arXiv subjects

Samuel J. Cooper

Publications and source records attributed to Samuel J. Cooper.

17 recordsLinked to original sources

arXiv2026

Elicitation Matters: How Prompts and Query Protocols Shape LLM Surrogates under Sparse Observations

Large language models are increasingly used as surrogate models for low-data optimization, but their optimizer-facing prediction and its uncertainty remain poorly understood. We study the surrogate belief elicited from an LLM under sparse observations, showing that it depends strongly on prompt text and query protocol. We introduce an uncertainty-alignment criterion that measures whether model uncertainty tracks residual ambiguity among sample-consistent functions. Across controlled inference tasks and Bayesian optimization studies, we find that structural prompts act as effective priors, POINTWISE and JOINT querying induce different beliefs, and sequential evidence leads to non-monotonic, order-sensitive confidence updates. These effects change downstream acquisition decisions and regret, showing that elicitation protocol is part of the LLM surrogate specification, not a formatting detail.

cs.CL↗

arXiv2026

What DINO saw: ALiBi positional encoding reduces positional bias in Vision Transformers

Vision transformers (ViTs) - especially feature foundation models like DINOv2 - learn rich representations useful for many downstream tasks. However, architectural choices (such as positional encoding) can lead to these models displaying positional biases and artefacts independent of semantic content. This makes zero-shot adaption difficult in fields like material science, where images are often cross-sections of homogeneous microstructure (i.e. having no preferred direction). In this work, we investigate the positional bias in ViTs via linear probing, finding it present across a range of objectives and positional encodings, and subsequently reduce it by finetuning models to use ALiBi relative positional encoding. We demonstrate that these models retain desirable general semantics and their unbiased features can be used successfully in trainable segmentation of complex microscopy images.

cs.CV↗

arXiv2026

From Prompt to Protocol: Fast Charging Batteries with Large Language Models

Efficiently optimizing battery charging protocols is challenging because each evaluation is slow, costly, and non-differentiable. Many existing approaches address this difficulty by heavily constraining the protocol search space, which limits the diversity of protocols that can be explored, preventing the discovery of higher-performing solutions. We introduce two gradient-free, LLM-driven closed-loop methods: Prompt-to-Optimizer (P2O), which uses an LLM to propose the code for small neural-network-based protocols, which are then trained by an inner loop, and Prompt-to-Protocol (P2P), which simply writes an explicit function for the current and its scalar parameters. Across our case studies, LLM-guided P2O outperforms neural networks designed by Bayesian optimization, evolutionary algorithms, and random search. In a realistic fast charging scenario, both P2O and P2P yield around a 4.2 percent improvement in state of health (capacity retention based health metric under fast charging cycling) over a state-of-the-art multi-step constant current (CC) baseline, with P2P achieving this under matched evaluation budgets (same number of protocol evaluations). These results demonstrate that LLMs can expand the space of protocol functional forms, incorporate language-based constraints, and enable efficient optimization in high cost experimental settings.

cs.LG↗

arXiv2025

Maybe you don't need a U-Net: convolutional feature upsampling for materials micrograph segmentation

Feature foundation models - usually vision transformers - offer rich semantic descriptors of images, useful for downstream tasks such as (interactive) segmentation and object detection. For computational efficiency these descriptors are often patch-based, and so struggle to represent the fine features often present in micrographs; they also struggle with the large image sizes present in materials and biological image analysis. In this work, we train a convolutional neural network to upsample low-resolution (i.e, large patch size) foundation model features with reference to the input image. We apply this upsampler network (without any further training) to efficiently featurise and then segment a variety of microscopy images, including plant cells, a lithium-ion battery cathode and organic crystals. The richness of these upsampled features admits separation of hard to segment phases, like hairline cracks. We demonstrate that interactive segmentation with these deep features produces high-quality segmentations far faster and with far fewer labels than training or finetuning a more traditional convolutional network.

cs.CV↗

arXiv2025

evoxels: A differentiable physics framework for voxel-based microstructure simulations

