1
个性化你的桌面，谷歌 Pixel Launcher 整合迪斯科风主题图标
谷歌Pixel Launcher新添迪斯科风主题图标，桌面自定义更个性
IT之家 5 月 23 日消息，科技媒体 Android Authority 昨日（5 月 22 日）发布博文，报道称伴随着“迪斯科风”主题图标在社交平台走红， 谷歌将其做成 Pixel Launcher 的官方自定义样式，Pixel 用户现在可以直接套用。 Pixel 手机迪斯科风图标主屏 IT之…
2
TabulaBili-Plus – 让 B 站暂时忘记你是谁[Chrome]
让B站首页回归“新用户热门推荐”，一键摆脱个性化算法束缚。
这是一个让 B 站首页重新回到“新用户热门推荐”模式的浏览器扩展。安装之后，首页不再根据你的观看习惯、兴趣偏好来推荐内容，而是直接显示当前热门视频，用来摆脱个性化推荐算法。@Appinn 来自发现频道，tjsky 同学的自荐：https://meta.appinn.net/t/topic/85526
3
Evaluating the Utility of Personal Health Records in Personalized Health AI
最新arXiv研究系统评估个人健康记录对个性化健康AI的效用，揭示数据价值与挑战
arXiv:2605.18937v1 Announce Type: new Abstract: Patient-managed Personal Health Records (PHRs) promises to empower patients to better understand their…
4
Query-Conditioned Graph Retrieval for Contextualized LLM Reasoning in Personalized Wearable Data
提出一种查询条件图检索方法，为大模型在个性化可穿戴数据分析中精准选择上下文，提升效率与推理质量。
arXiv:2605.18763v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly applied to analyzing wearable sensing data, which are …
5
A Survey on Foundation Models for Personalized Federated Intelligence
综述探讨基础模型在个性化联邦智能中的应用，汇总当前方法、挑战与未来方向。
arXiv:2505.06907v2 Announce Type: replace-cross Abstract: The rise of large language models (LLMs), such as ChatGPT, Gemini, and Grok, has reshaped th…
6
PPAI: Enabling Personalized LLM Agent Interoperability for Collaborative Edge Intelligence
将个性化LLM代理部署到边缘设备，实现P2P协作，突破本地能力限制
arXiv:2605.18067v1 Announce Type: new Abstract: Deploying large language model (LLM) on edge device enables personalized LLM agents for various users.…
7
科技云报到：当AI闯入特教行业，一场颠覆变革正在发生！
AI正突破特教行业“不可能三角”，用精准个性化干预让偏远地区孩子也能享受优质康复资源。
8
Personalized Digital Health Modeling with Adaptive Support Users
从人口预训练到自适应支持，新方法解决数字健康中数据稀疏下的个性化建模难题
arXiv:2605.02004v2 Announce Type: replace Abstract: Personalized models are essential in digital health because individuals exhibit substantial physio…
9
Cognitive-Uncertainty Guided Knowledge Distillation for Accurate Classification of Student Misconceptions
用认知不确定性引导知识蒸馏，解决学生误解分类中数据稀疏与边界模糊难题。
arXiv:2605.14752v1 Announce Type: cross Abstract: Accurately identifying student misconceptions is crucial for personalized education but faces three …
10
Collaborative Yet Personalized Policy Training: Single-Timescale Federated Actor-Critic
联邦强化学习新突破：单时间尺度actor-critic框架平衡协作与个性化，适合多智能体异构环境。
arXiv:2605.14423v1 Announce Type: cross Abstract: Despite the popularity of the actor-critic method and the practical needs of collaborative policy tr…
11
Thinking Ahead: Prospection-Guided Retrieval of Memory with Language Models
提出前瞻性引导的记忆检索方法，让对话助手在长周期交互中准确找回语义相似度低的关键事实，突破传统RAG回溯局限。
arXiv:2605.14177v1 Announce Type: cross Abstract: Long-horizon personalization requires dialogue assistants to retrieve user-specific facts from exten…
12
CineMesh4D: Personalized 4D Whole Heart Reconstruction from Sparse Cine MRI
4D心脏重建新突破，从稀疏MRI实现个性化高精度建模
arXiv:2605.13994v1 Announce Type: cross Abstract: Accurate 3D+t whole-heart mesh reconstruction from cine MRI is a clinically crucial yet technically …
13
Mixed Integer Goal Programming for Personalized Meal Optimization with User-Defined Serving Granularity
新方法用混合整数目标规划解决膳食规划中份量不合理和约束冲突问题，实现个性化营养优化。
arXiv:2605.13849v1 Announce Type: new Abstract: Determining what to eat to satisfy nutritional requirements is one of the oldest optimization problems…
14
LLM-Based Intelligent Notification Composition: From Static Personalization to Context-Aware Persuasive Messaging
从静态模板到动态说服，LLM如何让通知消息更懂你的场景与需求？
arXiv:2605.16264v1 Announce Type: cross Abstract: Push notifications remain among the most direct channels through which digital platforms engage user…
15
PersonalHomeBench: Evaluating Agents in Personalized Smart Homes
AI智能体在个性化智能家居环境中的表现如何？全新基准PersonalHomeBench帮你科学评估。
arXiv:2604.16813v3 Announce Type: replace Abstract: Agentic AI systems are rapidly advancing toward real-world applications, yet their readiness in co…
16
Ask HN: Who is working on applying AI to learning?
AI如何成为学习加速器而非技能杀手？HN社区正热议自适应学习与个性化内容定制。
For me, this is the real exciting stuff. Using AI, not to atrophy existing skills in humans, but to facilitate them to learn more things, faster. I'm …
17
Capability Conditioned Scaffolding for Professional Human LLM Collaboration
大型语言模型个性化新方案：Capability Conditioned Scaffolding，解决专业领域依赖AI推理导致的能力漂移风险。
arXiv:2605.15404v1 Announce Type: new Abstract: Large language model personalization typically adapts outputs to user preferences and style but does n…
18
NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation
多智能体协同进化技能与记忆，实现个性化研究全流程自动化，直击“为谁自动化”的核心问题。
arXiv:2605.10813v2 Announce Type: replace Abstract: LLM-powered multi-agent systems can now automate the full research pipeline from ideation to paper…
19
An LLM-RAG Approach for Healthy Eating Index-Informed Personalized Food Recommendations
用大模型配合检索增强，结合健康饮食指数，精准推荐个性化餐食，AI赋能营养科学。
arXiv:2605.15213v1 Announce Type: cross Abstract: Diet quality is a leading determinant of chronic disease risk. Advances in artificial intelligence (…
20
微软承认个性化是 Windows 基因，承诺为 Win11 推出更多控制功能
微软终低头！Win11任务栏可移动，开始菜单自定义即将回归
IT之家 5 月 17 日消息，据科技媒体 Windows Latest 今天报道，微软表示，个性化与自定义永远根植于 Windows 的 DNA，并计划未来几个月推出更多新功能，让用户能够自定义 Win11 的开始菜单、任务栏。 据报道，Windows 曾是微软最核心的产品，但最近几年微软大力押注…