Searcharxiv⌕ Search

arXiv subjects

Nathan Brown

Publications and source records attributed to Nathan Brown.

8 recordsLinked to original sources
arXiv2026

Creating a biologically more accurate spider robot to study active vibration sensing

Orb-weaving spiders detect prey on a web using vibration sensors at leg joints. They often dynamically crouch their legs during prey sensing, likely an active sensing strategy. However, how leg crouching enhances sensing is poorly understood, because measuring system vibrations in behaving animals is difficult. We use robophysical modeling to study this problem. Our previous spider robot had only four legs, simplified leg morphology, and a shallow crouching range of motion. Here, we developed a new spider robot, with eight legs, each with four joints that better approximated spider leg morphology. Leg exoskeletons were 3-D printed and joint stiffness was tuned using integrated silicone molding with variable materials and geometry. Tendon-driven actuation allowed a motor in the body to crouch all eight legs deeply as spiders do, while accelerometers at leg joints record leg vibrations. Experiments showed that our new spider robot reproduced key vibration features observed in the previous robot while improving biological accuracy. Our new robot provides a biologically more accurate robophysical model for studying how leg behaviors modulate vibration sensing on a web.

cs.RO↗
arXiv2026

PDPL Metric: Validating a Scale to Measure Personal Data Privacy Literacy Among University Students

Personal data privacy literacy (PDPL) refers to a collection of digital literacy skills related to an individuals ability to understand, evaluate, and manage the collection, use, and protection of personal data in online and digital environments. This study introduces and validates a new psychometric scale (PDPL Metric) designed to measure data privacy literacy among university students, focusing on six key privacy constructs: perceived risk of data misuse, expectations of informed consent, general privacy concern, privacy management awareness, privacy-utility trade-off acceptance, and perceived importance of data security. A 24-item questionnaire was developed and administered to students at U.S.-based research universities. Principal components analysis confirmed the unidimensionality and internal consistency of each construct, and a second-order analysis supported the integration of all six into a unified PDPL construct. No differences in PDPL were found based on basic demographic variables like academic level and gender, although a difference was found based on domestic/international status. The findings of this study offer a validated framework for assessing personal data privacy literacy within the higher education context and support the integration of the core constructs into higher education programs, organizational policies, and digital literacy initiatives on university campuses.

cs.CY↗
arXiv2025

A Survey of AI Methods for Geometry Preparation and Mesh Generation in Engineering Simulation

Artificial intelligence is beginning to reduce the manual effort in the CAD-to-mesh pipeline. Written for meshing and geometry practitioners with limited AI background, this survey organizes recent work by workflow step. We cover part classification and segmentation, mesh quality prediction, and defeaturing. We review AI guidance for unstructured meshing, block-structured meshing in 2D and 3D, and volumetric parameterization, including reconstruction from implicit or sampled geometry. We also discuss parallel mesh generation and scripting automation via reinforcement learning and large language models. Across these topics, AI complements established geometry and meshing algorithms rather than replacing them. We conclude with practical lessons and open challenges in data, benchmarks, and trustworthy integration.

cs.CE↗
arXiv2024

Pula: Training Large Language Models for Setswana

In this work we present Pula, a suite of bilingual language models proficient in both Setswana and English. Leveraging recent advancements in data availability and efficient fine-tuning, Pula 8B and Pula 14B outperform GPT-4o and Gemini 1.5 Pro on English-Setswana translation tasks and achieve state-of-the-art performance on Setswana reasoning tasks for their size. We release the weights for Pula 1B, 3B, 8B, and 14B as well as training logs and training and evaluation code. Alongside Pula, we release the largest-ever Setswana text corpus, Marothodi, and the first comprehensive Setswana instruction-tuning dataset, Medupi, consisting of reformatted datasets, translated corpora, and synthetic LLM-generated text. To accompany this data, we release the code used for dataset construction, formatting, filtering, and scraping. Last, we release two Setswana LLM-translated benchmarks, MMLU-tsn and GSM8K-tsn, to measure Setswana knowledge and reasoning capabilities.

cs.CL↗
arXiv2023

Efficient Transformer Knowledge Distillation: A Performance Review

As pretrained transformer language models continue to achieve state-of-the-art performance, the Natural Language Processing community has pushed for advances in model compression and efficient attention mechanisms to address high computational requirements and limited input sequence length. Despite these separate efforts, no investigation has been done into the intersection of these two fields. In this work, we provide an evaluation of model compression via knowledge distillation on efficient attention transformers. We provide cost-performance trade-offs for the compression of state-of-the-art efficient attention architectures and the gains made in performance in comparison to their full attention counterparts. Furthermore, we introduce a new long-context Named Entity Recognition dataset, GONERD, to train and test the performance of NER models on long sequences. We find that distilled efficient attention transformers can preserve a significant amount of original model performance, preserving up to 98.6% across short-context tasks (GLUE, SQUAD, CoNLL-2003), up to 94.6% across long-context Question-and-Answering tasks (HotpotQA, TriviaQA), and up to 98.8% on long-context Named Entity Recognition (GONERD), while decreasing inference times by up to 57.8%. We find that, for most models on most tasks, performing knowledge distillation is an effective method to yield high-performing efficient attention models with low costs.

cs.CL↗
arXiv2018

GuacaMol: Benchmarking Models for De Novo Molecular Design

De novo design seeks to generate molecules with required property profiles by virtual design-make-test cycles. With the emergence of deep learning and neural generative models in many application areas, models for molecular design based on neural networks appeared recently and show promising results. However, the new models have not been profiled on consistent tasks, and comparative studies to well-established algorithms have only seldom been performed. To standardize the assessment of both classical and neural models for de novo molecular design, we propose an evaluation framework, GuacaMol, based on a suite of standardized benchmarks. The benchmark tasks encompass measuring the fidelity of the models to reproduce the property distribution of the training sets, the ability to generate novel molecules, the exploration and exploitation of chemical space, and a variety of single and multi-objective optimization tasks. The benchmarking open-source Python code, and a leaderboard can be found on https://benevolent.ai/guacamol

q-bio.QM↗
arXiv2014

Stochastic identification of malware with dynamic traces

A novel approach to malware classification is introduced based on analysis of instruction traces that are collected dynamically from the program in question. The method has been implemented online in a sandbox environment (i.e., a security mechanism for separating running programs) at Los Alamos National Laboratory, and is intended for eventual host-based use, provided the issue of sampling the instructions executed by a given process without disruption to the user can be satisfactorily addressed. The procedure represents an instruction trace with a Markov chain structure in which the transition matrix, $\mathbf {P}$, has rows modeled as Dirichlet vectors. The malware class (malicious or benign) is modeled using a flexible spline logistic regression model with variable selection on the elements of $\mathbf {P}$, which are observed with error. The utility of the method is illustrated on a sample of traces from malware and nonmalware programs, and the results are compared to other leading detection schemes (both signature and classification based). This article also has supplementary materials available online.

stat.AP↗