Task Agnostic Architecture for Algorithm Induction via Implicit Composition

arXiv:2404.02450v1 Announce Type: new
Abstract: Different fields in applied machine learning such as computer vision, speech or natural language processing have been building domain-specialised solutions. Currently, we are witnessing an opposing trend towards developing more generalist architectures, driven by Large Language Models and multi-modal foundational models. These architectures are designed to tackle a variety of tasks, including those previously unseen and using inputs across multiple modalities. Taking this trend of generalization to the extreme suggests the possibility of a single …

abstract algorithm applied machine learning architecture architectures arxiv building computer computer vision cs.ai cs.lg domain fields foundational foundational models language language models language processing large language large language models machine machine learning modal multi-modal natural natural language natural language processing processing solutions speech trend type via vision