sGPO uses an initial-policy success-rate profiling pass to adaptively set rollout group sizes, filter data, and build a curriculum, cutting total RLVR training compute by 3x while matching baseline performance.
& Balasubra- manian, V
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
verdicts
UNVERDICTED 8roles
method 1polarities
use method 1representative citing papers
XWP and XWP_c are novel attribution methods for FCNNs that estimate feature importance by perturbing attached weights to avoid added bias and out-of-distribution issues in occlusion approaches.
Quantum annealing solves a combinatorial feature-map selection problem for CNNs, yielding improved class disentanglement over GradCAM and GradCAM++ in the reported evaluation.
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.
Introduces a unified evaluation framework for XAI using five principled metrics and the PGCA method that fuses grid perturbation with Grad-CAM++ , reporting top scores in fidelity, interpretability and fairness on ResNet-50 models across five image domains.
An itinerant oscillator model extracts molecular timescales from the memory function of MD simulations to interpret bulk EIS spectra in room-temperature ionic liquids without low-concentration assumptions.
Realistic noise synthesis incorporating Rician expectation and effective variance into simulated training data reduces bias in supervised ML for diffusion MRI microstructure estimation.
Model interpretation methods are reformulated to emphasize baselines; gradient-based methods, IG, and Taylor expansion are unified with explicit baselines identified, and a revised IG is developed for improved results from any layer.
citing papers explorer
-
sGPO: Trading Inference FLOPs for Training Efficiency in RLVR
sGPO uses an initial-policy success-rate profiling pass to adaptively set rollout group sizes, filter data, and build a curriculum, cutting total RLVR training compute by 3x while matching baseline performance.
-
From Weight Perturbation to Feature Attribution for Explaining Fully Connected Neural Networks
XWP and XWP_c are novel attribution methods for FCNNs that estimate feature importance by perturbing attached weights to avoid added bias and out-of-distribution issues in occlusion approaches.
-
Towards interpretable AI with quantum annealing feature selection
Quantum annealing solves a combinatorial feature-map selection problem for CNNs, yielding improved class disentanglement over GradCAM and GradCAM++ in the reported evaluation.
-
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 Unified Framework for Evaluating and Enhancing the Transparency of Explainable AI Methods via Perturbation-Gradient Consensus Attribution
Introduces a unified evaluation framework for XAI using five principled metrics and the PGCA method that fuses grid perturbation with Grad-CAM++ , reporting top scores in fidelity, interpretability and fairness on ResNet-50 models across five image domains.
-
Molecular interpretability of the bulk electrochemical impedance of concentrated electrolytes
An itinerant oscillator model extracts molecular timescales from the memory function of MD simulations to interpret bulk EIS spectra in room-temperature ionic liquids without low-concentration assumptions.
-
Realistic noise synthesis reduces bias and improves tissue microstructure estimation with supervised machine learning
Realistic noise synthesis incorporating Rician expectation and effective variance into simulated training data reduces bias in supervised ML for diffusion MRI microstructure estimation.
-
The Neglected Baseline in Model Interpretation
Model interpretation methods are reformulated to emphasize baselines; gradient-based methods, IG, and Taylor expansion are unified with explicit baselines identified, and a revised IG is developed for improved results from any layer.