Michael Poli

Orcid: 0000-0001-5384-9372

According to our database1, Michael Poli authored at least 28 papers between 2019 and 2024.

Collaborative distances:

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
Mechanistic Design and Scaling of Hybrid Architectures.
CoRR, 2024

2023
Zoology: Measuring and Improving Recall in Efficient Language Models.
CoRR, 2023

HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Learning Efficient Surrogate Dynamic Models with Graph Spline Networks.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Deep Latent State Space Models for Time-Series Generation.
Proceedings of the International Conference on Machine Learning, 2023

Hyena Hierarchy: Towards Larger Convolutional Language Models.
Proceedings of the International Conference on Machine Learning, 2023

Effectively Modeling Time Series with Simple Discrete State Spaces.
Proceedings of the Eleventh International Conference on Learning Representations, 2023

Ideal Abstractions for Decision-Focused Learning.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022
Optimal Energy Shaping via Neural Approximators.
SIAM J. Appl. Dyn. Syst., September, 2022

Learning Stochastic Optimal Policies via Gradient Descent.
IEEE Control. Syst. Lett., 2022

Self-Similarity Priors: Neural Collages as Differentiable Fractal Representations.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Transform Once: Efficient Operator Learning in Frequency Domain.
Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Monarch: Expressive Structured Matrices for Efficient and Accurate Training.
Proceedings of the International Conference on Machine Learning, 2022

Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective.
Proceedings of the Tenth International Conference on Learning Representations, 2022

Neural Solvers for Fast and Accurate Numerical Optimal Control.
Proceedings of the Tenth International Conference on Learning Representations, 2022

2021
Continuous-Depth Neural Models for Dynamic Graph Prediction.
CoRR, 2021

Neural Hybrid Automata: Learning Dynamics With Multiple Modes and Stochastic Transitions.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Differentiable Multiple Shooting Layers.
Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020
Neural Ordinary Differential Equations for Intervention Modeling.
CoRR, 2020

TorchDyn: A Neural Differential Equations Library.
CoRR, 2020

Stable Neural Flows.
CoRR, 2020

Hypersolvers: Toward Fast Continuous-Depth Models.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Dissecting Neural ODEs.
Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

2019
Graph Neural Ordinary Differential Equations.
CoRR, 2019

WATTNet: Learning to Trade FX via Hierarchical Spatio-Temporal Representation of Highly Multivariate Time Series.
CoRR, 2019

Port-Hamiltonian Approach to Neural Network Training.
Proceedings of the 58th IEEE Conference on Decision and Control, 2019


  Loading...