言栖资讯收录 193881 篇 AI、开发与建站文章，按发布时间排序，支持搜索与按语言筛选。
arXiv:2608.19250v2 Announce Type: replace Abstract: We propose a fully discrete method for linear fourth-order parabolic equations with Dirichlet boundary condi…
arXiv:2607.10652v2 Announce Type: replace Abstract: This paper presents a symplectic Hamiltonian direct discontinuous Galerkin (DDG) method for approximating wa…
arXiv:2609.08219v2 Announce Type: replace-cross Abstract: Neural networks acquire internal representations through learning. In this work, we formulate stochast…
arXiv:2609.06598v2 Announce Type: replace-cross Abstract: The optimal transport (OT) map provides a geometric transformation for aligning probability distributi…
arXiv:2608.25807v2 Announce Type: replace-cross Abstract: Kolmogorov-Arnold Networks (KANs) learn univariate functions on edges, making the choice of edge respo…
arXiv:2608.14430v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) post-training provides a direct way to align diffusion models with human p…
arXiv:2606.08493v4 Announce Type: replace-cross Abstract: Tissue graph counterfactuals ask what a cell would express if its spatial neighborhood were altered, a…
arXiv:2605.08069v2 Announce Type: replace-cross Abstract: We study methods for simultaneous analysis of many noisy and biased estimates, each paired with an eve…
arXiv:2605.07104v3 Announce Type: replace-cross Abstract: Establishing almost sure convergence rates for stochastic approximation and reinforcement learning und…
arXiv:2604.24737v2 Announce Type: replace-cross Abstract: Chain-of-thought (CoT) supervision makes computationally hard learning problems tractable by exposing …
arXiv:2603.24626v3 Announce Type: replace-cross Abstract: Single-cell RNA sequencing (scRNA-seq) enables gene expression profiling at cellular resolution but is…
arXiv:2602.24207v3 Announce Type: replace-cross Abstract: The use of algorithmic predictions in decision-making leads to a feedback loop where the models we dep…
arXiv:2602.20457v2 Announce Type: replace-cross Abstract: We study online alignment of large language models under misspecified preference feedback, where the o…
arXiv:2512.06370v4 Announce Type: replace-cross Abstract: Recent works have shown that gradient-update alignment is a powerful signal for modulating optimizer u…
arXiv:2508.05844v3 Announce Type: replace-cross Abstract: We study a stochastic budget-allocation problem over $K$ tasks. At each round $t$, the learner chooses…
arXiv:2402.17595v2 Announce Type: replace-cross Abstract: The phenomenon of implicit bias has attracted interest in recent years as a fundamental aspect of the …
arXiv:2610.04992v2 Announce Type: replace Abstract: Detecting malicious smart contracts is essential to safeguarding the Web3.0 ecosystem. However, existing aud…
arXiv:2609.35596v3 Announce Type: replace Abstract: Self-evolving LLM agents have gained prominence for their ability to improve after deployment by modifying t…
arXiv:2609.34804v2 Announce Type: replace Abstract: Federated learning enables industrial operators to train shared intrusion detection models without disclosin…
arXiv:2609.16541v2 Announce Type: replace Abstract: We have applied a novel combination of classic relational database modeling and modern reinforcement learnin…