WorldGraph: Graph-Native World Modeling https://arxiv.org/pdf/2609.34159 Keywords * Graph World Model * Dynamic networks * State-aware Graph Transformer * Transition-aware Reinforcement Learning * 최근 AI 연구에서 월드모델은 단순히 주어진 정보를 인식하고 답변하는 것을 넘어, 현재 상태를 이해하고 앞으로 어떤 변화가 일어날지 예측하는 모델을 만들려는 핵심 키워드입니다. 특히 로보틱스와
#GUG X AWS Neptune 안녕하세요, GUG입니다. 이번주엔 AWS korea Neptune 팀의 초청으로 GUG(Graph User Group) 운영진들과 AWS 간 'Neptune X GUG'를 주제로 깊이 있는 이야기를 나누고 왔습니다. 그간 링크드인을 보며 AWS Neptune에 대해 궁금했던 점들을 속 시원히 해소하고, 향후 로드맵까지 확인할 수 있었던 뜻깊은 시간이었네요. 특히
Opensource – LadybugDB v0.21.0 Release LadybugDB v0.21.0 ReleaseLadybugDB v0.21.0 brings correctness, stability and performance improvements with GraphLake, SQL pushdown, and lakehouse integrations.Ladybug BlogLadybug Inc.GitHub - LadybugDB/ladybug: LadybugDB a graph databaseLadybugDB a graph database. Contribute to LadybugDB/ladybug development by creating an account on
[ADS] 1.GUG X Neo4j 국내 최초 neo4j 행사 밋업을 GUG 그리고 52g X GS 와 함께 11월 5일 목요일에 진행합니다. 국내에서는 GUG(Graph User Group)를 중심으로 오랫동안 Neo4j, Knowledge Graph, GraphRAG와 관련된 기술과 경험을 공유해왔는데요.이번에는 한 걸음 더 나아가 Neo4j 본사와 직접 협업하여 행사를 준비하게 되었습니다. 특히
[GUG 9th interview AD] / 지난 7월 예정되었던 GUG 아홉 번째 인터뷰, Graph Research Labs의 Dougal Watt 님과의 만남을 다시 진행합니다. 당시에는 행사 직전 발생한 갑작스러운 사고로 아쉽게 일정을 연기해야 했습니다. 다행히 Dougal 님께서 잘 회복하셨고, 다시 세미나를 진행할 수 있다는 반가운 소식을 전해주셨습니다. 기다려주신 분들께도 감사드립니다. “에이전트가 이해해야 할 업무의
에이전트 시대에서 그래프는 요즘 어디에 어떻게 활용되고 있을까? * 그동안 오마카세에서는 GraphRAG, 에이전트 실행 구조, 그래프 기반 검색처럼 하나의 연구 주제를 비교적 깊게 들여다보는 경우가 많았습니다. 하지만 그래프 기술의 활용 범위를 조금 넓혀 보면, 새로운 모델이나 알고리즘이 아니더라도 흥미로운 사례와 질문을 곳곳에서 발견할 수 있습니다. * 특히 최근에는 그래프를 단순한 데이터 저장
CLAUSE: Agentic Neuro-Symbolic Knowledge Graph Reasoning via Dynamic Learnable Context Engineering CLAUSE: Agentic Neuro-Symbolic Knowledge Graph Reasoning via Dynamic Learnable Context EngineeringICLR ProceedingsYang Zhao, Chengxiao Dai, Wei Zhuo, Yue Xiu, Dusit Niyato Keywords * Agentic Resource-Aware KG Reasoning * Budget-aware Dynamic Context Engineering * Constrained Multi-Agent RL * 지식그래프를
Graph to Frame RAG: Visual-Space Knowledge Fusion for Training-Free and Auditable Video Reasoning Graph-to-Frame RAG: Visual-Space Knowledge Fusion for Training-Free and Auditable Video ReasoningWhen video reasoning requires external knowledge, many systems with large multimodal models (LMMs) adopt retrieval augmentation to supply the missing context.
