most citedEmergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs

22 citations

129 papers

cs.DC20261 cited

Quantum Blackhole Learning-Optimized Hadamard Neural Network Model for Dynamic Resource Reservation in Industry Clouds

Deepika Saxena, Hari Mohan Gaur, Ashutosh Kumar Singh +1

Accurate workload prediction and proactive resource reservation are crucial for industry clouds. However, the conventional machine learning (CML) models with limited learning capab…

cs.RO2026

Design of a Human-Assistance Robot System with Contextual Action Recognition

Amanuel Ergogo, Teresa Zielińska

This paper presents a conceptual design for a proactive human assisting robot system capable of recognizing human activities and responding proactively. The system leverages contex…

cond-mat.soft2026

Pitch-controlled reorientational nonlinearity in chiral nematic liquid crystals: a reduced-order model for self-focusing and soliton formation

Homa Saadatmand, M. Javad Zakeri, Ahmed Sameh Ahmed +6

We present a reduced-order semi-analytical model for reorientational nonlinearity in chiral nematic liquid crystals, showing that the chiral pitch acts as the dominant physical len…

cond-mat.mtrl-sci2026

Comparison of mechanical properties of Ag/W1-xTixB2.5 and pure silver coatings deposited by PLD/HIPIMS method

Katarzyna Zielińska, Mateusz Włoczewski, Rafał Psiuk +4

Transition metal borides are attracting increasing interest due to their unique properties. They are not only characterised by very high hardness, but also considerable chemical an…

cs.CL2026

On Measuring Semantic Preservation in Legal Ontology Learning

Albert Sadowski, Jarosław A. Chudziak

Ontology learning transforms unstructured text into structured representations for automated reasoning. Yet structuring information risks losing it, and current evaluation methodol…

cs.LO2026

Explainable Belief Harmonization under Dynamic Epistemic Partitions

Adam Kostka, Jarosław A. Chudziak

Existing approaches to multi-agent belief combination have established mature foundations for combining uncertain beliefs under common assumptions: consensus methods use iterative…