A survey of parameter-efficient fine-tuning techniques for audio foundation models

MEPO-SLM: multi-objective evolutionary prompt optimization for energy-efficient small language models on edge devices

MEPO-SLM is presented, a framework that reformulates prompt engineering for SLMs as a four-objective Pareto problem over task inaccuracy, and Phi-3-mini and Gemma-2B on English TriviaQA and Arabic medical QA, and TinyLlama-1.1B on TriviaQA only are evaluated.

Adaptation-based control approach via describing function to adjust PWPF modulator parameters

Adaptive gradient-norm weighting for improved domain adversarial training

Adaptive Gradient-Norm Weighting (AWD), a lightweight scalarization mechanism that dynamically adjusts gradient norms of the classification and alignment losses in UDA consistently improves average performance over fixed and scheduled baselines, with the strongest gains on more difficult transfer settings.

Generalized adaptive bridge regression: a unified framework for high-dimensional architecture discovery

The generalized adaptive bridge regression (GABR) framework successfully identifies optimal, off-grid grouping architectures and is evaluated on simulated architectures, demonstrating its dynamic adaptivity to structural sparsity, collinearity, and varying signal-to-noise ratios.

Flexibly Incorporating Prior Information Into Subset Scan Statistics

It is demonstrated that this approach maintains computational efficiency and exact detection of the highest-scoring subset for small-sized filter sets, and initial results for scaling to larger-sized filter sets are presented.

Forecasting the Term Structure of Crude Oil Futures Prices Under Mean-Reverting Dynamics and Deep Learning Models

The research indicates that combining mean-reversion theory with scientific machine learning (SciML) yields a robust, theoretically sound methodology for forecasting commodity prices.