arXiv subjects

Andrew Brown

Publications and source records attributed to Andrew Brown.

At least 19 recordsLinked to original sources

arXiv2026

Compact quasiaxisymmetric stellarators, a near axisymmetric theory

We develop a theory of ridges in compact stellarators with quasiaxisymmetry (QA). The equilibrium with finite plasma currents and pressure is modeled by ideal magnetohydrostatics (MHS). Field lines are collimated near sharp ridges, much like X-points, making ridges attractive to divertor designs without the requirement of a rational rotational transform at the divertor. However, unlike X-points, which must cover the entire torus an integer number of times, sharp ridges are typically localized in certain parts of the flux surfaces. Motivated by recent work (Henneberg and Plunk, Phys. Rev. Research 6, L022052) on compact hybrid devices, we develop a perturbative treatment of nearly axisymmetric quasisymmetric devices by expanding in the deviation from perfect axisymmetry. As a result, we can analytically describe the key features of compact QA devices, such as the tendency for ridges to be localized on the inboard side, where the Gaussian curvature is typically negative, and the field strength is maximum. We provide comprehensive numerical evidence in support of our analytical theory.

physics.plasm-ph↗

arXiv2026

Optical analogy for stellarators: Ridges as caustics and coils as singularities

A common feature of most numerically optimized stellarator geometries is the presence of sharp ridges on outer flux surfaces, irrespective of the rotational transform. Despite their importance, an analytical theory for their existence has been lacking. In this work, we demonstrate that ridges are not artifacts but mathematical necessities. We develop such a theory for devices with quasisymmetry (QS). We demonstrate that QS exhibits close connections with the theory of geometrical optics, following Parker's ``optical analogy" (E.N. Parker, Geophys. Astrophys. Fluid Dyn, 1989). By mapping vacuum QS to the eikonal equation of geometrical optics, we derive the conditions for ridge formation, identified as field line caustics where magnetic field lines focus. Furthermore, we prove a geometric theorem for stellarator coil design: both ridges and filamentary coils must lie on the zero-determinant manifold of the magnetic gradient tensor. This topological constraint unifies the description of plasma ridges and external coils, providing a precise criterion for identifying valid coil locations and explaining the efficacy of the magnetic gradient lengthscale (J. Kappel et al., Plasma Phys. Control. Fusion, 2024) as a coil optimization parameter. We demonstrate that as the device becomes more compact, sharp ridges naturally form on the inboard side in quasiaxisymmetry. We support our analytical theory with extensive numerical evidence.

physics.plasm-ph↗

arXiv2026

Statistical equilibrium model for stellarators

In three dimensional toroidal domains without symmetry, the standard magnetohydrodynamic (MHD) equilibrium model used for magnetic confinement fusion does not generally support smooth solutions. Instead, solutions have singular plasma currents on resonant magnetic surfaces that violate the MHD assumption of length-scale separation, further leading to the non- or slow convergence of numerical approximations under refinement. In this work, we present an improved equilibrium principle derived from a statistical model for plasma fluctuations. Instead of being static, we assume that the plasma magnetic field is ergodically and rapidly fluctuating relative to the MHD time scale. By averaging the resulting force, we derive a variational equilibrium problem for the statistical mean magnetic field which depends on fluctuation variance. Then, through asymptotics, numerical simulations, and a Grad-Shafranov type argument, we show that the variational principle supports smooth solutions for specific fluctuation statistics chosen to minimally modify the standard equilibrium modeling paradigm. Physically, this model smooths singular current sheets with a length scale determined by the magnetic field fluctuations.

physics.plasm-ph↗

arXiv2026

Forced Reconnection in Voigt-Regularized MHD

Forced reconnection in Voigt-regularized MHD is investigated in the Hahm-Kulsrud-Taylor problem. It is shown that Voigt regularization introduces an early linear phase of reconnection that partially bypasses the ideal current sheet formation phase. A Rutherford-like model of nonlinear island growth and saturation is introduced, including time-dependent spatial variation in the island current distribution and the braking effects of regularization and viscosity. It is conjectured, with numerical justification, that the inclusion of drag in the momentum equation results in precise MHS equilibria in the long-time limit.

physics.plasm-ph↗

arXiv2025

Climatological variability of a thunderstorm environment dataset in tropical and temperate regions

Spatiotemporal variations in thunderstorm occurrence frequency are considered here using an environmental dataset derived from ERA5 reanalysis data. Interannual variability in the thunderstorm environments is examined for the period 1979-2023, with the standard deviation and coefficient of variation showing considerable spatial differences through the world. Atmospheric and oceanic modes of climate variability account for some of this interannual variability, particularly for the El Nino-Southern Oscillation through tropical and maritime regions, as well as to a lesser degree for the Indian Ocean Dipole, Arctic Oscillation and Antarctic Oscillation. Long-term trends can also contribute to interannual variability, with results showing increases are more common than decreases in the thunderstorm environments through the study region over the period 1979-2023. However, considerable uncertainties in those trends are noted as is also suggested from some additional analysis of global climate models, indicating that although more favorable thunderstorm environments might occur in a warming world, the estimated change over the period 1979-2023 is relatively small compared to the standard deviation in most locations. The study findings are intended to be complementary to other studies and contribute as part of a broader range of information available on thunderstorms and climate variability.

physics.ao-ph↗

arXiv2025

A Systematic Literature Review of Retrieval-Augmented Generation: Techniques, Metrics, and Challenges

