扩散语言模型跨界图学习，文本属性图建模迎来新范式，值得关注的技术突破。
arXiv:2606.31166v1 Announce Type: cross Abstract: Text-attributed graphs (TAGs), where each node carries a natural language description, require model…
提出SkillMoV混合视图路由架构，用原型条件门控统一多视角能力估计，创新融合视图选择与专家路由
arXiv:2606.17615v1 Announce Type: cross Abstract: Estimating human proficiency from video is a key challenge for automated skill assessment, with appl…
LLM与GNN协同教学攻克少样本图学习难题，双模型互补超越单打独斗。
arXiv:2606.11583v1 Announce Type: new Abstract: Text-attributed graphs (TAGs) underlie real-world applications such as citation networks, social media…
普通Transformer在链接预测任务上表现惊人，挑战了图神经网络在该领域的传统认知。
arXiv:2602.01553v2 Announce Type: replace-cross Abstract: Link prediction is a core challenge in graph machine learning, demanding models that capture…
LLM在图数据标注中的失败模式，揭示无标签学习新路径
arXiv:2605.27913v1 Announce Type: new Abstract: Node classification on graphs often requires labeled nodes, yet obtaining labels at graph scale is exp…
融合Mamba状态空间模型与大语言模型推理，首度实现自闭症脑fMRI功能连接的动态图学习与解释
arXiv:2602.13770v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated strong semantic reasoning across multimodal d…
ICML 2026 接收论文，将 k-means 聚类重新诠释为链式思维推理，为图学习提供全新数学视角。
arXiv:2605.24867v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting has shown promise in enhancing the reasoning capabilities of large la…
利用大语言模型学习超图结构，实现可编辑性更强的平面图自动生成新方法。
arXiv:2605.18932v1 Announce Type: new Abstract: In this work, we propose HypergraphFormer, a novel and efficient approach to floor plan generation bas…
图学习新突破：拓扑到拓扑的LLM智能体，无需特征和任务知识即可高效处理CAD等图结构数据。
arXiv:2512.08964v4 Announce Type: replace Abstract: Graph learning aims to convert data into graph representations, which are fundamental to many prob…
用互kNN构建过程图，追踪多链推理中路径的共享与分裂，揭示思维过程几何。
arXiv:2605.14619v1 Announce Type: new Abstract: Multi-run chain-of-thought reasoning is usually collapsed to final-answer aggregates, which discard ho…
提出GelGT模型，用高斯机制突破传统消息传递局限，同步建模结构、语义与时间信息
arXiv:2605.15575v1 Announce Type: new Abstract: Relational graph learning models relational databases as graphs and has demonstrated superior performa…