Materials science inherently spans disciplines: experimentalists use advanced microscopy to uncover micro- and nanoscale structure, while theorists and computational scientists develop models that link processing, structure, and properties. Bridging these domains is essential for inverse material design where you start from desired performance and work backwards to optimal microstructures and manufacturing routes. Integrating high-resolution imaging with predictive simulations and data-driven optimization accelerates discovery and deepens understanding of process-structure-property relationships. The differentiable physics framework evoxels is based on a fully Pythonic, unified voxel-based approach that integrates segmented 3D microscopy data, physical simulations, inverse modeling, and machine learning.

cs.LG↗

arXiv2025

Layerwise Recall and the Geometry of Interwoven Knowledge in LLMs

This study explores how large language models (LLMs) encode interwoven scientific knowledge, using chemical elements and LLaMA-series models as a case study. We identify a 3D spiral structure in the hidden states that aligns with the conceptual structure of the periodic table, suggesting that LLMs can reflect the geometric organization of scientific concepts learned from text. Linear probing reveals that middle layers encode continuous, overlapping attributes that enable indirect recall, while deeper layers sharpen categorical distinctions and incorporate linguistic context. These findings suggest that LLMs represent symbolic knowledge not as isolated facts, but as structured geometric manifolds that intertwine semantic information across layers. We hope this work inspires further exploration of how LLMs represent and reason about scientific knowledge, particularly in domains such as materials science.

cs.CL↗

arXiv2024

Prediction of microstructural representativity from a single image

In this study, we present a method for predicting the representativity of the phase fraction observed in a single image (2D or 3D) of a material. Traditional approaches often require large datasets and extensive statistical analysis to estimate the Integral Range, a key factor in determining the variance of microstructural properties. Our method leverages the Two-Point Correlation function to directly estimate the variance from a single image, thereby enabling phase fraction prediction with associated confidence levels. We validate our approach using open-source datasets, demonstrating its efficacy across diverse microstructures. This technique significantly reduces the data requirements for representativity analysis, providing a practical tool for material scientists and engineers working with limited microstructural data. To make the method easily accessible, we have created a web-application, www.imagerep.io, for quick, simple and informative use of the method.

stat.CO↗

arXiv2024

Upsampling DINOv2 features for unsupervised vision tasks and weakly supervised materials segmentation

The features of self-supervised vision transformers (ViTs) contain strong semantic and positional information relevant to downstream tasks like object localization and segmentation. Recent works combine these features with traditional methods like clustering, graph partitioning or region correlations to achieve impressive baselines without finetuning or training additional networks. We leverage upsampled features from ViT networks (e.g DINOv2) in two workflows: in a clustering based approach for object localization and segmentation, and paired with standard classifiers in weakly supervised materials segmentation. Both show strong performance on benchmarks, especially in weakly supervised segmentation where the ViT features capture complex relationships inaccessible to classical approaches. We expect the flexibility and generalizability of these features will both speed up and strengthen materials characterization, from segmentation to property-prediction.

cs.CV↗

arXiv2024

Materials science in the era of large language models: a perspective

Large Language Models (LLMs) have garnered considerable interest due to their impressive natural language capabilities, which in conjunction with various emergent properties make them versatile tools in workflows ranging from complex code generation to heuristic finding for combinatorial problems. In this paper we offer a perspective on their applicability to materials science research, arguing their ability to handle ambiguous requirements across a range of tasks and disciplines mean they could be a powerful tool to aid researchers. We qualitatively examine basic LLM theory, connecting it to relevant properties and techniques in the literature before providing two case studies that demonstrate their use in task automation and knowledge extraction at-scale. At their current stage of development, we argue LLMs should be viewed less as oracles of novel insight, and more as tireless workers that can accelerate and unify exploration across domains. It is our hope that this paper can familiarise material science researchers with the concepts needed to leverage these tools in their own research.

cond-mat.mtrl-sci↗

arXiv2024

HRTF upsampling with a generative adversarial network using a gnomonic equiangular projection

