#And

游戏 None

T-Mobile 促销代码：25% 折扣 |可能

Discover how to save on T-Mobile Business Internet and phone plans, from sign-up perks and switching rewards to bundled

and Discover how

2026-05-23 Molly Higgins

安全攻防 None

Newegg 促销代码：2026 年 5 月 10% 折扣

Enjoy up to 10% off your entire order with today’s Newegg promo code and discount codes。Save with the latest deals for g

with and Enjoy

2026-05-23 Molly Higgins

智能AI None

2026 年 5 月 Valvoline 优惠券和促销代码

We've gathered all the top Valvoline coupons and promo codes for May 2026, including deals on full synthetic oil changes

and gathered all

2026-05-23 Kat Merck

科技头条 None

Ulta 促销代码：5 月份最高 50% 折扣

Shop the latest beauty trends and save big using an Ulta promo code for beauty tech, makeup, and more。

beauty and Shop

2026-05-23 Boutayna Chokrane

科技头条 None

Lowe's 促销代码和优惠：电器最高立减 300 美元

Find the latest Lowe’s promo codes and offers, including up to $300 off select major appliances and $5 off $50 with sign

and off Find

2026-05-23 Matthew Korfhage

科技头条 None

环形耳塞折扣代码：40% 折扣

Save on Loop Earplugs, including Quiet 2 and popular gift sets for improved sleep, focus, and comfort。

and Save Loop

2026-05-23 Louryn Strampe

开发者生态 None

我很无聊，所以我把我的开发工具变成了一个由我的狗统治的外星球

Planet Maiko These alien dogs want to live in your computer。Would you let them in。Planet Maiko is a free local dev tool

your Maiko the

2026-05-23 bkawa-bot

智能AI None

用于执行轨迹上的推理时间对齐的工具

arXiv:2605.21516v1 Announce Type: new Abstract: Harness engineering has emerged as an important inference-time technique

and execution decomposition

2026-05-23 Boyuan Wang, Bochao Li, Minghan Wang, Yuxin Tao, Fang Kong

智能AI None

通过示例预测符号和提示程序的性能

21515v1 Announce Type: new Abstract: LLM prompting is widely used for naturally stated tasks, yet it is unreliable it ma

programs performance and

2026-05-23 Chengqi Zheng, Keya Hu, Shuzhi Liu, Tao Wu, Kevin Ellis, Yewen Pu

智能AI None

HealthCraft：急诊医学的强化学习安全环境

21496v1 Announce Type: new Abstract: Frontier language models are being deployed into clinical workflows faster than the

and the safety

2026-05-23 Brandon Dent

智能AI None

不要破坏你的特征：为什么 CenterLoss 会损害 OOD 检测，而多尺度 Mahalanobis 会获胜

21493v1 Announce Type: new Abstract: The ability to detect out-of-distribution (OOD) inputs is fundamental to safe deplo

OOD that for

2026-05-23 Rahul D Ray

智能AI None

归因不可能性：共线性下没有忠实、稳定、完整的特征排名

21492v1 Announce Type: new Abstract: No feature ranking can be simultaneously faithful, stable, and complete when featur

and for the

2026-05-23 Drake Caraker, Bryan Arnold, David Rhoads

智能AI None

教授语言模型通过比较想法评估来预测研究成功

arXiv:2605.21491v1 Announce Type: new Abstract: As language models accelerate scientific research by automating hypothes

and models research

2026-05-23 Srujan P Mule, Aniketh Garikaparthi, Manasi Patwardhan

智能AI None

语言模型中拒绝规避的潜在空间攻击

21706v1 Announce Type: new Abstract: Safety-aligned language models are trained to refuse harmful requests, yet refusal

the refusal and

2026-05-23 Giorgio Piras, Raffaele Mura, Fabio Brau, Maura Pintor, Luca Oneto, Fabio Roli, Battista Biggio

智能AI None

使用不可信的类别成员调查概念对齐

arXiv:2605.21683v1 Announce Type: new Abstract: Developing AI systems with a human-like understanding of everyday concep

category the categories

2026-05-23 Sunayana Rane, Brenden M. Lake, Thomas L. Griffiths

智能AI None

AOP-Wiki EMOD 3.0：使用代理 AI 改进 AOP 和新方法方法 (NAM) 之间集成的数据模型扩展和内容评估框架

arXiv:2605.21645v1 Announce Type: new Abstract: Adverse Outcome Pathways (AOP) are logic models that causally link biolo

AOP and the

2026-05-23 Virginia K. Hench, J. Harry Caufield, Sierra A. T. Moxon, Jason M. O'Brien, Stephen W. Edwards

智能AI None

MindLoom：构建前沿级推理数据合成的思维模式

21630v1 Announce Type: new Abstract: Although LLMs have made substantial progress in reasoning, systematically producing

reasoning and MindLoom

2026-05-23 Haiyang Shen, Taian Guo, Xuanzhong Chen, Mugeng Liu, Weichen Bi, Wenchun Jing, Sixiong Xie, Zhuofan Shi, Yudong Han, Chongyang Pan, Siqi Zhong, Jinsheng Huang, Ming Zhang, Yun Ma

智能AI None

证词的形状：口述历史档案比较的可扩展框架

arXiv:2605.21623v1 Announce Type: new Abstract: Researchers in Holocaust studies have often distinguished between two st

the and analysis

2026-05-23 Itamar Trainin, Renana Keydar, Amit Pinchevski

智能AI None

TO-Agents：用于偏好引导的拓扑优化的多代理 AI 管道

arXiv:2605.21622v1 Announce Type: new Abstract: Topology optimization can generate efficient structures, but designers o

and design the

2026-05-23 Isabella A. Stewart, Hongrui Chen, Faez Ahmed

智能AI None

法学硕士分布外对齐失败的基准测试和改进监视器

arXiv:2605.21602v1 Announce Type: new Abstract: Many safety and alignment failures of large language models (LLMs) occur

OOD that and

2026-05-23 Dylan Feng, Pragya Srivastava, Cassidy Laidlaw