Hi! I’m Yuriel and I’m currently a Research Assistant at NUS Glow.AI Lab. I like to use information theory for (multimodal) machine learning. My publications usually go by “Yuriel Ryan”.

Research Interests

Broadly speaking, I am interested in understanding how task-relevant information flows within complex systems — from deep neural networks to multi-agent environments — to utilize them for learning. This means building on theoretical frameworks, such as information theory (PID), to both quantify and optimize for these task-relevant signals. More details in Research.

What am I currently thinking about?

I am excited to work on other directions where information can flow dynamically. For instance, thinking about augmented LMs (e.g., RAG / tool calling), world modelling, or meta systems through the different lenses of information theory (e.g., V / accessible information). Of particular interest, I’m exploring ideas of collective intelligence and self/co-evolving systems, where agents improve themselves by interacting with the world and sharing what they have learned to other agents. In this manner, information not only flows forward (for inference) / backward (for learning), but also laterally to other agents!

A couple of works that inspired me: CORAL (multi-agent self-evolution), Colony (a film — the zombies exhibit collective intelligence!), R-Zero (Self-evolving agent)

While this relatively new direction of AI research is exciting, I’m also mindful of the social and practical implications of these “evolving agents/systems”. My intended goal is to build these adaptive systems to collaborate with humans — and definitely not to deprecate us! (see this position paper) Ultimately, I hope to actualize the Human(s)-AI(s) symbiosis ideal (note that both human and AI can be plural) through this collective intelligence approach where both sides continuously improve each other.

Updates!