wavelet

This paper proposes learnable wavelet activations to combat plasticity loss in continual learning, decomposing activations into low- and high-frequency components with dynamic injection and regularization, achieving state-of-the-art results on benchmarks.

This paper introduces LiNO, a neural operator that uses a lifting-based multiresolution decomposition to learn solution operators for PDEs. It demonstrates strong performance on benchmarks including Darcy flow, Poisson equation, and Navier-Stokes, capturing both global dynamics and fine-scale structure.

WaveDiT is a conditional flow matching framework for full-resolution 3D brain MRI synthesis that operates in wavelet coefficient space, enabling efficient generation on standard GPUs without lossy latent compression. It achieves improved alignment with real MRI distributions and downstream tasks.

This paper proposes Energy-Gated Attention (EGA) and Morlet Positional Encoding (MoPE) to address missing inductive biases in transformer attention: token salience and scale-adaptive locality. Experiments on TinyShakespeare show superadditive gains when combined, highlighting complementarity.

libwce is a minimal, patent-clean Rust library implementing a Bit-Plane Count (BPC) entropy layer for wavelet codecs, providing a stateless and dependency-free module for entropy coding.

Dywave is a dynamic tokenization framework for IoT sensing signals that uses wavelet-based hierarchical decomposition to align tokens with semantic events, achieving up to 12% higher accuracy and 75% reduction in input token length on five real-world datasets.