a Feature Stability Enhancement
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Aligned Training: A Parameter-Free Method to Improve Feature Quality and Stability of Sparse Autoencoders (SAE)
Announce Type: replace Abstract: Sparse autoencoders (SAEs) are one of the main methods to interpret the inner workings of deep neural networks (DNNs), decomposing activations into higher-dimensional features. However, they exhibit critical shortcomings where a large fraction of features are never activated and are unstable. Despite variants of SAEs that attempt to mitigate these issues, they require additional data, resampling, or training.
Laser-Stabilized Fiber Sensing on Terrestrial Field-Deployed Cable for Enhanced Sensitivity
Physics > Optics [Submitted on 5 Jun 2026] Title:Laser-Stabilized Fiber Sensing on Terrestrial Field-Deployed Cable for Enhanced Sensitivity View PDFAbstract:We demonstrate distributed acoustic sensing on deployed buried cable leveraging laser frequency stabilization and probing code optimization. Our results confirm the capability to accurately localize weak events with high resolution and sensitivity over 80 km.
Modeling Nonlinear Feature Interactions with Product-Unit Residual Networks
arXiv:2606.06861v1 Announce Type: new Abstract: Understanding nonlinear feature interactions is crucial in science and engineering, yet standard multilayer perceptrons (MLPs) often capture such interactions only implicitly, leading to entangled representations that can impair robustness and interpretability. We investigate product-unit residual networks (PURe) that integrate multiplicative product units with residual connections to explicitly model cross-feature couplings while stabilizing...
Text-guided Feature Disentanglement for Cross-modal Gait Recognition
Announce Type: new Abstract: Gait recognition is a biometric technique that identifies individuals based on their walking patterns, offering advantages in long-range, non-intrusive scenarios. However, real-world scenarios often involve heterogeneous sensing modalities such as LiDAR and RGB cameras, making LiDAR-Camera Cross-modal Gait recognition (LCCGR) a critical yet challenging task due to the substantial modality gap between 2D videos and 3D point cloud sequences. To address this...
Trans GAN-WT: A Feature Extraction and Interactive Learning-Based Anomaly Detection Model for Wind Turbine Time Series Data
Announce Type: cross Abstract: With the increasing scale and number of wind farms, wind turbines' daily operation and maintenance costs are increasing. To reduce operation and maintenance costs and enhance the reliability of wind turbine and system operation data before reaching catastrophic failures, monitoring the operating status of the equipment and detecting failures at an early stage is crucial. It is of great practical significance to utilize the working condition data for abnormal...
First whole-genome sequence of a Greenland shark holds clues to their extreme longevity
First whole-genome sequence of a Greenland shark holds clues to their extreme longevity A genomic study of Greenland sharks, thought to be the longest-lived vertebrates on the planet, is hinting at the secrets to their epic lifespan and cancer resistance. The first-ever whole-genome sequence of a Greenland shark has revealed genetic clues to how the animals avoid cancer and live for hundreds of years. The work may pave the way to a better understanding of age-related diseases in humans.
FCUS-rPPG: A Fast-Converging Unsupervised Framework for Remote Photoplethysmography via Gradient Oscillation Suppression
arXiv:2606.03050v1 Announce Type: new Abstract: Remote photoplethysmography (rPPG) enables non-contact extraction of blood volume pulse (BVP) signals using consumer-grade cameras. Recent unsupervised rPPG methods learn BVP representations without requiring ground-truth physiological annotations, yet their optimization is often hindered by noisy and unstable gradients, resulting in slow convergence and limited cross-domain generalization. In this paper, we propose FCUS-rPPG, a fast-converging...
Step-adaptive multimodal fusion network with multi-scale cloud feature learning for ultra-short-term solar irradiance forecasting
arXiv:2606.06102v1 Announce Type: new Abstract: Ultra-short-term solar irradiance prediction is critical for photovoltaic system dispatch and power grid stability. Existing approaches suffer from three key shortcomings: single time-series models cannot capture the spatial dynamics of clouds under complex conditions, standard convolutions inadequately represent multi-scale cloud features, and fixed low-frequency compensation strategies fail to adapt to different prediction steps. To address...
Co-Fusion4D: Spatio-temporal Collaborative Fusion for Robust 3D Object Detection
Announce Type: replace Abstract: In autonomous driving, 3D object detection is essential for accurate perception and reliable decision-making. However, object motion and ego-motion often induce cross-frame spatiotemporal inconsistencies in BEV-based detectors, leading to temporal BEV feature misalignment and degraded spatiotemporal consistency. To address these challenges, we propose Co-Fusion4D, a unified framework that explicitly preserves cross-frame spatiotemporal consistency and...
In situ nanocrystal confinement for efficient blue perovskite LEDs
Abstract Metal halide perovskites have emerged as promising semiconductors for light-emitting diodes (LEDs) owing to their excellent luminescence properties1. However, their performance remains limited, primarily owing to the inherent contradiction between ‘high crystallinity’ and ‘small size’ in the in situ synthesis of perovskite nanocrystals on substrates. Here we report efficient blue perovskite LEDs (PeLEDs) achieved via in situ polymerization-driven nanocrystal confinement to...