#across

智能AI None

RIFT-Bench：代理人工智能系统的动态红队

arXiv:2606.23927v1 Announce Type: new Abstract: Agentic AI systems powered by large language models (LLMs) are rapidly e

systems across RIFT

2026-06-24 Yarin Yerushalmi Levi, Roy Betser, Amit Giloni, Lidor Erez, Itay Gershon, Oren Rachmil, Sindhu Padakandla, Roman Vainshtein

智能AI None

模型在预填充时做笔记：KV 缓存可以编辑和组合

17107v1 Announce Type: new Abstract: Prefix caching reuses prefill only across an exactly shared prefix, so one changed

the field and

2026-06-17 Bojie Li

智能AI None

SpeechDx: A Multi-Task Benchmark for Clinical Speech AI

17339v1 Announce Type: new Abstract: Speech offers a uniquely informative window into health by simultaneously engaging

and speech clinical

2026-06-17 Sejal Bhalla, Larry Kieu, Aina Merchant, Eyal de Lara, Alex Mariakakis

智能AI None

通过相变出现：复杂系统的机制景观和普遍趋同

arXiv:2606.07563v1 Announce Type: new Abstract: Across machine learning, biology, and physics, independently evolving sy

and convergence the

2026-06-09 Truong Xuan Khanh

智能AI None

大型语言模型中的置信度校准

23909v1 Announce Type: new Abstract: We investigate the calibration of large language models' (LLMs') confidence across

the calibration LLMs

2026-05-26 Noam Michael, Daniel BenShushan, Jacob Bien, Don A. Moore

安全攻防 None

Claude Mythos AI 在广泛使用的软件中发现 10,000 个严重缺陷

Anthropic on Friday disclosed that Project Glasswing has helped uncover more than 10,000 high- or critical-severity vuln

the Project Glasswing

2026-05-23 info@thehackernews.com (The Hacker News)

科技头条 None

旧石油和天然气井可以重获新生，生产清洁能源

States across the US are looking to take major sources of pollution and use them to generate much-needed power。

States across the

2026-05-16 Maria Gallucci

智能AI None

中国短剧如何成为AI内容机器

In a dimly lit bedroom, a frightened young woman is thrown onto a bed by a tall, muscular man。He grabs her hand, and fla

her man across

2026-05-15 Caiwei Chen

开发者生态 None

Claude Code 如何在大型代码库中工作

How Claude Code works in large codebases: Best practices and where to start The most successful Claude Code deployments

Claude Code and

2026-05-15 shenli3514

智能AI None

迈向法学硕士的下一个前沿，私有数据培训：联合微调的跨域基准

13936v1 Announce Type: new Abstract: The recent success of large language models (LLMs) has been largely driven by vast

and data across

2026-05-15 Daniel M. Jimenez-Gutierrez, Enrique Zuazua, Georgios Kellaris, Joaquin del Rio, Oleksii Sliusarenko, Xabi Uribe-Etxebarria

智能AI None

通过稀疏自动编码器对脑电图基础模型进行机械解释

arXiv:2605.13930v1 Announce Type: new Abstract: EEG foundation models achieve state-of-the-art clinical performance, yet

and the clinical

2026-05-15 William Lehn-Schi{\o}ler, Magnus Ruud Kj{\ae}r, Rahul Thapa, Magnus Guldberg Pedersen, Anton Storgaard Mosquera, Nick Williams, Radu Gatej, Tue Lehn-Schi{\o}ler, S\'andor Beniczky, Sadasivan Puthusser