Related papers: A Preliminary Exploration of Floating Point Gramma…
Catastrophic forgetting impairs the continuous learning of large language models. We propose Fisher-Guided Gradient Masking (FGGM), a framework that mitigates this by strategically selecting parameters for updates using diagonal Fisher…
The mapping between biological genotypes and phenotypes is central to the study of biological evolution. Here we introduce a rich, intuitive, and biologically realistic genotype-phenotype (GP) map, that serves as a model of self-assembling…
Darwinian evolution is driven by random mutations, genetic recombination (gene shuffling) and selection that favors genotypes with high fitness. For systems where each genotype can be represented as a bitstring of length $L$, an overview of…
Genetic Programming (GP) is known to suffer from the burden of being computationally expensive by design. While, over the years, many techniques have been developed to mitigate this issue, data vectorization, in particular, is arguably…
We propose a training-free approach to improve sentence embeddings leveraging test-time compute by applying generative text models for data augmentation at inference time. Unlike conventional data augmentation that utilises synthetic…
We consider evolution of a large population, where fitness of each organism is defined by many phenotypical traits. These traits result from expression of many genes. We propose a new model of gene regulation, where gene expression is…
The rapid advancement of large language models (LLMs) has transformed the landscape of agentic information seeking capabilities through the integration of tools such as search engines and web browsers. However, current mainstream approaches…
Recent advances in the masked autoencoder (MAE) paradigm have significantly propelled self-supervised skeleton-based action recognition. However, most existing approaches limit reconstruction targets to raw joint coordinates or their simple…
Feature selection reduces the dimensionality of data by identifying a subset of the most informative features. In this paper, we propose an innovative framework for unsupervised feature selection, called fractal autoencoders (FAE). It…
Generative Adversarial Network (GAN) is a current focal point of research. The body of knowledge is fragmented, leading to a trial-error method while selecting an appropriate GAN for a given scenario. We provide a comprehensive summary of…
An important problem in bioinformatics is the inference of gene regulatory networks (GRN) from temporal expression profiles. In general, the main limitations faced by GRN inference methods is the small number of samples with huge…
Generative modeling aims to generate new data samples that resemble a given dataset, with diffusion models recently becoming the most popular generative model. One of the main challenges of diffusion models is solving the problem in the…
Many existing learning-based grasping approaches concentrate on a single embodiment, provide limited generalization to higher DoF end-effectors and cannot capture a diverse set of grasp modes. We tackle the problem of grasping using…
Parameter-Efficient Fine-Tuning (PEFT) has emerged as a key strategy for adapting large-scale pre-trained models to downstream tasks, but existing approaches face notable limitations. Addition-based methods, such as Adapters, introduce…
Generative Pre-trained Transformer (GPT) architectures are the most popular design for language modeling. Energy-based modeling is a different paradigm that views inference as a dynamical process operating on an energy landscape. We propose…
Automated polyp segmentation is essential for early diagnosis of colorectal cancer, yet developing robust models remains challenging due to limited annotated data and significant performance degradation under domain shift. Although…
We introduce a dataset for studying the evolution of words, constructed from WordNet and the Google Books Ngram Corpus. The dataset tracks the evolution of 4,000 synonym sets (synsets), containing 9,000 English words, from 1800 AD to 2000…
We propose a novel surrogate-assisted Evolutionary Algorithm for solving expensive combinatorial optimization problems. We integrate a surrogate model, which is used for fitness value estimation, into a state-of-the-art P3-like variant of…
State-of-the-art methods for data-driven modelling of non-linear dynamical systems typically involve interactions with an expert user. In order to partially automate the process of modelling physical systems from data, many EA-based…
A phylogeny describes the evolutionary history of an evolving population. Evolutionary search algorithms can perfectly track the ancestry of candidate solutions, illuminating a population's trajectory through the search space. However,…