gated recurrent unit
PulseAugur coverage of gated recurrent unit — every cluster mentioning gated recurrent unit across labs, papers, and developer communities, ranked by signal.
16 day(s) with sentiment data
-
New 'wrong-physics backdoors' found in neural PDE operators
Researchers have identified a new vulnerability in neural partial differential equation (PDE) operators, termed "wrong-physics backdoors." This attack exploits reusable solver archives by subtly altering inputs to trigg…
-
AI framework enhances bankruptcy prediction using ensemble models and XAI
Researchers have developed a novel framework for predicting bankruptcy by combining feature selection, hybrid resampling techniques, and stacking ensemble models with explainable AI (XAI). The study utilized the Taiwane…
-
New TH-GNN model detects LLM-agent shilling attacks
Researchers have developed TH-GNN, a novel heterogeneous temporal graph neural network designed to detect sophisticated shilling attacks orchestrated by LLM agents. This model utilizes a two-layer Heterogeneous Graph Tr…
-
Banking intent router built with RoBERTa, LoRA, and privacy controls
A banking intent router was developed using the BANKING77 dataset, incorporating RoBERTa, LoRA, and calibration techniques. The project focused on privacy controls and uncertainty testing, ultimately finding that a mode…
-
BRAID model uses graph neural networks to speed up game equilibrium calculations
Researchers have developed BRAID, a novel model utilizing weight-tied iterative graph neural networks to efficiently compute Nash equilibria in interdependent security (IDS) games. This approach significantly speeds up …
-
New framework forecasts public events with over 97% accuracy
Researchers have introduced auto-ibDLM, a novel deep learning framework designed for forecasting public event evolution. This framework models events as dynamic interaction networks and predicts future participant growt…
-
New framework X-AddGraph adds explainability to graph anomaly detection
Researchers have developed X-AddGraph, a novel post-hoc explainability framework for AddGraph, a recurrent graph anomaly detection system. This new method provides auditable reasons for anomaly detection scores without …
-
AI framework uses Vision Transformer and GRU for mosquito disease detection
Researchers have developed a novel hybrid framework for detecting mosquito-borne diseases, specifically focusing on identifying dengue virus-infected mosquitoes. The system integrates the YOLO 11M model for initial mosq…
-
Machine Learning vs. Deep Learning for Starbucks Review Sentiment Analysis
A new research paper compares the effectiveness of various machine learning and deep learning models for analyzing consumer sentiment in the retail coffee sector. The study focused on Starbucks reviews from ConsumerAffa…
-
Deep learning framework accurately detects repetitive behaviors using wearable sensors
Researchers have developed a deep learning framework using multimodal wearable sensor data to accurately detect and classify body-focused repetitive behaviors like hair pulling and skin picking. The system, which combin…
-
New framework optimizes digital twin calibration with budgeted data acquisition
Researchers have developed a new framework for calibrating digital twins, which are virtual replicas of physical systems. This framework addresses the challenge of expensive data collection by optimizing the generation …
-
New C2L-Net model offers faster, more efficient lithium-ion battery SOC estimation
Researchers have developed C2L-Net, a novel data-driven framework designed for efficient and accurate state-of-charge (SOC) estimation in lithium-ion batteries. This new model addresses limitations of existing methods b…
-
LITEWAY framework offers lightweight, efficient human activity recognition
Researchers have developed LITEWAY, a novel framework for human activity recognition (HAR) using wearable sensors. This modality-agnostic, fully convolutional approach aims to overcome the computational and energy limit…
-
New methods tackle LLM and VLM hallucinations with internal analysis · 2 sources tracked
Researchers have developed new methods to detect hallucinations in large language and vision-language models. UniProbe, a technique for Large VLMs, uses a graph neural network, a Vision Transformer, and a gated recurren…
-
New foundation model FemWear targets women's health from wearable data
Researchers have developed FemWear, a specialized foundation model for women's health tasks using wearable sensor data. This model efficiently repurposes a pre-trained multimodal wearable backbone, training a small frac…
-
New FSD-RM paradigm offers effective time-series prediction for limited-data domains
Researchers have developed a new paradigm called FSD-RM (Family of Small-Data Representation Models) for time-series prediction in domains with limited data, such as industrial and scientific applications. This approach…
-
Hybrid ML framework forecasts cattle weight gain in grazing systems
Researchers have developed a hybrid machine learning framework to forecast cattle weight gain and growth patterns in grazing systems. The framework integrates various sensing data, including live weight, demographics, a…
-
New framework evaluates wildfire risk models on operational coherence, not just accuracy
A new framework for evaluating wildfire risk systems has been proposed, moving beyond traditional accuracy metrics like F1-score. This novel approach focuses on the operational coherence of risk signals, assessing wheth…
-
TextNCA: Neural Cellular Automata for Language Modeling Explored
Researchers have developed TextNCA, a language model based on Neural Cellular Automata that utilizes hierarchical local attention. While not outperforming a similarly sized Transformer model on the WikiText-103 benchmar…
-
New Recurrent Network Model Mimics Brain Computation for Working Memory
Researchers have introduced the Recurrent Divisive Normalization Network (RDNN), a novel artificial neural network model inspired by biological divisive normalization. This model is designed to overcome the limitations …