Skip to content

Author

Nicolás Vera Zúñiga

7 papers indexed here

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.

#natural language process... Preprint Oct 2026

Easy to anticipate, hard to compute: boundary dependence finds the computed outputs that entropy patching misses

Byte-level language models such as the Byte Latent Transformer (BLT) group bytes into patches and run their large global model once per patch. BLT starts a patch where a small model's next-byte entropy is high, so global compute goes where the next byte is hard to predict. We show that this rule has a systematic blind...

Nicolás Vera Zúñiga · 2 citations
#artificial intelligence Preprint Sep 2026

Unknown is not normal: separating language-model extraction from rule-based decision logic for clinical risk scores

This work tests whether separating three-state extraction (present, absent or unknown, by an LLM) from decision logic (deterministic code computing score bounds over unknown inputs) lets a system ask only questions that can change the decision.

Nicolás Vera Zúñiga · 0 citations
#natural language process... Preprint Sep 2026

Where a Model Sends Its Own Repeated Token

Black-box model identification works by scoring a model's response to natural-language prompts. One line of work feeds models a degenerate input -- their own token, repeated -- to find a failure mode rather than an identity. We take that input and ask where the model goes when it does not. For each token t, read argmax...

Nicolás Vera Zúñiga · 0 citations
Preprint Aug 2026

What Iterated Self-Feeding Probes of Language Models Measure, and a test that separates the construction from the model

The instrument is validated by reproduction first, recovering a Domany-Kinzel damage field bit-exactly against an independent prediction, and the estimator failures that this discipline caught are reported -- four retracted verdicts, each on a quantity that looked like a measurement.

Nicolás Vera Zúñiga · 3 citations
Preprint Aug 2026

Prompt-Model Interaction Reaches the Fixed Points: A deterministic, task-free structural readout -- and the factorizations of it that failed

Four phenomenological factors -- prose-versus-markup, a universal direction, bidirectionality, instruct-resistance, and four phenomenological factors -- were each withdrawn within one run of being proposed, dissolved by widening the sample.

Nicolás Vera Zúñiga · 1 citation · ⚡1

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.