arXiv:2509.26351v2 Announce Type: replace
Abstract: Research on emergency and mass casualty incident (MCI) triage has been limited by the absence of openly usable, reproducible benchmarks. Yet these scenarios demand rapid identification of the patient…
arXiv:2603.20253v1 Announce Type: cross
Abstract: Evaluating LLM agents for scientific tasks has focused on token costs while ignoring tool-use costs like simulation time and experimental resources. As a result, metrics like pass@k become impractical …
arXiv:2509.22381v2 Announce Type: replace
Abstract: Effective credit risk management is fundamental to financial decision-making, requiring robust models to predict default probabilities and classify financial entities. Traditional machine learning ap…
arXiv:2603.28764v1 Announce Type: new
Abstract: Similarity measures are widely used to interpret the representational geometries used by neural networks to solve tasks. Yet, because existing methods compare the extrinsic geometry of representations in…
arXiv:2509.17889v2 Announce Type: replace
Abstract: Many practical applications of multi-objective optimization (MOO), including engineering design, autonomous systems, and machine learning, often yield complex Pareto frontiers (e.g., discontinuous, d…
arXiv:2603.28750v1 Announce Type: new
Abstract: Recurrent networks do not need Jacobian propagation to adapt online. The hidden state already carries temporal credit through the forward pass; immediate derivatives suffice if you stop corrupting them w…
arXiv:2509.12573v3 Announce Type: replace
Abstract: AI systems often struggle to provide reliable predictions across all inputs, motivating hybrid human-AI decision-making. Existing Learning to Defer (L2D) approaches address this by training models to…
arXiv:2603.28744v1 Announce Type: new
Abstract: The linear representation hypothesis states that neural network activations encode high-level concepts as linear mixtures. However, under superposition, this encoding is a projection from a higher-dimens…
arXiv:2509.03417v3 Announce Type: replace
Abstract: Kolmogorov-Arnold Networks (KANs) are a recently introduced neural architecture that replace fixed nonlinearities with trainable activation functions, offering enhanced flexibility and interpretabili…
arXiv:2603.28743v1 Announce Type: new
Abstract: Scaling laws for large language models depend critically on the optimizer and parameterization. Existing hyperparameter transfer laws are mainly developed for first-order optimizers, and they do not stru…