framework
active
framework:bayesian-icl-xie-et-al-2022Bayesian ICL (Xie et al. 2022)
Prior framework explaining ICL as inference over task structure; UCCT adopts and extends the Bayesian lens
Neighborhood — ranked by edge-count
Artifacts (1)
artifact
- Main paper presenting UCCT and semantic anchoring framework.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Views transformers as performing implicit gradient descent; UCCT complements this mechanistic account
- Views ICL as a form of meta-learning; UCCT sits alongside this account
- Umbrella framework for brain-centric Bayesian approaches; contrasted with active inference
- Online inversion of nonlinear dynamic causal models using DEM.
- The ideal limit of self-supervised learning as modeling the true conditional distribution.
- Framework for maximizing expected utility under uncertainty.