言栖资讯收录 194192 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: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…
arXiv:2608.25667v2 Announce Type: replace Abstract: The integration of Large Language Models (LLMs) into cybersecurity has transformed vulnerability assessment,…
arXiv:2605.03158v2 Announce Type: replace Abstract: Cyber threat intelligence (CTI) systems must link exploit code, advisories, and fix commits to the vulnerabi…
arXiv:2509.17836v3 Announce Type: replace Abstract: Machine Learning (ML) techniques have shown strong potential for network traffic analysis; however, their ef…
arXiv:2508.00351v3 Announce Type: replace Abstract: Quantum money is a representative application in cryptography that utilizes quantum technology to achieve se…
arXiv:2505.23814v3 Announce Type: replace Abstract: Watermarking has emerged as a leading technical proposal for attributing generative AI content and is increa…
arXiv:2304.14717v3 Announce Type: replace Abstract: Trusted Platform Modules constitute an integral building block of modern security features. Moreover, as Win…
arXiv:2611.08442v1 Announce Type: cross Abstract: Standardised post-quantum cryptography (PQC) is critical for protecting software systems against future quantu…
arXiv:2611.07413v1 Announce Type: cross Abstract: Whether useful structured hardness can arise from unstructured assumptions is a fundamental question in comple…
arXiv:2611.07313v1 Announce Type: cross Abstract: We give a randomized, rank-preserving reduction from exact $\ell_p$-CVP to exact Euclidean SVP for every integ…