Depth Models
Neural Information Processing Systems · 2020
50
cited
Stable Neural Flows
arXiv.org · 2020
38
cited
Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions
Neural Information Processing Systems · 2023
29
cited
TorchDyn: A Neural Differential Equations Library
arXiv.org · 2020
25
cited
Transform Once: Efficient Operator Learning in Frequency Domain
Neural Information Processing Systems · 2022
24
cited
Neural Ordinary Differential Equations for Intervention Modeling
arXiv.org · 2020
21
cited
Differentiable Multiple Shooting Layers
Neural Information Processing Systems · 2021
20
cited
Optimal Energy Shaping via Neural Approximators
SIAM Journal on Applied Dynamical Systems · 2021
17
cited
Port–Hamiltonian Approach to Neural Network Training
IEEE Conference on Decision and Control · 2019
14
cited
Neural Hybrid Automata: Learning Dynamics with Multiple Modes and Stochastic Transitions
Neural Information Processing Systems · 2021
11
cited
Learning Stochastic Optimal Policies via Gradient Descent
IEEE Control Systems Letters · 2021
10
cited
Sotabase
Michael Poli | Researcher Profile | Sotabase | Sotabase