26 citations · 51 across the 23 of their papers we have counts for
24 papers
Can Large Language Model Agents Learn by Watching Tutorial Videos?
Haoyu Zhao, Zafeirios Fountas, Jun Wang
Humans continuously acquire knowledge from carefully crafted materials such as books and tutorial videos, carrying that understanding into future tasks. Millions of such instructio…
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…
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…
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…
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…
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…
Interactive Inference: A Neuromorphic Theory of Human-Computer Interaction
Roel Vertegaal, Timothy Merritt, Saul Greenberg +3
Neuromorphic Human-Computer Interaction (HCI) is a theoretical approach to designing better user experiences (UX) motivated by advances in the understanding of the neurophysiology…
Human-inspired Episodic Memory for Infinite Context LLMs
Zafeirios Fountas, Martin A Benfeghoul, Adnan Oomerjee +4
Large language models (LLMs) have shown remarkable capabilities, but still struggle with processing extensive contexts, limiting their ability to maintain coherence and accuracy ov…
When in Doubt, Think Slow: Iterative Reasoning with Latent Imagination
Martin Benfeghoul, Umais Zahid, Qinghai Guo +1
In an unfamiliar setting, a model-based reinforcement learning agent can be limited by the accuracy of its world model. In this work, we present a novel, training-free approach to…
Sample as You Infer: Predictive Coding With Langevin Dynamics
Umais Zahid, Qinghai Guo, Zafeirios Fountas
We present a novel algorithm for parameter learning in generic deep generative models that builds upon the predictive coding (PC) framework of computational neuroscience. Our appro…
Predictive Coding as a Neuromorphic Alternative to Backpropagation: A Critical Evaluation
Umais Zahid, Qinghai Guo, Zafeirios Fountas
Backpropagation has rapidly become the workhorse credit assignment algorithm for modern deep learning methods. Recently, modified forms of predictive coding (PC), an algorithm with…
Curvature-Sensitive Predictive Coding with Approximate Laplace Monte Carlo
Umais Zahid, Qinghai Guo, Karl Friston +1
Predictive coding (PC) accounts of perception now form one of the dominant computational theories of the brain, where they prescribe a general algorithm for inference and learning…
Long-horizon video prediction using a dynamic latent hierarchy
Alexey Zakharov, Qinghai Guo, Zafeirios Fountas
The task of video prediction and generation is known to be notoriously difficult, with the research in this area largely limited to short-term predictions. Though plagued with nois…
Modelling non-reinforced preferences using selective attention
Noor Sajid, Panagiotis Tigas, Zafeirios Fountas +3
How can artificial agents learn non-reinforced preferences to continuously adapt their behaviour to a changing environment? We decompose this question into two challenges: () en…
Bayesian sense of time in biological and artificial brains
Zafeirios Fountas, Alexey Zakharov
Enquiries concerning the underlying mechanisms and the emergent properties of a biological brain have a long history of theoretical postulates and experimental findings. Today, the…
Variational Predictive Routing with Nested Subjective Timescales
Alexey Zakharov, Qinghai Guo, Zafeirios Fountas
Discovery and learning of an underlying spatiotemporal hierarchy in sequential data is an important topic for machine learning. Despite this, little work has been done to explore h…
Exploration and preference satisfaction trade-off in reward-free learning
Noor Sajid, Panagiotis Tigas, Alexey Zakharov +2
Biological agents have meaningful interactions with their environment despite the absence of immediate reward signals. In such instances, the agent can learn preferred modes of beh…
Episodic Memory for Learning Subjective-Timescale Models
Alexey Zakharov, Matthew Crosby, Zafeirios Fountas
In model-based learning, an agent's model is commonly defined over transitions between consecutive states of an environment even though planning often requires reasoning over multi…
Deep active inference agents using Monte-Carlo methods
Zafeirios Fountas, Noor Sajid, Pedro A. M. Mediano +1
Active inference is a Bayesian framework for understanding biological intelligence. The underlying theory brings together perception and action under one single imperative: minimiz…
Building Proactive Voice Assistants: When and How (not) to Interact
O. Miksik, I. Munasinghe, J. Asensio-Cubero +17
Voice assistants have recently achieved remarkable commercial success. However, the current generation of these devices is typically capable of only reactive interactions. In other…
Evolution of a Complex Predator-Prey Ecosystem on Large-scale Multi-Agent Deep Reinforcement Learning
Jun Yamada, John Shawe-Taylor, Zafeirios Fountas
Simulation of population dynamics is a central research theme in computational biology, which contributes to understanding the interactions between predators and preys. Conventiona…
Multimodal Data Fusion based on the Global Workspace Theory
Cong Bao, Zafeirios Fountas, Temitayo Olugbade +1
We propose a novel neural network architecture, named the Global Workspace Network (GWN), which addresses the challenge of dynamic and unspecified uncertainties in multimodal data…