arXiv:2504.01400v3 Announce Type: replace-cross Abstract: Tool learning, which allows Large Language Models (LLMs) to leverage external tools for solving complex user tasks, has emerged as a promising avenue for extending model capabilities. However, existing approaches primarily focus on data synthesis…
MIT Energy Initiative researchers calculated the economic and environmental impact of future ammonia energy production and trade pathways.
arXiv:2601.07637v1 Announce Type: cross Abstract: Outstanding claim liabilities are revised repeatedly as claims develop, yet most modern reserving models are trained as one-shot predictors and typically learn only from settled claims. We formulate individual claims reserving as a claim-level Markov…
arXiv:2511.08362v2 Announce Type: replace-cross Abstract: Qubit-efficient optimization studies how large combinatorial problems can be addressed with quantum circuits whose width is far smaller than the number of logical variables. In quadratic unconstrained binary optimization (QUBO), objective values depend only on…
arXiv:2601.07326v1 Announce Type: cross Abstract: This paper studies the AdamW-style Shampoo optimizer, an effective implementation of classical Shampoo that notably won the external tuning track of the AlgoPerf neural network training algorithm competition. Our analysis unifies one-sided and two-sided preconditioning…
arXiv:2307.07785v2 Announce Type: replace-cross Abstract: The problem of model selection is considered for the setting of interpolating estimators, where the number of model parameters exceeds the size of the dataset. Classical information criteria typically consider the large-data limit, penalizing model…
arXiv:2505.16313v3 Announce Type: replace-cross Abstract: Deep neural networks for image classification remain vulnerable to adversarial examples — small, imperceptible perturbations that induce misclassifications. In black-box settings, where only the final prediction is accessible, crafting targeted attacks that aim to misclassify…
arXiv:2506.14518v3 Announce Type: replace Abstract: We study a two-player zero-sum game in which the row player aims to maximize their payoff against an adversarial column player, under an unknown payoff matrix estimated through bandit feedback. We propose three algorithms based…
arXiv:2512.01384v3 Announce Type: replace Abstract: We present CLAPS, a posterior-aware conformal regression method that pairs a Last-Layer Laplace Approximation with split-conformal calibration. From the resulting Gaussian posterior, CLAPS defines a simple two-sided posterior CDF score that aligns the conformity metric…
arXiv:2601.06106v1 Announce Type: new Abstract: We propose a dedicated multimodal Judge Model designed to provide reliable, explainable evaluation across a diverse suite of tasks. Our benchmark spans text, audio, image, and video modalities, drawing from carefully sampled public datasets with…
