专为研究软件工程协作设计的AI对齐代理Aleena，让AI队友更懂人类科学家的需求与节奏！
arXiv:2607.08043v1 Announce Type: cross Abstract: Research software collaborations span meetings, informal chats, pull requests, and GitHub issues. A …
日本电信巨头KDDI遭遇大规模数据泄露，超1200万邮箱和700万密码遭黑客窃取，影响持续一个月
IT之家 7 月 7 日消息，日本电信运营商 KDDI 今日表示，今年 5~6 月发生的其面向 ISP （IT之家注：互联网服务提供商） 运营商的电子邮件平台遭遇未经授权访问致使数据泄露事件 影响了超 1233 万用户的电子邮件地址和近 762 万用户的密码 。 IT之家了解到，KDDI 为一些日本…
利用LLM实现电商定价中长期价值对齐，KDD 2026 oral论文，AI赋能商业决策新范式。
arXiv:2606.26787v1 Announce Type: cross Abstract: Traditional dynamic pricing models in large-scale e-commerce suffer from limited interpretability, p…
KDD 2026论文提出Tokenized MoE框架，用专家混合机制突破GNN泛化瓶颈
arXiv:2602.09258v2 Announce Type: replace Abstract: Deployed graph neural networks (GNNs) are frozen at deployment yet must fit clean data, generalize…
大模型与图数据深度融合，构建原生图协同AI系统，来自PAKDD前沿教程。
arXiv:2606.11560v1 Announce Type: cross Abstract: Large Language Models (LLMs) have advanced rapidly, but their limitations in structured and multi-ho…
LLM语义注入工业跨域推荐，新方法Atomic Intent Reasoning在KDD 2026提出，破解内容到电商的推荐难题。
arXiv:2606.10357v1 Announce Type: cross Abstract: Cross-domain recommendation is a core problem in content-to-e-commerce platforms. Its objective is t…
KDD 2026论文：用语义ID推理提升生成式推荐，新思路值得关注
arXiv:2603.23183v2 Announce Type: replace-cross Abstract: Recent advances in generative recommendation have leveraged pretrained LLMs by formulating s…
KDD 2026新研究，对比SHAP、规则提取与RuleSHAP三种全局可解释方法，检测大模型中注入的误导信息行为。
arXiv:2505.11189v3 Announce Type: replace-cross Abstract: Large language models (LLMs) can amplify misinformation, undermining societal goals such as …
联邦学习与大语言模型交叉领域的最新综述，由PAKDD 2026接收，系统梳理进展并展望未来方向。
arXiv:2409.15723v3 Announce Type: replace Abstract: Large Language Models have achieved impressive performance across diverse applications, yet their …
面向异构网络威胁情报的RAG基准测试，填补安全领域大模型应用评估空白，KDD 2026收录。
arXiv:2510.11974v2 Announce Type: replace-cross Abstract: Cyber Threat Intelligence (CTI) is foundational to modern cybersecurity, enabling organizati…
被KDD 2026收录的AI for Science研究，数据驱动AI揭示复合洪水形成机制
arXiv:2506.04281v2 Announce Type: replace Abstract: Compound flooding, driven by nonlinear interactions between multiple hydrometeorological factors, …
通过约束微调中的安全token，在极少量参数变动下保住大模型的安全护栏，KDD 2026 新思路。
arXiv:2603.07445v2 Announce Type: replace Abstract: Large language models (LLMs) often require fine-tuning (FT) to perform well on downstream tasks, b…
一项被KDD 2026接收的新方法，通过形式化与校准探针精准映射大模型推理能力，揭示LLM深层认知图谱。
arXiv:2603.05290v2 Announce Type: replace Abstract: Large language models (LLMs) achieve promising performance, yet their ability to reason remains po…
顶会KDD 2026提出HyperPatch，解决大模型在n元结构漂移下的顺序知识编辑难题，新范式值得关注
arXiv:2606.03179v1 Announce Type: new Abstract: Large Language Models (LLMs) rely on Knowledge Editing (KE) to maintain temporal validity, yet real-wo…
通过基准测试和干预审计，揭秘大模型在学者推荐中的公平性隐患
arXiv:2602.08873v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are now used for academic expert recommendation. Existing audit…
多智能体系统故障溯源难？基于时间语义的新框架StepFinder，被KDD 2026接收，帮系统快速定位协作失败根源。
arXiv:2606.03467v1 Announce Type: new Abstract: LLM-based multi-agent systems exhibit remarkable collaborative capabilities in complex multi-step task…
重新审视LLM如何利用拓扑与文本双重信息，提升文本属性图的分布外检测性能，被KDD 2026收录的研究。
arXiv:2602.11641v2 Announce Type: replace Abstract: Text-attributed graphs (TAGs) associate nodes with textual attributes and graph structure, enablin…
用LLM多智能体协作生成教育视频，颠覆传统端到端模型，KDD'26收录的学术新范式。
arXiv:2602.11790v2 Announce Type: replace Abstract: Although recent end-to-end video generation models demonstrate impressive performance in visually …
KDD 2026论文提出针对纵向数据中罕见事件的可扩展反事实风险估计方法，解决因果推断与高维数据挑战。
arXiv:2606.01539v1 Announce Type: cross Abstract: Estimating the causal effect of time-varying treatments on survival outcomes in large observational …
SIGKDD 2026接收论文，提出TimeBlocks统一时间序列建模框架，兼具基础模型能力与持续学习，适合时序预测研究者。
arXiv:2606.02142v1 Announce Type: new Abstract: The ongoing digitization has led to a proliferation of time-series data streams that monitor a variety…