Home Knowledge Base Frequency Attention

Frequency Attention

No mentions found

This entity hasn't been tracked yet, or Iris is still building its knowledge base.

Related Articles from SNS

Frequency-Domain Latent Attention Gating for Cross-Domain Token Aggregation

arXiv:2606.08191v1 Announce Type: new Abstract: Token aggregation is a common bottleneck in models that map token representations to sample-level predictions, yet most pooling methods operate only in the original token domain. We propose FLaG, a plug-in aggregation module that transforms token representations with the real FFT, summarizes spectral components with learnable latent queries, applies a channel-wise gate, and reconstructs enhanced time-domain tokens for final pooling.

arXiv CS 1d ago

ReFLEX: Length-Generalizable CSI Denoising for MIMO-OFDM via Relative-Frequency Bias

arXiv:2606.00263v1 Announce Type: cross Abstract: This letter studies CSI denoising for MIMO--OFDM with variable NR resource block (RB) allocations. ReFLEX is a length-generalizable Transformer whose frequency attention uses a relative-frequency position bias (RFPB) generated from subcarrier offsets. A single checkpoint handles unseen RB lengths and can be applied to sparse DM-RS observations in the tested RB5/

arXiv CS 8d ago

Deconstructing the Composite Channel for Beyond Diagonal RIS: Channel Estimation and Beamforming Design

arXiv:2606.01564v1 Announce Type: cross Abstract: As beyond-diagonal reconfigurable intelligent surfaces (BD-RISs) gain increasing attention in high-frequency wireless communications, accurate and scalable channel-estimation methods become essential. This paper develops a parametric channel-estimation and beamforming framework that deconstructs the composite BD-RIS channel into its generating directional factors, revealing the tensor structure induced jointly by propagation geometry and...

arXiv CS 8d ago

SRENet: Spectral Re-Entry Network for Point Cloud Action Recognition

arXiv:2606.03160v1 Announce Type: new Abstract: Recognizing human actions from point cloud sequences is critical for 3D perception driven applications such as autonomous driving and human-computer interaction. However, the irregular structure and temporal inconsistency of point clouds pose unique challenges for spatio-temporal representation learning, especially in capturing both global motion context and fine-grained temporal dynamics. We propose SRENet, a spectral-aware framework designed...

arXiv CS 7d ago

FSM-Net: An Efficient Frequency-Spatial Network for Real-World Deblurring

arXiv:2605.31400v1 Announce Type: new Abstract: Real-world image deblurring demands both high-fidelity restoration and computational efficiency, a balance existing methods often struggle to achieve. In this paper, we propose FSM-Net (Frequency-Spatial Multi-branch Network), a highly efficient solution that secured 2nd place in the NTIRE 2026 Challenge on Efficient Real-World Deblurring.

arXiv CS 9d ago

Hamiltonian-Inspired Attention Mechanism for Scalable RF Transmitter Fingerprinting

Announce Type: cross Abstract: Radio-frequency (RF) fingerprinting identifies wire-less transmitters using hardware-induced imperfections present in baseband I/Q signals. However, deep learning models often degrade under receiver and channel distribution shifts, particularly as transmitter populations grow. This work proposes the Hamiltonian Transformer, a physics-informed attention architecture that enforces norm preserving value dynamics within each attention head using a learned...

arXiv CS 9d ago

Wavelet Fourier Diffuser: Frequency-Aware Diffusion Model for Reinforcement Learning

Announce Type: replace Abstract: Diffusion probability models have shown significant promise in offline reinforcement learning by directly modeling trajectory sequences. However, existing approaches primarily focus on time-domain features while overlooking frequency-domain features, leading to frequency shift and degraded performance according to our observation. In this paper, we investigate the RL problem from a new perspective of the frequency domain.

arXiv CS 7d ago

Med-URWKV{\dag}: Toward Enhanced Pretrained Pure VRWKV Models for Medical Image Segmentation

arXiv:2506.10858v2 Announce Type: replace-cross Abstract: Medical image segmentation is a fundamental task in computer-aided diagnosis and treatment. Existing approaches based on CNNs, ViTs, Mamba, and hybrid models still suffer from limitations such as restricted receptive fields, high computational cost, or insufficient accuracy. Recently, Vision Receptive-field Weighted Key-Value (VRWKV) models have emerged as a promising alternative,delivering strong long-range dependency modeling for...

arXiv CS 8d ago

Retrieval and competition: how a protein foundation model starts a protein

Announce Type: replace-cross Abstract: Protein language models are increasingly used to guide experimental and clinical decisions, yet it is often unclear whether a confident prediction reflects recognition of biological evidence or retrieval of a statistical default. We examine this distinction for a near-universal biological rule, that proteins begin with methionine, by tracing the computational pathway through which ESM2-8M produces this prediction. The model does not detect methionine at...

arXiv CS 6d ago

Attention-Augmented LSTMs for Automatic Homophonic Ciphertext Decipherment

arXiv:2606.05078v1 Announce Type: new Abstract: Homophonic substitution ciphers replace each plaintext letter with one of several possible ciphertext codes, deliberately weakening letter-frequency patterns and making automated decipherment difficult. This paper evaluates whether an attention-augmented Long Short-Term Memory (LSTM) model can learn such mappings in a historically motivated shared-key setting: all ciphertexts draw from the same known homophonic code pool, while individual keys...

arXiv CS 6d ago