Ghosted Layers: Unconstrained Activation Alignment for Recovering Layer-Pruned LLMs

Robust Multi-Agent LLMs under Byzantine Faults

Locality-Aware Redundancy Pruning for LLM Depth Compression

Sharpness-Aware Minimization with Z-Score Gradient Filtering

On How Muon Reshapes Skill Learning Dynamics

Rethinking Layer Redundancy: Calibration Matters More Than Search in LLM Depth Pruning

Spectrum-Shaping Regularization for Neural Network Training Robust to Low-Rank Pruning

Weight Concentration Regularization for Improving Pruning Robustness Under High Sparsity

Asynchronous Sharpness-Aware Minimization for Fast and Accurate Deep Learning

Revisiting 16-bit Neural Network Training: A Practical Approach for Resource-Limited Learning

Why Does Stochastic Gradient Descent Slow Down in Low-Precision Training?

Hyperparameter-Free Auto-Scaled Gradient Normalization via Global Standard Deviation Dynamics

Fast Fourier Transform-Based Spectral and Temporal Gradient Filtering for Differential Privacy

Stochastic Gradient Sampling for Enhancing Neural Networks Training

ZNorm: Z-Score Gradient Normalization Accelerating Skip-Connected Network Training Without Architectural Modification

Mitigating Gradient Overlap in Deep Residual Networks with Gradient Normalization for Improved Non-Convex Optimization

Analysis and Predictive Modeling of Solar Coronal Holes Using Computer Vision and ARIMA-LSTM Networks

Robust Neural Pruning with Gradient Sampling Optimization for Residual Neural Networks

Uncertainty Estimation for Tumor Prediction with Unlabeled Data