Michael Poli
23 papers · 2020–2025 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+11 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (37) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π€
Dynamic Duo
(17)
π§¬
Topic Evolution
π§
Keyword Pioneer
π
Triple Crown
π
Renaissance Researcher
(6)
π₯
Unstoppable Β· Bronze
β
The Questioner
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
π
Trend Setter
ποΈ
Keyword Collector
(130)
Top co-authors
Research topics
Machine Learning
(20)
Deep Learning
(17)
Architectures
(13)
Artificial Intelligence
(10)
Core AI
(10)
Optimization & Theory
(10)
Core Methods
(8)
Application Areas
(5)
Techniques
(5)
Learning Types Β· Machine Learning
(4)
Models
(4)
Mathematics & Optimization
(3)
Data Science & Analytics
(2)
Learning Paradigms
(2)
Learning Types Β· Deep Learning
(2)
Keywords
neural network
(5)
attention mechanism
(3)
state space model
(3)
dynamical system
(3)
language modeling
(2)
model compression
(2)
deep learning
(2)
neural differential equation
(2)
sub-quadratic complexity
(2)
optimal control
(2)
neural ordinary differential equation
(2)
model architecture
(2)
language model
(2)
image compression
(1)
neural architecture search
(1)
variational inference
(1)
shortcut learning
(1)
representation learning
(1)
in-context learning
(1)
efficient computing
(1)
Papers
Quantifying Memory Utilization with Effective State-Size
ICML 2025
STAR: Synthesis of Tailored Architectures
ICLR 2025
Mechanistic Design and Scaling of Hybrid Architectures
ICML 2024
State-Free Inference of State-Space Models: The *Transfer Function* Approach
ICML 2024
Zoology: Measuring and Improving Recall in Efficient Language Models
ICLR 2024
Deep Latent State Space Models for Time-Series Generation
ICML 2023
Effectively Modeling Time Series with Simple Discrete State Spaces
ICLR 2023
HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution
NeurIPS 2023
Hyena Hierarchy: Towards Larger Convolutional Language Models
ICML 2023
Ideal Abstractions for Decision-Focused Learning
AISTATS 2023
Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions
NeurIPS 2023
Learning Efficient Surrogate Dynamic Models with Graph Spline Networks
NeurIPS 2023
Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture
NeurIPS 2023
Monarch: Expressive Structured Matrices for Efficient and Accurate Training
ICML 2022
Neural Solvers for Fast and Accurate Numerical Optimal Control
ICLR 2022
Self-Similarity Priors: Neural Collages as Differentiable Fractal Representations
NeurIPS 2022
Transform Once: Efficient Operator Learning in Frequency Domain
NeurIPS 2022
Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective
ICLR 2022
Differentiable Multiple Shooting Layers
NeurIPS 2021
Neural Hybrid Automata: Learning Dynamics With Multiple Modes and Stochastic Transitions
NeurIPS 2021
Dissecting Neural ODEs
NeurIPS 2020
Hypersolvers: Toward Fast Continuous-Depth Models
NeurIPS 2020
WATTNet: Learning to Trade FX via Hierarchical Spatio-Temporal Representation of Highly Multivariate Time Series
IJCAI 2020