9 papers
On the Limits of Prompt-Conditioned Language Models as General-Purpose Learners
David Mguni, Julian Ma, Jun Wang
Large Language Models (LLMs) are frequently portrayed as general-purpose solvers capable of solving arbitrary tasks. We argue that this view overlooks a fundamental constraint: lan…
Efficient and Principled Scientific Discovery through Bayesian Optimization: A Tutorial
Zhongwei Yu, Rasul Tutunov, Alexandre Max Maraval +13
Traditional scientific discovery relies on an iterative hypothesise-experiment-refine cycle that has driven progress for centuries, but its intuitive, ad-hoc implementation often w…
Bottlenecked Transformers: Periodic KV Cache Consolidation for Generalised Reasoning
Adnan Oomerjee, Zafeirios Fountas, Haitham Bou-Ammar +1
Transformer LLMs have been shown to exhibit strong reasoning ability that scales with inference-time compute, most prominently through token-space "thinking" chains of thought. A g…
Why the Brain Consolidates: Predictive Forgetting for Optimal Generalisation
Zafeirios Fountas, Adnan Oomerjee, Haitham Bou-Ammar +2
Standard accounts of memory consolidation emphasise the stabilisation of stored representations, but struggle to explain representational drift, semanticisation, or the necessity o…
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…
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…