paper
referenced-only
paper:gem-iniGem-ini: a family of highly capable multimodal models
Similar preprints — Semantic Scholar
Cited by (2)
- Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering
In-context learning and activation steering are the same operation on a latent-concept belief: context adds log-likelihood evidence while a steering vector adds a constant shift to the log prior odds,
- The Platonic Representation Hypothesis
Neural networks trained on different data modalities, architectures, and objectives are converging toward a shared statistical model of reality — what the paper terms the "platonic representation" — f