Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systems
Paper • 2502.17019 • Published
Max Zhdanov PRO
maxxxzdn
AI & ML interests
scalable architectures for large-scale simulations, hierarchical representations, geometric deep learning
Recent Activity
authored a paper 4 days ago
Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systems authored a paper 4 days ago
Clifford-Steerable Convolutional Neural Networks authored a paper 4 days ago
BSA: Ball Sparse Attention for Large-scale GeometriesOrganizations
authored 3
papers 4 days ago
updated a
Space 4 days ago
published a
Space 4 days ago
liked a
model 11 days ago
authored 3
papers 13 days ago
(Sparse) Attention to the Details: Preserving Spectral Fidelity in ML-based Weather Forecasting Models
Paper • 2604.16429 • Published • 2
MSPT: Efficient Large-Scale Physical Modeling via Parallelized Multi-Scale Attention
Paper • 2512.01738 • Published • 1
Follow the Mean: Reference-Guided Flow Matching
Paper • 2605.10302 • Published • 5
upvoted a paper 14 days ago
updated a
model 14 days ago
updated a
Space 14 days ago
upvoted a paper 14 days ago
updated a
dataset 15 days ago
published a
Space 16 days ago
published a
dataset 17 days ago
published a
model 19 days ago