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

Unsupervised domain adaptation (UDA) transfers knowledge from a labeled source domain to an unlabeled target domain by jointly optimizing source classification and domain-alignment objectives. A key practical challenge is selecting the trade-off coefficient λ\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda $$\end{document}, which controls the strength of domain alignment. Fixed values and manually designed schedules are commonly used, but the appropriate balance can vary across datasets, transfer directions, and training stages. This paper proposes Adaptive Gradient-Norm Weighting (AWD), a lightweight scalarization mechanism that dynamically adjusts λ\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda $$\end{document} using the ratio between the gradient norms of the classification and alignment losses. AWD introduces no additional learnable parameters and can be applied to UDA objectives of the form LCE+λLAlign\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\mathcal {L}_{\textrm{CE}}+\lambda \mathcal {L}_{\textrm{Align}}$$\end{document}. We evaluate AWD within Deep Adaptation Network (DAN) and Domain-Adversarial Neural Network (DANN) on Office-31, Office-Home, DomainNet, and digit adaptation benchmarks using five independent seeds. Across the evaluated benchmarks, AWD consistently improves average performance over fixed and scheduled baselines, with the strongest gains on more difficult transfer settings. On Office-Home with DANN, AWD improves average accuracy over fixed λ=1\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\lambda {=}1$$\end{document} by +4.4\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$+4.4$$\end{document} percentage points, while avoiding manual per-task grid search. The method incurs only modest computational overhead. Overall, the results show that gradient-aware adaptive weighting is a simple, practical, and interpretable mechanism for balancing classification and alignment losses in UDA.

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

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