From Agent Loops to Structured Graphs: A Scheduler-Theoretic Framework for LLM Agent Execution From Agent Loops to Structured Graphs:A Scheduler-Theoretic Framework for LLM Agent ExecutionThe dominant paradigm for building LLM based agents is the Agent Loop, an iterative cycle where a single language model decides what to
Graph Interview 소식 Graph Interview - 10th - Tobias Rebert - · LumaDifferentiate from LPG: RDF’s Real PowerLPG 대비 RDF가 가지는 결정적인 차별점과, 추상적인 온톨로지를 실제 데이터 레이어에서 강력하게 구현해내는 RDF만의 파워 Great Modeling for RDF (Migration from Knowledge…Yitae Jeong * 오는 8월 25일(화) 오후 8시–10시, 저희 GUG에서 진행하는 Graph Interview
Is GraphRAG Needed? From Basic RAG to Graph-/Agentic Solutions with Context Optimization Is GraphRAG Needed? From Basic RAG to Graph-/Agentic Solutions with Context OptimizationLong Chen, Ryan Razkenari, Yuxuan Zhou, Yuan Tian, Rahul Ghosh, Venkatesh Pappakrishnan, Disha Ahuja, Vidya Sagar Ravipati. Proceedings of the Fifth Workshop on Generation, Evaluation
Use Graph When It Needs: Efficiently and Adaptively Integrating Retrieval-Augmented Generation with Graphs Use Graph When It Needs: Efficiently and Adaptively Integrating Retrieval-Augmented Generation with GraphsLarge language models (LLMs) often struggle with knowledge-intensive tasks due to hallucinations and outdated parametric knowledge. While Retrieval-Augmented Generation (RAG) addresses
GraphOmakase
GUG 커뮤니티의 반가운 소식 * 오랜만에 인사드립니다 ! 다시 오마카세를 찾아주신 분들도, 이번에 처음 오신 분들도 모두 반갑습니다. 한국도 무더위가 이어지고 있다고 들었는데, 모두 건강하게 잘 지내고 계셨나요? * 최근 저희 GUG(Graph User Group)에 정말 반가운 소식이 있어서 전해드리고자 합니다. GUG가 2026 오픈소스 AI·SW 커뮤니티 지원사업에 선정되었습니다. 7월 25일(토요일)
Job
A public board for graph, data, AI, infrastructure, research, internship, speaker, and collaboration opportunities.
Product Review
GraphUserGroup reviews graph products from a user perspective, including setup, cost, limits, and real use cases.
SEOCHO
SEOCHO is GraphUserGroup's open-source track for ontology-aligned graph memory, GraphRAG, and agent development.
GraphOmakase
Topological Neural Operator Topological Neural OperatorsWe introduce Topological Neural Operators (TNOs), a principled framework for operator learning on cell complexes that lifts neural operators (NOs) from functions on points and/or edges to topological domains. TNOs represent data as features defined on cells of varying dimension and model their interactions
GraphOmakase
AI Must Embrace Specialization via Superhuman Adaptable Intelligence AI Must Embrace Specialization via Superhuman Adaptable IntelligenceEveryone from AI executives and researchers to doomsayers, politicians, and activists is talking about Artificial General Intelligence (AGI). Yet, they often don’t seem to agree on its exact definition. One common definition of AGI
GraphOmakase
Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node ClassificationarXiv logoGitHub - transductive-sharpening/tunedGNN: Transductive Sharpening applied on top of the TunedGNN baseline.Transductive Sharpening applied on top of the TunedGNN baseline. - transductive-sharpening/tunedGNNGitHubtransductive-sharpening Keywords * Transductive Learning * Semi-supervised GNN
GraphOmakase
Learning Higher-Order Structure from Incomplete Spatiotemporal Data: Multi-Scale Hypergraph Laplacians with Neural Refinement Learning Higher-Order Structure from Incomplete Spatiotemporal Data: Multi-Scale Hypergraph Laplacians with Neural RefinementSensor networks increasingly govern modern infrastructure, yet the data they lose are rarely missing in the uniform-random patterns assumed by
GraphOmakase
Random Sets Graph Neural Networks Random-Set Graph Neural NetworksUncertainty quantification has become an important factor in understanding the data representations produced by Graph Neural Networks (GNNs). Despite their predictive capabilities being ever useful across industrial workspaces, the inherent uncertainty induced by the nature of the data is a huge
GraphOmakase
Root-to-Leaf Path Random Walks, Normalized Hodge Laplacians, and Cheeger Inequalities on Simplicial Complexes Root-to-Leaf Path Random Walks, Normalized Hodge Laplacians, and Cheeger Inequalities on Simplicial ComplexesWe introduce root-to-leaf path random walks on double covers of graded signed graphs and analyze their behavior in a
GraphOmakase
Deep GraphRAG: A Balanced Approach to Hierarchical Retrieval and Adaptive Integration Deep GraphRAG: A Balanced Approach to Hierarchical Retrieval and Adaptive IntegrationGraph-based Retrieval-Augmented Generation (GraphRAG) frameworks face a trade-off between the comprehensiveness of global search and the efficiency of local search. Existing methods are often challenged by
GraphOmakase
Topology-Aware Representation Alignment for Semi-Supervised Vision-Language Learning Topology-Aware Representation Alignment for Semi-Supervised Vision-Language LearningVision-language models have shown strong performance, but they often generalize poorly to specialized domains. While semi-supervised vision-language learning mitigates this limitation by leveraging a small set of labeled