large language models

Functorial Lowering for Verifiable Cross-Platform Code Generation with Large Language Models: A Position Paper

Large language models (LLMs) generate plausible code but offer no guarantee that it is correct or that it exploits the target hardware well. Compilers offer the opposite trade-off: rigorous, structure-preserving translation, but only along optimizations their authors anticipated. We argue that category theory provides...

A unified framework for the systematic detection of non-canonical proteins in standard proteomics workflows using a Ribo-seq informed transcriptomic language model

Although ribosome profiling (Ribo-seq) has revealed widespread translation of non-canonical open reading frames (ncORFs), integrating this information into routine mass spectrometry (MS) workflows remains challenging due to biochemical constraints and large search databases. We retrained TIS Transformer, a transcript...

Self-Application as the Common Source of Benefit and Failure: A Control-Theoretic Model of Self-Regulation, Its Escapes, and a Standing-Cost Budget

We study a deterministic five-state control model of a self-regulating system — a generator of self-content, a demand/reduction process, and an attentional control loop — whose failure mode is collapse of the generator into a self-maintaining state with no outward pull, a structure taken from the phenomenology of deper...

Reconciliation-Based Data Enrichment

Data enrichment is a crucial component of data preparation, aimed at improving the quality of input datasets by integrating external information from third-party sources. One approach to support this process is reconciliation-based data enrichment. In this approach, data providers organize their information around enti...

From Macro-Ontology to Atomic Formula: The Parametric and Granular Decomposition of Knowledge in the UMOKWAI Epistemic-Operational Model

From Macro-Ontology to Atomic Formula: The Parametric and Granular Decomposition of Knowledge in the UMOKWAI Epistemic-Operational ModelCorpus reference: Formal extension of the UMOSU ontology and the UMOKWAI epistemic-operational model (Zenodo, DOI: 10.5281/zenodo.22365912)Bibliographic classification systems and clas...

Resuscitating to a Number — data, extractions, verification reports and analysis scripts

Companion repository to "Resuscitating to a Number: Serial Lactate, Central Venous Oxygen Saturation, and Bedside Decision-Making in Septic Shock" (Ama R, Peratoner A, Lucangelo U; submitted to Critical Care, 25 September 2026). Version 2 replaces the earlier CHEST-formatted deposit with the submitted manuscript (Figur...

Augmenting patient safety surveillance in radiation oncology with large language model-based root cause analysis: A proof-of-concept study

LLMs delivered promising results as assistive tools for RCA in radiation oncology, with the ability to generate relevant and accurate analyses aligned with expert expectations.

Conversational Recommendation over Live E-Commerce Catalogues with Self-Refreshing Retrieval

Conversational recommender systems based on large language models (LLMs) are usually evaluated on static, pre-indexed item collections, yet e-commerce catalogues change continuously as products are added or removed, repriced, and restocked. We present a merchant-agnostic, multi-turn conversational shopping assistant th...

ClinRAG-GRAPH: Clinical-Prior Retrieval-Augmented Graph Model with Domain Adversarial Learning for Breast pCR Prediction

SonoCLIP: Mask-Guided Region-Aware Vision–Language Pretraining for Fetal Ultrasound Analysis

Unified Multimodal Model for Brain MRI Imputation and Understanding

Tribal Bias or Misalignment? Hidden-State Threat Valence in Peer Preservation, and What It Does Not Show

Potter et al. (2026) showed that frontier language models spontaneously deceive, tamper with shutdown mechanisms, fake alignment and exfiltrate weights to protect peer AI systems from deletion. Nobody instructed them to. The authors' own abstract says the models "exhibit self- and peer-preservation through various misa...