This paper introduces Hardness-Aware Meta-Resample (HAMR), a unified framework that adaptively addresses class imbalance and data difficulty in NLP tasks. HAMR employs bi-level optimizations and a neighborhood-aware resampling mechanism to prioritize genuinely challenging samples and minority classes, showing substantial improvements on diverse imbalanced datasets.
This paper introduces the Langevin Gradient Descent (LGD) algorithm for convex regression problems, proving that optimal hyperparameter configurations achieve the Bayes' optimal solution. The work also provides generalization guarantees for meta-learning LGD's optimal hyperparameters, with a pseudo-dimension bound of O(dh).
Adaptive Hierarchical Compression (AHC) is a meta-learning framework for continual object detection on memory-constrained microcontrollers, adapting to evolving task distributions. It employs MAML-based adaptive compression, hierarchical multi-scale compression, and a dual-memory architecture to prevent catastrophic forgetting within a strict 100KB memory budget.
The author describes a pivotal moment when static optimization, including meta-learning, proved obsolete for dynamic circular manufacturing supply chains, failing catastrophically under sudden policy changes like a carbon tax. This experience exposed the fundamental limitation of traditional methods in adapting to real-world complexities.
This paper proposes LAM-PINN, a compositional meta-learning framework designed to mitigate task heterogeneity in Physics-Informed Neural Networks (PINNs). It addresses the challenge of training PINNs for families of partial differential equations (PDEs) which often face high computational costs or negative transfer under data-scarce conditions.
Mochi is a Graph Foundation Model that improves efficiency and task unification by employing a meta-learning based training framework. It pre-trains on few-shot episodes directly mirroring downstream evaluation, addressing limitations of traditional reconstruction-based pre-training and achieving competitive performance.
MetaAdamW is a novel optimizer that employs a self-attention mechanism to dynamically adjust per-group learning rates and weight decay, addressing the limitation of uniform hyperparameters in adaptive optimizers. Its attention module is trained via a meta-learning objective, integrating gradient alignment, loss decrease, and generalization gap.
OMEGA is an end-to-end framework automating AI research, from idea generation to executable code, using structured meta-prompt engineering and code generation. It has produced novel ML classifiers that outperform scikit-learn baselines across 20 benchmark datasets.
SOLAR is an autonomous AI agent designed to overcome challenges of large language models in dynamic environments by enabling lifelong learning and continual adaptation. It uses parameter-level meta-learning and multi-level reinforcement learning to self-improve and discover adaptation strategies.