Tag
The paper proposes EEG-AS, an algorithm selection framework that enables instance-level selection among multiple EEG foundation models by reconstructing their behaviors, thereby improving neural decoding performance.
This paper presents an automated agentic approach using Large Language Models to synthesize interpretable Python feature extractors for algorithm selection in constraint satisfaction problems, outperforming expert-curated methods.
This paper investigates when weight-tied looped transformers implement actual algorithms, introducing the budget law and showing mechanisms are portable across training budgets, with implications for adaptive computation and interpretability.
This paper presents CASOP, a framework for context-aware synthesis and evaluation of optimization pipelines for warehouse order fulfillment, enabling automatic construction of valid algorithmic pipelines from a modular repository.