RoVE: Rotary Value Embeddings Attention for Relative Position-dependent Value Pathways
Paper • 2606.11275 • Published • 1
Max Zhdanov PRO
maxxxzdn
AI & ML interests
scalable architectures for large-scale simulations, hierarchical representations, geometric deep learning
Recent Activity
upvoted a paper 28 days ago
RoVE: Rotary Value Embeddings Attention for Relative Position-dependent Value Pathways authored a paper about 1 month ago
Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systems authored a paper about 1 month ago
Clifford-Steerable Convolutional Neural NetworksOrganizations
upvoted a paper 28 days ago
authored 3
papers about 1 month ago
updated a
Space about 1 month ago
published a
Space about 1 month ago
liked a
model about 2 months ago
authored 3
papers about 2 months 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 about 2 months ago
updated a
model about 2 months ago
updated a
Space about 2 months ago
upvoted a paper about 2 months ago
updated a
dataset about 2 months ago
published a
Space about 2 months ago
published a
dataset about 2 months ago
published a
model about 2 months ago