# COLLAGE Lab

Current unsustainable AI monolithic approach: build, use and throw away (left); COLLAGE main approach (right): incrementally build, share and re-use knowledge and skills as a set of compositional building blocks that can be efficiently and effectively composed, adapted, and ultimately used for the specific task at hand in a decentralized network of AI applications.

The **COLLAGE Lab** advances the vision of **Sustainable Artificial Intelligence** understood as the pursuit of efficiency and democratization in AI development and use. While modern AI has achieved remarkable progress, it remains heavily dependent on vast computational and data resources, limiting accessibility and long-term scalability. At COLLAGE, we address this challenge by rethinking AI from the ground up through the concept of **reusability**—the idea that AI systems should be designed to evolve, adapt, and build upon existing knowledge rather than being recreated from scratch. Reusability serves as the foundation of our approach and can only be realized through **continuality**, **compositionality**, and **decentralization**. Continuality ensures that AI models can grow and adapt over time without catastrophic forgetting. Compositionality allows new systems to emerge from the combination and refinement of existing ones. Decentralization enables the open exchange and collective improvement of AI components across decentralized peer-to-peer networks. Together, these principles define a new paradigm for efficient and democratic AI—one that promotes shared progress and reduces the structural inefficiencies of current, siloed AI ecosystems. The COLLAGE Lab thus represents a shift from isolated, application-specific AI toward a **reusable, adaptable, and collectively built infrastructure** for intelligent systems. By developing the theoretical and methodological underpinnings of this vision, the lab aims to chart a path toward a truly sustainable AI—one that is not only computationally efficient but also accessible, transparent, and democratic by design. The group is supported by several grants including the prestigious *FIS2 - Starting Grant* (a.k.a. the Italian ERC) with a budget over 1.3M euros. {% hint style="success" %} Check out our [**GitHub organization**](https://github.com/collagelab) to learn more about our *open-source* research! {% endhint %} ### Key Articles * [The Future of Continual Learning in the Era of Foundation Models: Three Key Directions](https://arxiv.org/abs/2506.03320), Bell et al., Trustworthy and Collaborative Artificial Intelligence Workshop, HHAI 2025. * [A Compositional Paradigm for Foundation Models: Towards Smarter Robotic Agents](https://arxiv.org/abs/2510.18608), Quarantiello et al., I-RIM 3D 2025 Conference Workshop. ### Members * [Vincenzo Lomonaco](https://www.luiss.it/faculty/357557) (Principal Investigator) * [Daniele Malitesta](https://scholar.google.com/citations?user=Aeg9i_IAAAAJ\&hl=en) (Post-Doc) * [Jack Charles Bell](https://scholar.google.it/citations?hl=it\&user=MMukC9kAAAAJ) (PhD Student) * [Luigi Quarantiello](https://scholar.google.com/citations?user=TM5H03oAAAAJ\&hl=it) (PhD Student) * [Gerlando Gramaglia](https://scholar.google.com/citations?user=SrB4KocAAAAJ\&hl=it) (PhD Student) * [Giacomo Carfi](https://scholar.google.com/citations?hl=it\&user=ATn6PxgAAAAJ) (PhD Student) * [Irene Testa](https://scholar.google.com/citations?hl=it\&user=uDsnUzgAAAAJ) (PhD Student) * [Ehsan Tavan](https://scholar.google.com/citations?hl=it\&user=oY-ufO0AAAAJ) (PhD Student) * [Mauro Madeddu](https://scholar.google.com/citations?hl=it\&user=rBVtq8kAAAAJ) (PhD Student) * [Lanpei Li](https://scholar.google.com/citations?hl=it\&user=PnkoFQYAAAAJ) (PhD Student) * [Malio Li](https://scholar.google.com/citations?hl=it\&user=l1GF6dsAAAAJ) (PhD Student) * [Pierre Averty](https://www.linkedin.com/in/pierre-averty-996ab5195/?locale=en_US) (Research Assistant) ### Mentees * [Gennaro Francesco Landi](https://landigf.github.io/) (Master's student in Computer Science @ ETH Zurich) * [Federico Gerardi](https://www.federicogerardi.ovh/) (Master's student in Computer Science @ Sapienza University of Rome) * [Anthony Tricarico](mailto:undefined) (Master's student in Data Science @ University of Trento) * [Giovanni Zacchini](https://www.linkedin.com/in/giovannizecchini/) (Master's student in Statistics @ University of Bologna) * [Andres Claudio Lazzari](https://www.linkedin.com/in/andres-lazzari/?originalSubdomain=it) (Master's student in Computer Science @ University of Pisa) * [Giulio Rossi](https://www.linkedin.com/in/giulio-rossi-3699412b4) (Master's student in Computer Science @ University of Pisa) ### Previous Members * [Elia Piccoli](https://scholar.google.com/citations?user=-TKxJbro74UC\&hl=en) (PhD Student) * [Eric Nuertey Coleman](https://scholar.google.com/citations?hl=it\&user=326UIJYAAAAJ) (PhD Student) --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://www.vincenzolomonaco.com/collage-lab.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.