Find below EMERGE’s news articles, press releases, digests of scientific publications, as well as other outreach materials.
Publication: Adapting language models with continual learning for temporal drifts
28 March 2026
In this study, EMERGE partners from the University of Pisa address the challenge of keeping LLMs up to date with factual knowledge (adaptation) while avoiding forgetting the relevant existing knowledge.
Publication: Mental Models in Human-AI Interaction: Systematic Review of Empirical Methodologies and Guidelines
22 March 2026
In this work, EMERGE partners from the Ludwig Maximilian University of Munich systematically review 88 empirical studies that elicit humans’ mental models of AI systems.
Publication: Evaluating Online Moderation Via LLM-Powered Counterfactual Simulations
14 March 2026
In this study, EMERGE partners from the University of Pisa designed a LLM-powered simulator of Online Social Networks conversations enabling a parallel, counterfactual simulation where toxic behavior is influenced by moderation interventions, keeping all else equal.
Publication: Covert neural and autonomic signatures of shared perception
17 February 2026
In this study, EMERGE partners from the Ludwig Maximilian University of Munich tested whether awareness that a visual stimulus is simultaneously available to another person, without interaction, modulates behavioral performance and neurophysiological signatures of perceptual decision-making.
Publication: Sparse assemblies of recurrent neural networks with stability guarantees
03 February 2026
In this study, EMERGE partners from the University of Pisa introduce AdaDiag, a framework for constructing sparse assemblies of recurrent neural networks (RNNs) with formal stability guarantees.
Publication: Symbolic Learning of Interpretable Reduced-Order Models for Jumping Quadruped Robots
08 January 2026
In this study, EMERGE partners from the Delft University of Technology propose a methodology that combines a linear autoencoder with symbolic regression to derive reduced-order models that are central to motion planning and control of quadruped robots.
Publication: AI’s assigned gender affects human-AI cooperation
19 December 2025
In this study, EMERGE partners from the Ludwig Maximilian University of Munich investigates how cooperation varies with the gender labels assigned to AI partners.
Publication: SONAR: Long-Range Graph Propagation Through Information Waves
01 December 2025
In this work, EMERGE partners from the University of Pisa introduce SONAR, a novel GNN architecture inspired by the dynamics of wave propagation in continuous media.
Publication: A Framework for the Examination of Awareness in Artificial Systems
25 November 2025
In this work, EMERGE partners propose a novel and tractable approach to measure the impact of awareness on system performance, structured around distinct dimensions of awareness – temporal, spatial, metacognitive, self and agentive.
