Statistical Learning
Provably Optimal Memory Capacity for Modern Hopfield Models: Transformer-Compatible Dense Associative Memories as Spherical Codes Jerry Y ao-Chieh Hu Dennis Wu
We study the optimal memorization capacity of modern Hopfield models and Kernelized Hopfield Models (KHMs), a transformer-compatible class of Dense Associative Memories.
GEPS: Boosting Generalization in Parametric PDE Neural Solvers through Adaptive Conditioning
We demonstrate the versatility of our approach for both fully data-driven and for physics-aware neural solvers.
Self-Distilled Depth Refinement with Noisy Poisson Fusion Jiaqi Li1, Yiran Wang
With noisy depth predictions as input, SDDR generates low-noise depth edge representations as pseudo-labels by coarse-to-fine self-distillation.
Continual Learning with Global Alignment
Specifically, we learn the data representation as a task-specific composition of pre-trained token representations shared across all tasks. Then the correlations between different tasks' data representations are grounded
