Stay updated with the latest research and technology news
arXiv:2505.18051v3 Announce Type: replace Abstract: Vision transformers are ever larger, more accurate, and more expensive to compute. The expense is even more extreme at high...
arXiv:2505.19969v3 Announce Type: replace Abstract: Achieving differential privacy (DP) guarantees in fully decentralized machine learning is challenging due to the absence of a central aggregator...
arXiv:2505.20295v4 Announce Type: replace Abstract: The common approach to communicate a large language model's (LLM) uncertainty is to add a percentage number or a hedging...
arXiv:2505.23071v2 Announce Type: replace Abstract: Multi-Modal Learning (MML) integrates information from diverse modalities to improve predictive accuracy. While existing optimization strategies have made significant strides...
arXiv:2505.23216v2 Announce Type: replace Abstract: We propose a Trefftz discontinuous Galerkin (TDG) method for the approximation of plane wave scattering by periodic diffraction gratings, modelled...
arXiv:2505.24779v4 Announce Type: replace Abstract: The proliferation of machine learning-based methods for Mixed-Integer Linear Programming (MILP) instance generation has surged, driven by the need for...
arXiv:2506.01758v3 Announce Type: replace Abstract: Diffusion models have shown impressive performance in many visual generation and manipulation tasks. Many existing methods focus on training a...
arXiv:2506.03874v2 Announce Type: replace Abstract: It's well known that MDS, AMDS or self dual codes have good algebraic properties, and are applied in communication systems,...
arXiv:2506.04022v2 Announce Type: replace Abstract: Multi-objective reinforcement learning (MORL) aims at optimising several, often conflicting goals to improve the flexibility and reliability of RL in...
arXiv:2506.05701v3 Announce Type: replace Abstract: This position paper argues that post-deployment monitoring in clinical AI is underdeveloped and proposes statistically valid and label-efficient testing frameworks...
arXiv:2506.06536v3 Announce Type: replace Abstract: Given a set $S$ of $n$ keys, a perfect hash function for $S$ maps the keys in $S$ to the...
arXiv:2506.07433v3 Announce Type: replace Abstract: In this paper, we investigate the approximation properties of solutions to the Ginzburg-Landau equation (GLE) in finite element spaces. Special...
arXiv:2506.08194v3 Announce Type: replace Abstract: Modern monocular 3D reconstruction methods and vision-language models (VLMs) demonstrate impressive results on standard benchmarks, yet recent works cast doubt...
arXiv:2506.11719v2 Announce Type: replace Abstract: Lax-Wendroff methods combined with discontinuous Galerkin/flux reconstruction spatial discretization provide a high-order, single-stage, quadrature-free method for solving hyperbolic conservation laws....
arXiv:2506.12176v4 Announce Type: replace Abstract: In explainable AI, surrogate models are commonly evaluated by their fidelity to a neural network's predictions. Fidelity, however, measures alignment...
arXiv:2506.12474v2 Announce Type: replace Abstract: Accurate driving behavior modeling is fundamental to safe and efficient trajectory prediction, yet remains challenging in complex traffic scenarios. This...
arXiv:2506.13342v2 Announce Type: replace Abstract: Fact verification is essential for ensuring the reliability of LLM applications. In this study, we evaluate 12 pre-trained LLMs and...
arXiv:2506.13771v5 Announce Type: replace Abstract: The deployment of large language models (LLMs) is frequently hindered by prohibitive memory and computational requirements. While quantization mitigates these...
arXiv:2506.17208v3 Announce Type: replace Abstract: The rapid progress in Automated Program Repair (APR) has been driven by advances in AI, particularly large language models (LLMs)...
arXiv:2506.19806v2 Announce Type: replace Abstract: This position paper argues that LLM-based social simulations require clear boundaries to make meaningful contributions to social science. While Large...
arXiv:2506.20628v5 Announce Type: replace Abstract: This paper investigates maximum likelihood estimation for direct system identification in networks of dynamical systems. We establish that the proposed...
arXiv:2506.21996v3 Announce Type: replace Abstract: Deterministic game-solving algorithms are conventionally analyzed in the light of their average-case complexity against a distribution of random game-trees, where...
arXiv:2506.22186v2 Announce Type: replace Abstract: Thompson sampling (TS) is a Bayesian randomized exploration strategy that samples options (e.g., system parameters or control laws) from the...
arXiv:2506.22740v2 Announce Type: replace Abstract: Explanations of model behavior are commonly evaluated via proxy properties weakly tied to the purposes explanations serve in practice. We...