collaborators

5 papers

cs.AI2026

A Brain-like Synergistic Core in LLMs Drives Behaviour and Learning

Pedro Urbina-Rodriguez, Zafeirios Fountas, Fernando E. Rosas +5

The independent evolution of intelligence in biological and artificial systems offers a unique opportunity to identify its fundamental computational principles. Here we show that l…

cs.CL2025

Emergent Bayesian Behaviour and Optimal Cue Combination in LLMs

Julian Ma, Jun Wang, Zafeirios Fountas

Large language models (LLMs) excel at explicit reasoning, but their implicit computational strategies remain underexplored. Decades of psychophysics research show that humans intui…

cs.LG2025

SuRe: Surprise-Driven Prioritised Replay for Continual LLM Learning

Hugo Hazard, Zafeirios Fountas, Martin A. Benfeghoul +3

Continual learning, one's ability to adapt to a sequence of tasks without forgetting previously acquired knowledge, remains a major challenge in machine learning and a key gap betw…

cs.LG2025

Subjective Depth and Timescale Transformers: Learning Where and When to Compute

Frederico Wieser, Martin Benfeghoul, Haitham Bou Ammar +2

The rigid, uniform allocation of computation in standard Transformer (TF) architectures can limit their efficiency and scalability, particularly for large-scale models and long seq…

cs.LG2025

Untangling Component Imbalance in Hybrid Linear Attention Conversion Methods

Martin Benfeghoul, Teresa Delgado, Adnan Oomerjee +3

Transformers' quadratic computational complexity limits their scalability despite remarkable performance. While linear attention reduces this to linear complexity, pre-training suc…