让大模型从“被动应答”走向“主动服务”，教你训练会察言观色的个性化AI代理，附完整方法框架。
arXiv:2511.02208v2 Announce Type: replace Abstract: Despite rapid progress, current AI agents are primarily optimized for isolated task completion. We…
AI tutor 直接从你的资料出题，读书科研的好帮手，告别泛泛而谈的通用问答
I built Learn Leap because I found myself constantly asking ChatGPT questions while reading research papers. I wanted something that already understoo…
不看任务准确率，专测AI模仿你文风的“神似度”，PersonalBench填补了个性化写作评测空白
arXiv:2608.19746v1 Announce Type: new Abstract: Personalized text generation aims to make LLMs write in a specific individual's style, yet existing be…
AI 根据聊天偏好实时调整内容流，记住你的喜好，让每次刷新都更懂你。
Google will soon allow you to customize your Discover feed by describing what you want to see. The new feature, rolling out to the Google app in the "…
大模型结合强化学习，打造精准适配每位学生的AI导师，个性化教育迎来新突破。
arXiv:2608.16907v1 Announce Type: cross Abstract: Generative AI (GenAI) is rapidly reshaping education by unlocking the potential for personalized tut…
当LLM装上“大脑”，BYOK模式开启个性化智能新玩法，值得一看
Article URL: https://alicebraincore.web.app Comments URL: https://news.ycombinator.com/item?id=49357139 Points: 1 # Comments: 0
稀疏数据下用推理增强个性化生成，少样本也能精准建模，推荐给做推荐系统的朋友。
arXiv:2602.21219v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) personalization holds great promise for tailoring responses by le…
用AI定制从入门到进阶的课程，再通过提问检测你的理解，开源可自部署。
I used to learn from books and courses. But I kept realising I hadn't built a real mental model. I always needed an LLM on the side to fill in what th…
Win11 入门应用大更新，新增推荐、个性化等页面，帮您快速玩转新系统。
IT之家 8 月 18 日消息，科技媒体 NeoWin 今天（8 月 18 日）发布博文，报道称在今天发布的 Windows 11 26H2 Build 26340.9212 预览版中， 微软更新“入门”（Get Started）应用程序，加入应用安装、网站固定和个性化主题等页面。 在本次版本更新中…
用作者身份验证理论评估LLM风格个性化，揭示模型模仿个人文风时的真实差距与评测盲点。
arXiv:2604.26460v2 Announce Type: replace Abstract: Stylistic personalization - making LLMs write in a specific individual's style, rather than merely…
元学习+LoRA让大模型快速适应跨域偏好，个性化调校从此更聪明高效。
arXiv:2608.12389v1 Announce Type: new Abstract: Cross-domain zero- or few-shot personalization aims to generate user-preferred responses in unseen con…
IT之家 8 月 13 日消息，据外媒 GSMarena 今天（13 日）晚间报道，传音旗下品牌 TECNO 正式发布了此前已经多次曝光的 Pova 8 Pro。 TECNO Pova 8 Pro 搭载 天玑 7400 Ultimate 芯片 ，最高提供 12GB 内存和 512GB 存储空间，并额…
大模型生成教育反馈时，如何感知学习者差异？这项研究用实证设计给出新思路。
arXiv:2602.11650v2 Announce Type: replace Abstract: Although large language models (LLMs) show promise for generating educational feedback, it remains…
不用改权重，在输出空间“调参”就能个性化LLM，轻量又省资源。
arXiv:2608.11342v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) is a standard approach for adapting LLMs to a target distribution, but in…
IT之家 8 月 11 日消息，现如今，个性化定制正成为超豪华汽车领域的热门趋势。几乎每一辆劳斯莱斯都是按客户要求专门定制的，迈巴赫也有 Made to Measure 定制项目，保时捷的 Sonderwunsch 和 Exclusive Manufaktur 项目也比以往任何时候都更受欢迎。 据外…
答完30秒问卷，AI按亲密度、兴趣和预算排出礼物清单，还附解释，送礼不再头大。
Most "AI gift finders" are a search box with a chatbot glued on. I wanted to build something different — GiftHive , a quiz-driven gift recommender tha…
把个性化奖励拆解成可解释概率偏好，不确定性建模让LLM对齐更稳更准。
arXiv:2604.00997v2 Announce Type: replace Abstract: Reward factorization personalizes large language models (LLMs) by decomposing rewards into shared …
LLM推理并非万能，主观任务中会失灵？这篇论文剖析失败模式并给出动态路由方案。
arXiv:2608.08889v1 Announce Type: new Abstract: Recommendation systems thrive on personalization, where ''correctness'' is rarely a binary truth but a…
用结构化记忆给LLM“降噪”，破解过度个性化难题，AI调校新思路。
arXiv:2608.08300v1 Announce Type: new Abstract: Conversational assistants increasingly rely on persistent long-term memory to personalize responses ac…