When intelligence is distributed across many parts, be they robots, devices, or objects, it can be tricky for the bigger picture to emerge. Yet answering these questions is key to making collective systems that are easy to design, monitor and control.

EMERGE will deliver a new philosophical, mathematical, and technological framework to demonstrate, both theoretically and experimentally, how a collaborative awareness – a representation of shared existence, environment and goals – can arise from the interactions of elemental artificial entities.

In this effort, we will rely only on unstructured conditions that the real world demands without leveraging a pre-existing shared language between them. Our goal is to surpass the limitations and barriers of the current state-of-the-art distributed systems to produce breakthroughs and open new markets in the next generation of robotic systems.

Learn More

Latest News

Publication: MAINLE: A Multi-Agent, Interactive, Natural Language Local Explainer of Classification Tasks

Publication: MAINLE: A Multi-Agent, Interactive, Natural Language Local Explainer of Classification Tasks

Calendar30 September 2025

In this work, EMERGE partners from the University of Pisa introduce a multi-agent architecture to provide interactive explanations for classification tasks based on a range of machine learning algorithms, so that end-users can obtain answers in natural language.

View Article

Publication: Sparse Autoencoders Find Partially Interpretable Features in Italian Small Language Models

Publication: Sparse Autoencoders Find Partially Interpretable Features in Italian Small Language Models

Calendar26 September 2025

In this work, EMERGE partners from the University of Pisa provide an early evaluation on the feasibility of using Sparse Autoencoders to interpret models trained to be natively Italian.

View Article

Publication: MAIA: a Benchmark for Multimodal AI Assessment

Publication: MAIA: a Benchmark for Multimodal AI Assessment

Calendar26 September 2025

In this work, EMERGE partners from the University of Pisa introduce MAIA, a multimodal dataset developed as a core component of a competence-oriented benchmark designed for fine-grained investigation of the reasoning abilities of Visual Language Models (VLMs) on videos.

View Article

Partners

The EMERGE consortium brings together the University of Pisa (Italy), Ludwig Maximilian University of Munich (Germany), Delft University of Technology (Netherlands), University of Bristol (United Kingdom), and Da Vinci Labs (France).

View Consortium