Author

Narcis Marincat

h-index 1 View on Semantic Scholar

We have 4 of 5 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

What You Can't See Is What You Learn: Slot-Selective Evidence Masking Favors Compositional Generalization in Shared-Genome Language-Model Societies

Multi-module neural systems often expose every module to the full input. We test whether a slot-selective evidence-masking regime -- restricting each module to its own evidence span -- changes which solutions gradient-based training discovers. Four-cell societies share one frozen pretrained language model and one low-r...

Narcis Marincat · 1 citation

#artificial intelligence Preprint Sep 2026

What You Can't See Is Still What You Learn: A Preregistered Sixty-Society Confirmation That Evidence Masking Drives Compositional Generalization

A preregistered confirmation with sixty four-cell systems sharing a frozen language-model backbone and communicating through learned continuous packets confirms a large advantage of the tested masking regime, while leaving its finer attribution and generality open.

Narcis Marincat · 0 citations

#artificial intelligence Preprint Sep 2026

Portable Semantics, Private Dialects: Reuse and Negative Transfer in Latent Communication Between Language-Model Cells

In shared-genome language-model societies, restricted evidence visibility favors reusable, value-indexed latent packet interfaces, whereas the sole high-performing globally visible model in the parent study learned an episode-entangled code. This companion study asks whether independently trained societies share one pa...

Narcis Marincat · 1 citation

What You Can’t See Is What You Learn: Restricted Evidence Visibility Favors Compositional Generalization in Shared-Genome Language-Model Societies

Under this protocol, restricted visibility is not necessary for composition; under this protocol it substantially increases the probability of learning a generalizing relay and favors a reusable, value-indexed interface.

Narcis Marincat · 2 citations