IEEE

Logic Consistency Makes Large Language Models Personalized Reasoning Teachers

Large Language Models (LLMs) have advanced natural language processing, particularly through Chain-of-Thought (CoT) reasoning, but their high computational costs limit deployment. We propose ...
the-decoder

OLMo 3 debuts as the first fully open "thinking" model with step-by-step logic exposed to users

(★ indicates Olmo won the category; indicates Olmo is within 2.0 points of the top score. Additional comparisons are available in the full report.) Bringing transparency to reasoning models OLMo ...
openaccessgovernment

Decoding Ukraine’s naval victories: A logic model approach

This article introduces the Black Sea Battle Lab (BBL) logic model, a framework designed to trace how Ukraine’s operational responses to Russia’s invasion link strategic pressures to measurable ...
IEEE

Model Predictive Control for Systems With Partially Unknown Dynamics Under Signal Temporal Logic Specifications

Abstract: In this letter, we design a model predictive controller (MPC) for systems to satisfy Signal Temporal Logic (STL) specifications when the system dynamics are partially unknown, and only a ...