MOICL: Mixtures of In-Context Learners

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Mixture-of-Experts (MoE)concept0.755
  Architecture of Mixtral-8x7B; uses sparse expert routing affecting how hidden states are computed across layers.
• In-Context Learning of Representations (Park et al. 2025)framework0.738
  Reports phase-like breakpoints and geometry changes as context scales; UCCT provides measurable predictor
• in-context learning (ICL)concept0.735
  Test-time adaptation from prompt or retrieved context with no parameter updates.
• Synthetic In-Context Learning Task with Predefined Geometriesconcept0.718
  An additional task in the full paper where geometric structure is predefined and used to test whether representation and behavior geometry align.
• In-Context Learning as Optimizationconcept0.717
• Contrastive learningframework0.717
  Supervised learning framework where system learns by observing contrast between current response and nudged improved response; requires weak additional forces from supervisor
• A family of contrastive learners converges to a representation whose kernel is the pointwise mutual information (PMI) of the underlying eventshypothesis0.715
  Mathematical formalization of what representation models converge to
• Multi-Task Learningconcept0.711
  Learning paradigm that jointly learns multiple related tasks using a single model