An individualised head-related transfer function (HRTF) is very important for creating realistic virtual reality (VR) and augmented reality (AR) environments. However, acoustically measuring high-quality HRTFs requires expensive equipment and an acoustic lab setting. To overcome these limitations and to make this measurement more efficient HRTF upsampling has been exploited in the past where a high-resolution HRTF is created from a low-resolution one. This paper demonstrates how generative adversarial networks (GANs) can be applied to HRTF upsampling. We propose a novel approach that transforms the HRTF data for direct use with a convolutional super-resolution generative adversarial network (SRGAN). This new approach is benchmarked against three baselines: barycentric upsampling, spherical harmonic (SH) upsampling and an HRTF selection approach. Experimental results show that the proposed method outperforms all three baselines in terms of log-spectral distortion (LSD) and localisation performance using perceptual models when the input HRTF is sparse (less than 20 measured positions).

eess.AS↗

arXiv2023

SAMBA: A Trainable Segmentation Web-App with Smart Labelling

Segmentation is the assigning of a semantic class to every pixel in an image and is a prerequisite for various statistical analysis tasks in materials science, like phase quantification, physics simulations or morphological characterization. The wide range of length scales, imaging techniques and materials studied in materials science means any segmentation algorithm must generalise to unseen data and support abstract, user-defined semantic classes. Trainable segmentation is a popular interactive segmentation paradigm where a classifier is trained to map from image features to user drawn labels. SAMBA is a trainable segmentation tool that uses Meta's Segment Anything Model (SAM) for fast, high-quality label suggestions and a random forest classifier for robust, generalizable segmentations. It is accessible in the browser (https://www.sambasegment.com/) without the need to download any external dependencies. The segmentation backend is run in the cloud, so does not require the user to have powerful hardware.

cs.CV↗

arXiv2022

Two approaches to inpainting microstructure with deep convolutional generative adversarial networks

Imaging is critical to the characterisation of materials. However, even with careful sample preparation and microscope calibration, imaging techniques are often prone to defects and unwanted artefacts. This is particularly problematic for applications where the micrograph is to be used for simulation or feature analysis, as defects are likely to lead to inaccurate results. Microstructural inpainting is a method to alleviate this problem by replacing occluded regions with synthetic microstructure with matching boundaries. In this paper we introduce two methods that use generative adversarial networks to generate contiguous inpainted regions of arbitrary shape and size by learning the microstructural distribution from the unoccluded data. We find that one benefits from high speed and simplicity, whilst the other gives smoother boundaries at the inpainting border. We also outline the development of a graphical user interface that allows users to utilise these machine learning methods in a 'no-code' environment.

cs.CV↗

arXiv2022

Fusion of complementary 2D and 3D mesostructural datasets using generative adversarial networks

Modelling the impact of a material's mesostructure on device level performance typically requires access to 3D image data containing all the relevant information to define the geometry of the simulation domain. This image data must include sufficient contrast between phases to distinguish each material, be of high enough resolution to capture the key details, but also have a large enough field-of-view to be representative of the material in general. It is rarely possible to obtain data with all of these properties from a single imaging technique. In this paper, we present a method for combining information from pairs of distinct but complementary imaging techniques in order to accurately reconstruct the desired multi-phase, high resolution, representative, 3D images. Specifically, we use deep convolutional generative adversarial networks to implement super-resolution, style transfer and dimensionality expansion. To demonstrate the widespread applicability of this tool, two pairs of datasets are used to validate the quality of the volumes generated by fusing the information from paired imaging techniques. Three key mesostructural metrics are calculated in each case to show the accuracy of this method. Having confidence in the accuracy of our method, we then demonstrate its power by applying to a real data pair from a lithium ion battery electrode, where the required 3D high resolution image data is not available anywhere in the literature. We believe this approach is superior to previously reported statistical material reconstruction methods both in terms of its fidelity and ease of use. Furthermore, much of the data required to train this algorithm already exists in the literature, waiting to be combined. As such, our open-access code could precipitate a step change by generating the hard to obtain high quality image volumes necessary to simulate behaviour at the mesoscale.

