#learning

智能AI None

用于协调分布式能源资源的监督强化学习

arXiv:2606.24947v1 Announce Type: new Abstract: The increasing integration of distributed energy resources (DERs) is cru

for and fine

2026-06-25 Haoyuan Deng, Yihong Zhou, Thomas Morstyn, Yi Wang

智能AI None

通过约束流形控制的安全且可推广的分层多智能体强化学习

24010v1 Announce Type: new Abstract: Multi-agent systems are widely used in safety-critical applications that require co

safety and learning

2026-06-24 Zihao Guo, Jianing Zhao, Ling Li, Hao Liang, Giuseppe Loianno, Yali Du

智能AI None

新联想主义：深度学习的教训

20600v1 Announce Type: new Abstract: What can the success of modern AI tell us about how humans learn。

learning the that

2026-06-23 Daniel Rothschild

智能AI None

通过条件标准化流实现不确定性感知多保真闭包

arXiv:2606.09857v1 Announce Type: new Abstract: Reduced-order models (ROMs) provide an efficient surrogate for complex m

the and ROM

2026-06-10 Jice Zeng, Shady E. Ahmed, David Barajas-Solano, Panos Stinis

智能AI None

通过专家混合应对多模式学习挑战：一项调查

arXiv:2605.27431v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) presents a naturally compatible and scalable fr

and MoE multimodal

2026-05-28 Liangwei Nathan Zheng, Wei Emma Zhang, Olaf Maennel, Lin Yue, Weitong Chen

开发者生态 None

Pelica (YC P25) 正在招聘

Pelica Transforming healthcare operations with AI agents Machine Learning Engineer $80K - $150K • San Francisco, CA, US

and with learning

2026-05-28 lalitkundu

开发者生态 None

从数据中学习什么时候起作用（数学从基本概率开始）

VC Dimension and the Fundamental Theorem of Statistical Learning — from Scratch May 2026 This post answers a single ques

the mathcal and

2026-05-24 alok-g

智能AI None

SOLAR：一种自我优化的开放式自主代理，用于终身学习和持续适应

arXiv:2605.20189v1 Announce Type: new Abstract: Despite the remarkable success of large language models (LLMs), they sti

the adaptation and

2026-05-22 Nitin Vetcha, Dianbo Liu

智能AI None

通过反事实推理路径减少信用分配方差

arXiv:2605.16302v1 Announce Type: new Abstract: Reinforcement learning for multi-step reasoning with large language mode

the and reasoning

2026-05-19 Fei Ding, Yongkang Zhang, Yeling Peng, Youwei Wang, Guoxiong Zhou, Zijian Zeng

智能AI None

伯克利神作背刺OpenAI：持续学习才是真神！

新智元报道 【新智元导读】 伯克利等发布FST框架：通过快慢分层解决大模型持续学习死局。AI工程师Dan McAteer大胆预言，2026年持续学习（continual learning）即将爆发。通过记忆/上下文快速适应+权重缓慢调整的分

推理 持续学习 Learning

2026-05-19 新智元

开发者生态 None

自我蒸馏实现持续学习 [PDF]

Computer Science > Machine Learning arXiv:2601。

learning Learning arXiv

2026-05-17 teleforce

智能AI None

EMA：基于学习的系统的高效模型适应

13942v1 Announce Type: new Abstract: Machine learning (ML) is increasingly applied to optimize system performance in tas

and system training

2026-05-15 Daiyang Yu, Xinyu Chen, Yihan Zhang, Yan Liang, Yaqi Qiao, Fan Lai

开发者生态 None

用于刻意技能发展的克劳德代码和法典技能

Learning Opportunities: A Claude Code and Codex Skill for Deliberate Skill Development Build your expertise, not just yo

learning opportunities plugin

2026-05-14 cdrnsf

智能AI None

RankQ：通过自监督行动排名进行线下到线上的强化学习

11151v1 Announce Type: new Abstract: Offline-to-online reinforcement learning (RL) improves sample efficiency by leverag

learning online action

2026-05-13 Andrew Choi, Wei Xu

智能AI None

通过 Cram\'er 距离进行分布式强化学习

arXiv:2605.08104v1 Announce Type: new Abstract: This paper explores the application of the Soft Actor-Critic (SAC) algor

the and algorithm

2026-05-12 Vanya Aziz, Ivo Nowak, E. M. T Hendrix

智能AI None

CASCADE：部署期间基于案例的大型语言模型持续适配

arXiv:2605.06702v1 Announce Type: new Abstract: Large language models (LLMs) have become a central foundation of modern

and deployment learning

2026-05-11 Siyuan Guo, Yali Du, Hechang Chen, Yi Chang, Jun Wang

安全攻防 None

在 ShinyHunters 威胁泄露学校数据后，Canvas 再次上线

The Instructure-owned learning management platform, Canvas, is now online again after it went down following a massive d

the The Instructure

2026-05-08 Jess Weatherbed

安全攻防 None

超越神经网络的数据驱动变分基础学习：自适应基础发现的非神经框架

arXiv:2605.05221v1 Announce Type: new Abstract: Classical representation systems such as Fourier series, wavelets, and f

and basis the

2026-05-08 Andrew Kiruluta