Junnan Dong writes about the WFM (Wiki Foundation Model), a novel paradigm designed to improve how AI agents utilize complex knowledge through an agent-native representation called LLM Wiki. Moving beyond traditional sparse graph representations, this model couples dense document contexts with multi-layered topological linkages via a specialized "Wiki Graph" schema. To address scalability issues in large-scale commercial deployments, the authors introduce an infrastructural NCCL boundary exchange protocol that optimizes distributed training by bypassing CPU serialization and leveraging fixed-shape GPU-to-GPU collectives.
- achieves 10.5 times training acceleration on distributed clusters
- uses a query-conditioned attentive aggregation for rich wiki message passing
- includes explicit attention variance regularization to improve semantic density
- outperforms existing models across five long-term agent memory and multi-hop reasoning benchmarks
- achieves 10.5 times training acceleration on distributed clusters
- uses a query-conditioned attentive aggregation for rich wiki message passing
- includes explicit attention variance regularization to improve semantic density
- outperforms existing models across five long-term agent memory and multi-hop reasoning benchmarks
Dr. Ora Lassila is a Principal Graph Technologist at AWS, working within the Amazon Neptune team with a primary focus on knowledge graphs. Throughout his extensive career, he has held significant roles, including Managing Director at State Street and positions at Nokia Research Center and HERE. A recognized pioneer in his field, he co-authored the original W3C RDF specification and the seminal article on the Semantic Web. His professional expertise covers AI, ontologies, the Semantic Web, RDF, and Knowledge Representation. In addition to his technical contributions, he is an enthusiast of aviation photography and scale modeling, even applying knowledge graph technologies to manage his aviation photography business, So Many Aircraft.
