A Drosophila-connectome-constrained RNN matches EfficientNet/MobileNet navigation performance yet spontaneously retains function under total vision loss and realistic-texture OOD where dropout-trained baselines fail.
hub
Long short-term memory
21 Pith papers cite this work. Polarity classification is still indexing.
21
Pith papers citing it
hub tools
citation-role summary
method 2
citation-polarity summary
roles
method 2polarities
use method 2representative citing papers
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.
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.
Foot-mounted proximity sensors provide pre-contact feedback that, when integrated into RL, improves quadruped traversal robustness on discrete terrain with reliable sim-to-real transfer.
A structure-aware RL fairness attack with joint item and gender selection policies is introduced and shown effective on four recommender models across two datasets.
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.
STDR infers stage structure from expert videos to supply stage-transition and within-stage progress rewards, improving RL sample efficiency on 14 manipulation tasks.
LNN-Fly is a structured recurrent policy for continuous-time UAV obstacle avoidance trained with perturbed differentiable rollouts that shows improved tolerance to timing issues and zero-shot transfer to physical hardware with 100% success in real tests.
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.
HiSem adds bidirectional differential attention and a two-level hierarchical routing module with MoE to handle semantic granularity differences in remote sensing change captioning, reporting +7.52% BLEU-4 on WHU-CDC.
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.
A single-qubit quantum spiking RNN is applied to continuous-valued forecasting and claims a 15.4% MSE gain over a classical LIF baseline, but the comparison does not isolate quantum effects.
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.
A survey that organizes audio SSL into five objective paradigms, relates their demands to architectural biases, and interprets downstream applications as tests of generalization.
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
-
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.
-
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.