DELOS applies contrastive learning to phase-folded light curves to detect shallow intermediate-to-long period transits, reporting 15.5% and 11.25% gains in combined precision-recall over BLS and TLS in low-SNR tests plus 3-80x speedups.
super hub Tool reference
Delving Deep into Rectifiers
Tool reference. 71% of classified Pith citations use this work as a method, library, or software dependency, not as a substantive claim.
21
Pith papers citing it
12.9k
external citations · Crossref
Method reference
71% of classified citations
hub tools
citation-role summary
method 4
background 1
dataset 1
other 1
citation-polarity summary
authors
co-cited works
representative citing papers
Introduces graph-to-image prediction of per-node dynamic stability landscapes in oscillator networks from topology, releases two 10k-graph datasets, and shows GNN-CNN models achieve good accuracy with cross-size generalization.
Human face perception aligns with neural networks trained on inverse-generative and naturalistic discriminative tasks, as these best predict human dissimilarity judgments on controversial and random face pairs.
MASCing uses an LSTM surrogate and optimized steering masks to enable flexible, inference-time control over MoE expert routing for safety objectives, improving jailbreak defense and content generation success rates substantially across multiple models.
A stochastic-geometric model of solution-space topology under Adam derives explicit scaling laws for grokking transition time as a function of learning rate, batch size, and L2 coefficient.
Multi-agent LLM teams outperform human teams in creativity (d=1.50) across tasks by producing more novel ideas, with distinct semantic exploration patterns predicting success for each group.
An auxiliary modulus during training reduces wrap-around issues and preserves train-test input distributions, enabling better accuracy and sample efficiency for large N and q in modular addition learning.
An amortized variational framework jointly targets the posterior and posterior-predictive distributions via a KL upper bound and moment regularization, yielding more accurate predictions at lower online cost than two-stage variational inference.
A variational neural network using Kolosov-Muskhelishvili potentials solves 2D linear elasticity and fracture problems by minimizing total potential energy and embedding crack discontinuities into the ansatz, yielding higher accuracy and faster convergence than standard physics-informed networks.
LTBs-KAN delivers linear-time B-spline evaluation in KANs plus parameter reduction via product-of-sums factorization, with competitive results on MNIST, Fashion-MNIST, and CIFAR-10.
TalkLoRA equips MoE-LoRA experts with a communication module that smooths routing dynamics and improves performance on language tasks under similar parameter budgets.
A closed-form initialization for SIREN networks based on pre-activation fixed points and Jacobian variance sequences improves gradient scaling, training dynamics via NTK, and generalization on reconstruction tasks over the original scheme.
Deep learning system synthesizes intermediate head CT slices to halve through-plane anisotropy while providing implicit denoising, outperforming baselines on structural metrics.
QIF neurons outperform LIF neurons in spike-based gradient descent training of spiking neural networks by avoiding discontinuities that fragment the loss landscape.
ResNet models classify four particle types and regress vertex, direction, and momentum in Hyper-Kamiokande with resolutions matching likelihood methods but at 30,000-50,000x faster inference on GPU.
MLP and Attention U-Net outperform other models in reconstructing GRB light curves on 521 events, cutting plateau parameter uncertainties by 37-41% versus the Willingale baseline while achieving low MSE.
A lightweight hybrid CNN-LSTM network classifies bean leaf diseases at 94.38% accuracy and 1.86 MB size on the ibean dataset, with reported state-of-the-art F1 scores using EfficientNet-B7+LSTM.
TwinLiteNet+ is a hybrid-encoder multi-task segmentation model with new UCB, USB, and PCAA modules that reports 92.9% mIoU on drivable area and 34.2% IoU on lane segmentation on BDD100K while using 11x fewer FLOPs than prior models.
Established mathematical bottlenecks in representation, optimization, complexity, and high-dimensional learning aligned with the central disappointments of early AI research periods.
citing papers explorer
No citing papers match the current filters.