Related papers: Evolution and trade-off dynamics of functional loa…
We review the task of aligning simple models for language dynamics with relevant empirical data, motivated by the fact that this is rarely attempted in practice despite an abundance of abstract models. We propose that one way to meet this…
Phylogenetic species trees typically represent the speciation history as a bifurcating tree. Speciation events that simultaneously create more than two descendants, thereby creating polytomies in the phylogeny, are possible. Moreover, the…
Federated Learning (FL) has emerged as a fundamental learning paradigm to harness massive data scattered at geo-distributed edge devices in a privacy-preserving way. Given the heterogeneous deployment of edge devices, however, their data…
In recent years, we have witnessed a dramatic shift towards techniques driven by neural networks for a variety of NLP tasks. Undoubtedly, neural language models (NLMs) have reduced perplexity by impressive amounts. This progress, however,…
We use a combination of analytic models and computer simulations to gain insight into the dynamics of evolution. Our results suggest that certain interesting phenomena should eventually emerge from the fossil record. For example, there…
Reinforcement Learning (RL) for Large Language Models (LLMs) faces a fundamental tension: the numerical divergence between high-throughput inference engines and numerically precise training engines. Although these systems share the same…
We derive an expression for the variation between parallel trajectories in phenotypic evolution, extending the well known result that predicts the mean evolutionary path in adaptive dynamics or quantitative genetics. We show how this…
Language change is a cultural evolutionary process in which variants of linguistic variables change in frequency through processes analogous to mutation, selection and genetic drift. In this work, we apply a recently-introduced method to…
Phylogenetics is a branch of computational biology that studies the evolutionary relationships among biological entities. Its long history and numerous applications notwithstanding, inference of phylogenetic trees from sequence data remains…
The Colless index is one of the most popular and natural balance indices for bifurcating phylogenetic trees, but it makes no sense for multifurcating trees. In this paper we propose a family of Colless-like balance indices…
Africa has the highest linguistic diversity in the world. On account of the importance of language to communication, and the importance of reliable, powerful and accurate machine translation models in modern inter-cultural communication,…
Multi-task trade-offs in machine learning can be addressed via Pareto Front Learning (PFL) methods that parameterize the Pareto Front (PF) with a single model. PFL permits to select the desired operational point during inference, contrary…
Dynamic evaluation of language models (LMs) adapts model parameters at test time using gradient information from previous tokens and substantially improves LM performance. However, it requires over 3x more compute than standard inference.…
We present a systematic empirical study of small language models under strict compute constraints, analyzing how architectural choices and training budget interact to determine performance. Starting from a linear next-token predictor, we…
The evidence that Flowering Locus T (FT) protein and its paralog Twin Sister of FT, act as the long distance floral stimulus, or at least that they are part of it in diverse plant species, has attracted much attention in recent years.…
We present and evaluate a new model for Natural Language Generation (NLG) in Spoken Dialogue Systems, based on statistical planning, given noisy feedback from the current generation context (e.g. a user and a surface realiser). We study its…
In many species, genomic data have revealed pervasive adaptive evolution indicated by the fixation of beneficial alleles. However, when selection pressures are highly variable along a species range or through time adaptive alleles may…
Federated Learning (FL) applied to real world data may suffer from several idiosyncrasies. One such idiosyncrasy is the data distribution across devices. Data across devices could be distributed such that there are some "heavy devices" with…
Federated Learning (FL) is a distributed learning approach that trains machine learning models across multiple devices while keeping their local data private. However, FL often faces challenges due to data heterogeneity, leading to…
Phylogenetic trees elucidate evolutionary relationships among species, but phylogenetic inference remains challenging due to the complexity of combining continuous (branch lengths) and discrete parameters (tree topology). Traditional Markov…