cs.CV↗

arXiv2022

Metasurface Enhanced Spatial Mode Decomposition

Acquiring precise information about the mode content of a laser is critical for multiplexed optical communications, optical imaging with active wave-front control, and quantum-limited interferometric measurements. Hologram-based mode decomposition devices, such as spatial light modulators, allow a fast, direct measurement of the mode content, but they have limited precision due to cross-coupling between modes. Here we report the first proof-of-principle demonstration of mode decomposition with a metasurface, resulting in significantly enhanced precision. A mode-weight fluctuation of $6\times 10^{-7}$ was be measured with 1 second of averaging at a Fourier frequency of 80 Hz, an improvement of more than three orders of magnitude compared to the state-of-the-art spatial light modulator decomposition. The improvement is attributable to the reduction in cross-coupling enabled by the exceptional small pixel size of the metasurface. We show a systematic study of the limiting sources of noise, and we show that there is a promising path towards complete mode decomposition with similar precision.

physics.optics↗

arXiv2022

A Continuum of Physics-Based Lithium-Ion Battery Models Reviewed

Physics-based electrochemical battery models derived from porous electrode theory are a very powerful tool for understanding lithium-ion batteries, as well as for improving their design and management. Different model fidelity, and thus model complexity, is needed for different applications. For example, in battery design we can afford longer computational times and the use of powerful computers, while for real-time battery control (e.g. in electric vehicles) we need to perform very fast calculations using simple devices. For this reason, simplified models that retain most of the features at a lower computational cost are widely used. Even though in the literature we often find these simplified models posed independently, leading to inconsistencies between models, they can actually be derived from more complicated models using a unified and systematic framework. In this review, we showcase this reductive framework, starting from a high-fidelity microscale model and reducing it all the way down to the Single Particle Model (SPM), deriving in the process other common models, such as the Doyle-Fuller-Newman (DFN) model. We also provide a critical discussion on the advantages and shortcomings of each of the models, which can aid model selection for a particular application. Finally, we provide an overview of possible extensions to the models, with a special focus on thermal models. Any of these extensions could be incorporated into the microscale model and the reductive framework re-applied to lead to a new generation of simplified, multi-physics models.

physics.chem-ph↗

arXiv2021

Generating 3D structures from a 2D slice with GAN-based dimensionality expansion

Generative adversarial networks (GANs) can be trained to generate 3D image data, which is useful for design optimisation. However, this conventionally requires 3D training data, which is challenging to obtain. 2D imaging techniques tend to be faster, higher resolution, better at phase identification and more widely available. Here, we introduce a generative adversarial network architecture, SliceGAN, which is able to synthesise high fidelity 3D datasets using a single representative 2D image. This is especially relevant for the task of material microstructure generation, as a cross-sectional micrograph can contain sufficient information to statistically reconstruct 3D samples. Our architecture implements the concept of uniform information density, which both ensures that generated volumes are equally high quality at all points in space, and that arbitrarily large volumes can be generated. SliceGAN has been successfully trained on a diverse set of materials, demonstrating the widespread applicability of this tool. The quality of generated micrographs is shown through a statistical comparison of synthetic and real datasets of a battery electrode in terms of key microstructural metrics. Finally, we find that the generation time for a $10^8$ voxel volume is on the order of a few seconds, yielding a path for future studies into high-throughput microstructural optimisation.

cs.CV↗

arXiv2020

Pores for thought: The use of generative adversarial networks for the stochastic reconstruction of 3D multi-phase electrode microstructures with periodic boundaries

The generation of multiphase porous electrode microstructures is a critical step in the optimisation of electrochemical energy storage devices. This work implements a deep convolutional generative adversarial network (DC-GAN) for generating realistic n-phase microstructural data. The same network architecture is successfully applied to two very different three-phase microstructures: A lithium-ion battery cathode and a solid oxide fuel cell anode. A comparison between the real and synthetic data is performed in terms of the morphological properties (volume fraction, specific surface area, triple-phase boundary) and transport properties (relative diffusivity), as well as the two-point correlation function. The results show excellent agreement between for datasets and they are also visually indistinguishable. By modifying the input to the generator, we show that it is possible to generate microstructure with periodic boundaries in all three directions. This has the potential to significantly reduce the simulated volume required to be considered representative and therefore massively reduce the computational cost of the electrochemical simulations necessary to predict the performance of a particular microstructure during optimisation.

cs.NE↗