Related papers: Closing the Loop: How Semantic Closure Enables Ope…
Large language models (LLMs) make it plausible to build systems that improve through self-evolving loops, but many existing proposals are better understood as self-play and often plateau quickly. A central failure mode is that the loop…
For over a century, immunology has masterfully discovered and dissected the components of our immune system, yet its collective behavior remains fundamentally unpredictable. In this perspective, we argue that building on the learnings of…
Central to the artificial life endeavour is the creation of artificial systems spontaneously generating properties found in the living world such as autopoiesis, self-replication, evolution and open-endedness. While numerous models and…
An outstanding challenge for the widespread deployment of robotic systems like autonomous vehicles is ensuring safe interaction with humans without sacrificing performance. Existing safety methods often neglect the robot's ability to learn…
Propelling, and propelled by, the "deep learning revolution", recent years have seen the introduction of ever larger corpora of images annotated with natural language expressions. We survey some of these corpora, taking a perspective that…
The identification of semantic relations between terms within texts is a fundamental task in Natural Language Processing which can support applications requiring a lightweight semantic interpretation model. Currently, semantic relation…
Situationally-aware artificial agents operating with competence in natural environments face several challenges: spatial awareness, object affordance detection, dynamic changes and unpredictability. A critical challenge is the agent's…
The paper surveys automated scientific discovery, from equation discovery and symbolic regression to autonomous discovery systems and agents. It discusses the individual approaches from a "big picture" perspective and in context, but also…
Humans and animals exhibit a range of interesting behaviors in dynamic environments, and it is unclear how our brains actively reformat this dense sensory information to enable these behaviors. Experimental neuroscience is undergoing a…
Psychological and social systems provide us with a natural domain for the study of anticipations because these systems are based on and operate in terms of intentionality. Psychological systems can be expected to contain a model of…
The neural architectures of language models are becoming increasingly complex, especially that of Transformers, based on the attention mechanism. Although their application to numerous natural language processing tasks has proven to be very…
A conceptual system with rich connotation is key to improving the performance of knowledge-based artificial intelligence systems. While a conceptual system, which has abundant concepts and rich semantic relationships, and is developable,…
Human language is recognized as a very complex domain since decades. No computer system has been able to reach human levels of performance so far. The only known computational system capable of proper language processing is the human brain.…
Scaling robot learning to long-horizon tasks remains a formidable challenge. While end-to-end policies often lack the structural priors needed for effective long-term reasoning, traditional neuro-symbolic methods rely heavily on…
Psychological investigations have led to considerable insight into the working of the human language comprehension system. In this article, we look at a set of principles derived from psychological findings to argue for a particular…
Automatically generating a natural language description of an image has attracted interests recently both because of its importance in practical applications and because it connects two major artificial intelligence fields: computer vision…
This PhD thesis is essentially the story of a scientific idea, from what it has blossomed, how it has grown, what it might become. My ambition in writing has been to produce an original, coherent and compact narrative. It begins (1) with a…
We introduce Entropy2Vec, a novel framework for deriving cross-lingual language representations by leveraging the entropy of monolingual language models. Unlike traditional typological inventories that suffer from feature sparsity and…
Life is commonly described as a self-organized, far-from-equilibrium process that maintains internal order by consuming free energy and exporting entropy. This thermodynamic view underlies diverse theoretical frameworks -- from autopoiesis…
We review enzymatic systems which involve biocatalytic reactions utilized for information processing (biocomputing). Extensive ongoing research in biocomputing, mimicking Boolean logic gates has been motivated by potential applications in…