Welcome to the Multicom Research Group (Multicom Lab) at the University of Waterloo.
We believe that information theory—properly extended to handle semantics and nonlinearity — provides a powerful mathematical language for understanding, rigorously analyzing, and systematically improving modern AI systems.
Our lab investigates the deep connections between information theory, artificial intelligence, and multimedia communications. We are interested in how modern learning systems process and represent information, build predictive models, and uncover semantic structure in complex data — and in how these questions, in turn, open new frontiers for information theory itself.
Our research integrates fundamental theory, algorithm design, and practical system development to advance intelligent information technologies. Through this work, we aim to deepen the scientific foundations of modern AI and, simultaneously, to extend the reach of classical information theory into the era of learning and semantics.
Research in the Multicom Lab is guided by the SPIN framework:
Semantics – Prediction – Information – Nonlinearity
This framework views modern AI systems as nonlinear information-processing systems that learn predictive models and semantic representations from complex data. Importantly, the four elements form a coherent arc: nonlinear systems process information to produce predictive models, and those predictive models, when trained at sufficient scale, give rise to semantic representations. The SPIN framework unifies these four dimensions into a single research agenda.
The framework also highlights a central and largely open scientific challenge. While linear systems have been extensively studied and are supported by rich mathematical theory, nonlinear systems remain far less understood despite their ubiquity. The remarkable empirical success of deep learning suggests that AI may provide powerful new tools for addressing this longstanding challenge in science and engineering.
Within the SPIN framework:
-
Semantics emerges from contextual representations learned from large-scale data.
-
Prediction lies at the core of modern machine learning and large AI models.
-
Information provides the mathematical foundations for representation, learning, and communication.
-
Nonlinearity captures the complexity and richness of real-world systems.
Together, these four principles provide a unifying perspective for intelligent information systems, connecting information theory, machine learning, and data science. They also define the research agenda of the Multicom Lab: to develop the mathematical theory and practical algorithms that this unified perspective demands.
The SPIN Framework:
S |
Semantics emerges from contextual representations learned at scale |
P |
Prediction lies at the core of modern machine learning and large AI models |
I |
Information provides the mathematical foundations for representation and learning |
N |
Nonlinearity captures the complexity and richness of real-world systems |