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.
super hub Tool reference
Delving deep into rectifiers: Surpassing human- level performance on imagenet classification
Tool reference. 71% of classified Pith citations use this work as a method, library, or software dependency, not as a substantive claim.
16
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
TACK dataset enables scaffold-based evaluation showing classical ML methods outperform a domain-specific GNN for PROTAC activity prediction, with potency far more predictable than maximum degradation.
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.
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.
A Deep Ritz method with augmented Lagrangian and Fourier feature mappings computes high-dimensional steady states of the Cahn-Hilliard equation and identifies multiple nontrivial phase separation patterns.
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.
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.
citing papers explorer
-
Learning Dynamic Stability Landscapes in Synchronization Networks
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.
-
TACK: A statistical evaluation of degradation activity on a novel TArgeting Chimeras Knowledge dataset
TACK dataset enables scaffold-based evaluation showing classical ML methods outperform a domain-specific GNN for PROTAC activity prediction, with potency far more predictable than maximum degradation.
-
Human face perception reflects inverse-generative and naturalistic discriminative objectives
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: Configurable Mixture-of-Experts Behavior via Activation Steering Masks
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.
-
Multi-agent AI systems outperform human teams in creativity
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.
-
Learning Large-Scale Modular Addition with an Auxiliary Modulus
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.
-
Amortized Variational Inference for Joint Posterior and Predictive Distributions in Bayesian Uncertainty Quantification
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 Kolosov--Muskhelishvili Network for Elasticity and Fracture
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: Linear-Time B-splines Kolmogorov-Arnold 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.
-
A Deep Ritz Method for High-Dimensional Steady States of the Cahn--Hilliard Equation
A Deep Ritz method with augmented Lagrangian and Fourier feature mappings computes high-dimensional steady states of the Cahn-Hilliard equation and identifies multiple nontrivial phase separation patterns.
-
TalkLoRA: Communication-Aware Mixture of Low-Rank Adaptation for Large Language Models
TalkLoRA equips MoE-LoRA experts with a communication module that smooths routing dynamics and improves performance on language tasks under similar parameter budgets.
-
A new initialisation to Control Gradients in Sinusoidal Neural network
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.
-
Enhancing Event Reconstruction in Hyper-Kamiokande with Machine Learning: A ResNet Implementation
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.
-
Gamma-Ray Burst Light Curve Reconstruction: A Comparative Machine and Deep Learning Analysis
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 Resource-Efficient Hybrid CNN-LSTM network for image-based bean leaf disease classification
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+: An Enhanced Multi-Task Segmentation Model for Autonomous Driving
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.