QLAM extends state-space models with quantum superposition in the hidden state for linear-time long-sequence modeling and reports consistent gains over RNN and transformer baselines on sequential image tasks.
hub
Long short-term memory
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
citation-role summary
method 2
citation-polarity summary
roles
method 2polarities
use method 2representative citing papers
A graph-conditioned meta-optimizer learns QAOA parameter trajectories from one problem class and transfers them to others, yielding better initializations than standard methods in an empirical study of 64 settings.
TacticGen generates realistic, adaptable football tactics via a multi-agent diffusion transformer trained on 3.3M events and 100M frames, supporting rule-, language-, or model-based guidance at inference time.
QLIF-CAST uses single-qubit quantum states to simulate leaky integrate-and-fire spiking dynamics in a recurrent architecture, achieving 15.4% lower MSE than classical LIF and up to 94% faster convergence than QLSTM on weather and air quality benchmarks.
SeqLight maps music to multi-light HSV control via SkipBART for global color prediction followed by hybrid imitation learning in a goal-conditioned MDP to decompose colors across lights.
X-IONet combines rule-based platform classification with a dual-stage attention network to predict displacement and uncertainty from IMU data, then fuses outputs via EKF, achieving reported error reductions on pedestrian and quadruped datasets.
pDANSE enables nonlinear state estimation for model-free processes by using RNN-parameterized Gaussian priors and reparameterization-based particle sampling to compute posterior second-order statistics from nonlinear measurements.
Hybrid KAN+XGBoost model outperforms SARIMAX, LSTM, standalone KAN and XGBoost on week-ahead electricity price forecasting in the Australian NEM, cutting MAE by ~12% versus XGBoost and over 50% versus naive baseline.
A multi-head attention fusion network integrates monotonic degradation trends, discrete operating state embeddings from clustering, and residual noise using BiLSTM and attention mechanisms to improve prognostic accuracy under varying conditions on NASA data.
An end-to-end learning framework for joint building-data-center integrated energy systems improves operational performance 7-9% over predict-then-optimize baselines and cuts total energy cost ~10% via waste-heat recovery.
VR study finds eye gaze adds complementary information to pedestrian trajectory prediction models, cutting final displacement error by 8.47% when fused with situational context.
MoTIF uses HOSVD to separate multi-parametric unsteady flow data into modal components, applies GPR for parametric and spatial interpolation and RNN for temporal forecasting, achieving under 2% relative RMS error on laminar flow cases with varying Reynolds number and angle of attack.
Ensemble of three binary DNNs classifies network flows as benign, DoS or DDoS at 99.84% and 95.30% accuracy on CICIDS2018 and UNSW-NB15, paired with RAG to generate mitigation reports that outperform vanilla LLM outputs.
xLSTM records the lowest RMSE for 3-hour and 24-hour heat demand forecasts while a basic fully-connected network matches overall accuracy with far fewer resources.
citing papers explorer
-
QLAM: A Quantum Long-Attention Memory Approach to Long-Sequence Token Modeling
QLAM extends state-space models with quantum superposition in the hidden state for linear-time long-sequence modeling and reports consistent gains over RNN and transformer baselines on sequential image tasks.
-
Graph-Conditioned Meta-Optimizer for QAOA Parameter Generation on Multiple Problem Classes
A graph-conditioned meta-optimizer learns QAOA parameter trajectories from one problem class and transfers them to others, yielding better initializations than standard methods in an empirical study of 64 settings.
-
TacticGen: Grounding Adaptable and Scalable Generation of Football Tactics
TacticGen generates realistic, adaptable football tactics via a multi-agent diffusion transformer trained on 3.3M events and 100M frames, supporting rule-, language-, or model-based guidance at inference time.
-
QLIF-CAST: Quantum Leaky-Integrate-and-Fire for Time-Series Weather Forecasting
QLIF-CAST uses single-qubit quantum states to simulate leaky integrate-and-fire spiking dynamics in a recurrent architecture, achieving 15.4% lower MSE than classical LIF and up to 94% faster convergence than QLSTM on weather and air quality benchmarks.
-
Stage Light is Sequence$^2$: Multi-Light Control via Imitation Learning
SeqLight maps music to multi-light HSV control via SkipBART for global color prediction followed by hybrid imitation learning in a goal-conditioned MDP to decompose colors across lights.
-
X-IONet: Cross-Platform Inertial Odometry Network for Pedestrian and Legged Robot
X-IONet combines rule-based platform classification with a dual-stage attention network to predict displacement and uncertainty from IMU data, then fuses outputs via EKF, achieving reported error reductions on pedestrian and quadruped datasets.
-
pDANSE: Particle-based Data-driven Nonlinear State Estimation from Nonlinear Measurements
pDANSE enables nonlinear state estimation for model-free processes by using RNN-parameterized Gaussian priors and reparameterization-based particle sampling to compute posterior second-order statistics from nonlinear measurements.
-
Hybrid Kolmogorov-Arnold Network and XGBoost Framework for Week-Ahead Price Forecasting in Australia's National Electricity Market
Hybrid KAN+XGBoost model outperforms SARIMAX, LSTM, standalone KAN and XGBoost on week-ahead electricity price forecasting in the Australian NEM, cutting MAE by ~12% versus XGBoost and over 50% versus naive baseline.
-
A Multi-head Attention Fusion Network for Industrial Prognostics under Discrete Operational Conditions
A multi-head attention fusion network integrates monotonic degradation trends, discrete operating state embeddings from clustering, and residual noise using BiLSTM and attention mechanisms to improve prognostic accuracy under varying conditions on NASA data.
-
End-to-End Learning-based Operation of Integrated Energy Systems for Buildings and Data Centers
An end-to-end learning framework for joint building-data-center integrated energy systems improves operational performance 7-9% over predict-then-optimize baselines and cuts total energy cost ~10% via waste-heat recovery.
-
Eye Gaze-Informed and Context-Aware Pedestrian Trajectory Prediction in Shared Spaces with Automated Shuttles: A Virtual Reality Study
VR study finds eye gaze adds complementary information to pedestrian trajectory prediction models, cutting final displacement error by 8.47% when fused with situational context.
-
MoTIF: A Mode-Structured Tensor Framework for Multi-Parametric Approximation, Super-Resolution and Forecasting of Unsteady Systems
MoTIF uses HOSVD to separate multi-parametric unsteady flow data into modal components, applies GPR for parametric and spatial interpolation and RNN for temporal forecasting, achieving under 2% relative RMS error on laminar flow cases with varying Reynolds number and angle of attack.
-
From Detection to Response: A Deep Learning and Retrieval-Augmented Generation Framework for Network Intrusion Mitigation
Ensemble of three binary DNNs classifies network flows as benign, DoS or DDoS at 99.84% and 95.30% accuracy on CICIDS2018 and UNSW-NB15, paired with RAG to generate mitigation reports that outperform vanilla LLM outputs.
-
Benchmarking Transformer and xLSTM for Time-Series Forecasting of Heat Consumption
xLSTM records the lowest RMSE for 3-hour and 24-hour heat demand forecasts while a basic fully-connected network matches overall accuracy with far fewer resources.