druidowm
I am Owen Dugan, a physics major at MIT (class of 2025). I research at the intersection of AI and Physics.
Pinned Repositories
diffrax
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/
Gym-Snake
An OpenAI gym environment made for RL
jax-flows
Normalizing Flows in JAX 🌊
levanter
Legibile, Scalable, Reproducible Foundation Models with Named Tensors and Jax
OccamNet_Public
OccamNet_Versions
A compilation of all OccamNet versions
qiskift
A Package for Quantum Fault Tolerace in Qiskit
QuantFluNNAnalysis
Data processing and neural network training for the QuantifiedFlu project
srbench
A living benchmark framework for symbolic regression
state-spaces
Sequence Modeling with Structured State Spaces
druidowm's Repositories
druidowm/OccamNet_Public
druidowm/QuantFluNNAnalysis
Data processing and neural network training for the QuantifiedFlu project
druidowm/state-spaces
Sequence Modeling with Structured State Spaces
druidowm/OccamNet_Versions
A compilation of all OccamNet versions
druidowm/qiskift
A Package for Quantum Fault Tolerace in Qiskit
druidowm/srbench
A living benchmark framework for symbolic regression
druidowm/diffrax
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable. https://docs.kidger.site/diffrax/
druidowm/Gym-Snake
An OpenAI gym environment made for RL
druidowm/jax-flows
Normalizing Flows in JAX 🌊
druidowm/levanter
Legibile, Scalable, Reproducible Foundation Models with Named Tensors and Jax
druidowm/OccamNet_SocialSci
druidowm/mixed_autonomy_intersections
[ITSC 2021] Reinforcement Learning for Mixed Autonomy Intersections
druidowm/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
druidowm/netket
Machine learning algorithms for many-body quantum systems
druidowm/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration
druidowm/qst-cgan
Quantum state tomography with conditional generative adversarial networks
druidowm/qst-nn
Classification and reconstruction of optical quantum states with deep neural networks
druidowm/resume
druidowm/RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
druidowm/SatelliteRemoval
druidowm/v202
Proceedings of ICML 2023