A taxonomy of SNN training algorithms is presented with the release of NeuroTrain, an open benchmarking framework for reproducible comparisons across datasets and architectures.
hub Canonical reference
Discriminative and Geometry-Preserving Adaptive Graph Embedding for dimensionality reduc- tion
Canonical reference. 100% of citing Pith papers cite this work as background.
12
Pith papers citing it
Background
100% of classified citations
hub tools
citation-role summary
background 6
citation-polarity summary
roles
background 6polarities
background 6representative citing papers
An approximate IPTR framework for linearly constrained optimization uses low-rank projector updates to cut per-iteration cost while preserving feasibility and convergence guarantees, with experiments showing 2.48x speedup.
DeceptionX trains a multimodal LLM to explain lie judgments with visual and audio evidence, but its benchmark gains rest on overlapping train/test data and label-conditioned annotations.
Equivariant neural networks for 2D Q-tensor prediction in nematic liquid crystals achieve lower errors and better generalization than non-equivariant models while satisfying symmetry constraints.
DECHRL models causal structures and stochastic delay distributions within hierarchical RL and incorporates them into a delay-aware empowerment objective to improve performance under temporal uncertainty.
An adaptive anisotropic composite quadrature strategy combined with refresh-based training narrows the gap between training and reference losses in neural residual minimization for PDEs while using quadrature points more efficiently.
AW-PINN uses dynamic wavelet basis adaptation in PINNs to solve PDEs with localized high-magnitude sources, outperforming prior methods on loss imbalances up to 10^10:1 while deriving a Gaussian process limit and NTK structure under assumptions.
AWAC combines offline data with online RL via advantage-weighted actor-critic updates to enable faster acquisition of robotic skills such as dexterous manipulation.
Relative rankings of online EWC, LwF, SI and GEM are not consistently preserved across five trainable-depth regimes on five datasets and eleven task orders.
ICA and VEIL enable privacy-preserving supervised ML by producing structurally non-invertible encodings aligned with downstream tasks while maintaining predictive utility.
A systematic review of 55 papers finds explainability for multimodal attention-based models is dominated by attention-weight visualizations, while evaluation remains mostly qualitative and non-standardized.
citing papers explorer
-
NeuroTrain: Surveying Local Learning Rules for Spiking Neural Networks with an Open Benchmarking Framework
A taxonomy of SNN training algorithms is presented with the release of NeuroTrain, an open benchmarking framework for reproducible comparisons across datasets and architectures.
-
Scalable First-Order Interior Point Trust Region Algorithms for Linearly Constrained Optimization
An approximate IPTR framework for linearly constrained optimization uses low-rank projector updates to cut per-iteration cost while preserving feasibility and convergence guarantees, with experiments showing 2.48x speedup.
-
DeceptionX: From Multimodal Evidence to Explainable Deception Detection
DeceptionX trains a multimodal LLM to explain lie judgments with visual and audio evidence, but its benchmark gains rest on overlapping train/test data and label-conditioned annotations.
-
On the Equivariant Learning of the $Q$-tensor Order Parameter
Equivariant neural networks for 2D Q-tensor prediction in nematic liquid crystals achieve lower errors and better generalization than non-equivariant models while satisfying symmetry constraints.
-
Delay-Empowered Causal Hierarchical Reinforcement Learning
DECHRL models causal structures and stochastic delay distributions within hierarchical RL and incorporates them into a delay-aware empowerment objective to improve performance under temporal uncertainty.
-
Adaptive anisotropic composite quadratures for residual minimisation in neural PDE approximations
An adaptive anisotropic composite quadrature strategy combined with refresh-based training narrows the gap between training and reference losses in neural residual minimization for PDEs while using quadrature points more efficiently.
-
An adaptive wavelet-based PINN for problems with localized high-magnitude source
AW-PINN uses dynamic wavelet basis adaptation in PINNs to solve PDEs with localized high-magnitude sources, outperforming prior methods on loss imbalances up to 10^10:1 while deriving a Gaussian process limit and NTK structure under assumptions.
-
AWAC: Accelerating Online Reinforcement Learning with Offline Datasets
AWAC combines offline data with online RL via advantage-weighted actor-critic updates to enable faster acquisition of robotic skills such as dexterous manipulation.
-
Fine-Tuning Regimes Define Distinct Continual Learning Problems
Relative rankings of online EWC, LwF, SI and GEM are not consistently preserved across five trainable-depth regimes on five datasets and eleven task orders.
-
Informationally Compressive Anonymization: Non-Degrading Sensitive Input Protection for Privacy-Preserving Supervised Machine Learning
ICA and VEIL enable privacy-preserving supervised ML by producing structurally non-invertible encodings aligned with downstream tasks while maintaining predictive utility.
-
Decoding the Multimodal Maze: A Systematic Review on the Adoption of Explainability in Multimodal Attention-based Models
A systematic review of 55 papers finds explainability for multimodal attention-based models is dominated by attention-weight visualizations, while evaluation remains mostly qualitative and non-standardized.
- The Geometric Mechanics of Contrastive Representation Learning: Alignment Potentials, Entropic Dispersion, and Cross-modal Divergence