5 papers
FITTER: Vocabulary-Agnostic Cross-Domain Inference on Temporal Knowledge Graphs
Jiaxin Pan, Mojtaba Nayyeri, Osama Mohammed +4
Temporal knowledge graphs are central to many uses of the Semantic Web, but existing completion methods assume the entities, relation names, and timestamps to be reasoned about are…
GRATE: Temporal Extensions for Inductive KG Foundation Models via Gated Rotary Attention
Jiaxin Pan, Osama Mohammed, Daniel Hernández +1
Knowledge graph foundation models such as Ultra and Trix achieve strong inductive transfer by learning relation-graph representations that generalise to unseen entities and relatio…
The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
MiniMax, :, Aili Chen +219
We introduce the MiniMax-M2 series, a family of Mixture-of-Experts language models built around the principle that mini activations can unleash maximum real-world intelligence. The…
Full-History Graphs with Edge-Type Decoupled Networks for Temporal Reasoning
Osama Mohammed, Jiaxin Pan, Mojtaba Nayyeri +2
Modeling evolving interactions among entities is critical in many real-world tasks. For example, predicting driver maneuvers in traffic requires tracking how neighboring vehicles a…
Towards Foundation Model on Temporal Knowledge Graph Reasoning
Jiaxin Pan, Mojtaba Nayyeri, Osama Mohammed +4
Temporal Knowledge Graphs (TKGs) store temporal facts with quadruple formats (s, p, o, t). Existing Temporal Knowledge Graph Embedding (TKGE) models perform link prediction tasks i…