arXiv Machine Learning June 30, 2026 By Alex Costanzino, Pierluigi Zama Ramirez, Giuseppe Lisanti, Luigi Di Stefano

Spectral Gating via Damped Oscillations for Adaptive Implicit Neural Representations

Read the original on arXiv Machine Learning →

arXiv:2606. 23129v2 Announce Type: replace-cross Abstract: Implicit Neural Representations (INRs) have been proven successful in encoding continuous signals through coordinate-based networks, yet facing a spectral dilemma: periodic activations capture fine details but act as all-pass filters that memorise noise, while spatially compact activations regularise effectively but suffer from low-frequency bias.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 16

RepNet: Tackling spectral bias in deep neural networks via parameter reparameterization

arXiv:2606. 16575v1 Announce Type: new Abstract: Deep neural networks (DNNs) have achieved remarkable success in scientific computing, yet they often suffer from spectral bias in capturing oscillatory and multiscale behaviors.

By Yong Wang, Tao Zhou, Xuhui Meng

safety

arXiv AI

Jun 11

SirenFNO: Efficient and Full Frequency Learning of Fourier Neural Operators

arXiv:2606. 11518v1 Announce Type: cross Abstract: Fourier neural operators (FNOs) are effective and efficient surrogates for approximating solutions of PDEs and generalize across discretizations.

By Pengqing Shi, Jie Yin, Stephen Tierney, Junbin Gao

benchmarks safety

arXiv Machine Learning

Jul 28

Frequency-Based Reservoir computing

arXiv:2607. 24420v1 Announce Type: cross Abstract: Reservoir computing has emerged as an efficient machine learning framework for predicting time series generated by dynamical systems.

By Arthur S Powanwe

arXiv AI

Jul 15

Sparse Inter-Layer Dependencies of Transformer FFN Neurons

arXiv:2607. 11990v1 Announce Type: cross Abstract: Feedforward network (FFN) blocks account for a large fraction of the parameters and computation in Transformer architectures, yet their internal structure remains difficult to interpret due to the additive superposition induced by the residual stream.

By Johannes Knittel, Hanspeter Pfister

llms efficiency safety

arXiv Machine Learning

5d ago

Sustaining Plasticity via Learnable Wavelet Activations in Continual Learning

arXiv:2608. 12874v1 Announce Type: new Abstract: Plasticity loss has emerged as a critical challenge in continual learning that significantly hinders the acquisition of sequential tasks.

By Zeyang Zhang, Tieliang Gong, Junyan Lu, Weizhan Zhang

benchmarks safety

Hugging Face Trending Papers

Jul 23

Recurrent Sinusoidal INRs for Efficient High-Fidelity Representation

We study sinusoidal recurrence as an iterative mechanism for harmonic spectral enrichment in implicit neural representations (INRs). Our analysis reveals that sinusoidal activations induce a harmonic line spectrum, providing a spectral account of how recurrent unrolling enriches the effective spectral support.

benchmarks

Related stories

RepNet: Tackling spectral bias in deep neural networks via parameter reparameterization

SirenFNO: Efficient and Full Frequency Learning of Fourier Neural Operators

Frequency-Based Reservoir computing

Sparse Inter-Layer Dependencies of Transformer FFN Neurons

Sustaining Plasticity via Learnable Wavelet Activations in Continual Learning

Recurrent Sinusoidal INRs for Efficient High-Fidelity Representation