This systematic review of the research literature on retrieval-augmented generation (RAG) provides a focused analysis of the most highly cited studies published between 2020 and May 2025. A total of 128 articles met our inclusion criteria. The records were retrieved from ACM Digital Library, IEEE Xplore, Scopus, ScienceDirect, and the Digital Bibliography and Library Project (DBLP). RAG couples a neural retriever with a generative language model, grounding output in up-to-date, non-parametric memory while retaining the semantic generalisation stored in model weights. Guided by the PRISMA 2020 framework, we (i) specify explicit inclusion and exclusion criteria based on citation count and research questions, (ii) catalogue datasets, architectures, and evaluation practices, and (iii) synthesise empirical evidence on the effectiveness and limitations of RAG. To mitigate citation-lag bias, we applied a lower citation-count threshold to papers published in 2025 so that emerging breakthroughs with naturally fewer citations were still captured. This review clarifies the current research landscape, highlights methodological gaps, and charts priority directions for future research.

cs.DL↗

arXiv2025

A class of high-beta, large-aspect-ratio quasiaxisymmetric Palumbo-like configurations

The space of high-beta, approximately quasiaxisymmetric, large-aspect-ratio stellarator configurations is explored using an inverse coordinate approach and a quadratic polynomial ansatz for the flux function, following the method of Palumbo, extended by Hernandes and Clemente. This approach yields a system of nonlinear ODEs that, when solved, give equilibria exhibiting positive or negative triangularity, cusps, and (in an extreme limit) current singularities. It is shown that a cubic ansatz may also be used, but that polynomials of degree four or higher will lead to overdetermination.

physics.plasm-ph↗

arXiv2025

Gap modes in Arnold tongues and their topological origins

Gap modes in a modified Mathieu equation, perturbed by a Dirac delta potential, are investigated. It is proved that the modified Mathieu equation admits stable isolated gap modes with topological origins in the unstable regions of the Mathieu equation, which are known as Arnold tongues. The modes may be identified as localized electron wavefunctions in a 1D chain or as toroidal Alfv\'en eigenmodes. A generalization of this argument shows that gap modes can be induced in regimes of instability by localized potential perturbations for a large class of periodic Hamiltonians.

math-ph↗

arXiv2025

Computation of Magnetohydrodynamic Equilibria with Voigt Regularization

This work presents the first numerical investigation of using Voigt regularization as a method for obtaining magnetohydrodynamic (MHD) equilibria without the assumption of nested magnetic flux surfaces. Voigt regularization modifies the MHD dynamics by introducing additional terms that vanish in the infinite-time limit, allowing for magnetic reconnection and the formation of magnetic islands, which can overlap and produce field-line chaos. The utility of this approach is demonstrated through numerical solutions of two-dimensional ideal and resistive test problems. Our results show that Voigt regularization can significantly accelerate the convergence to solutions in resistive MHD problems, while also highlighting challenges in applying the method to ideal MHD systems. This research opens up new possibilities for developing more efficient and robust MHD equilibrium solvers, which could contribute to the design and optimization of future fusion devices.

physics.plasm-ph↗

arXiv2024

Flowing from Words to Pixels: A Noise-Free Framework for Cross-Modality Evolution

Diffusion models, and their generalization, flow matching, have had a remarkable impact on the field of media generation. Here, the conventional approach is to learn the complex mapping from a simple source distribution of Gaussian noise to the target media distribution. For cross-modal tasks such as text-to-image generation, this same mapping from noise to image is learnt whilst including a conditioning mechanism in the model. One key and thus far relatively unexplored feature of flow matching is that, unlike Diffusion models, they are not constrained for the source distribution to be noise. Hence, in this paper, we propose a paradigm shift, and ask the question of whether we can instead train flow matching models to learn a direct mapping from the distribution of one modality to the distribution of another, thus obviating the need for both the noise distribution and conditioning mechanism. We present a general and simple framework, CrossFlow, for cross-modal flow matching. We show the importance of applying Variational Encoders to the input data, and introduce a method to enable Classifier-free guidance. Surprisingly, for text-to-image, CrossFlow with a vanilla transformer without cross attention slightly outperforms standard flow matching, and we show that it scales better with training steps and model size, while also allowing for interesting latent arithmetic which results in semantically meaningful edits in the output space. To demonstrate the generalizability of our approach, we also show that CrossFlow is on par with or outperforms the state-of-the-art for various cross-modal / intra-modal mapping tasks, viz. image captioning, depth estimation, and image super-resolution. We hope this paper contributes to accelerating progress in cross-modal media generation.

cs.CV↗

arXiv2024

Optimising Iteration Scheduling for Full-State Vector Simulation of Quantum Circuits on FPGAs

As the field of quantum computing grows, novel algorithms which take advantage of quantum phenomena need to be developed. As we are currently in the NISQ (noisy intermediate scale quantum) era, quantum algorithm researchers cannot reliably test their algorithms on real quantum hardware, which is still too limited. Instead, quantum computing simulators on classical computing systems are used. In the quantum circuit model, quantum bits (qubits) are operated on by quantum gates. A quantum circuit is a sequence of such quantum gates operating on some number of qubits. A quantum gate applied to a qubit can be controlled by other qubits in the circuit. This applies the gate only to the states which satisfy the required control qubit state. We particularly target FPGAs as our main simulation platform, as these offer potential energy savings when compared to running simulations on CPUs/GPUs. In this work, we present a memory access pattern to optimise the number of iterations that need to be scheduled to execute a quantum gate such that only the iterations which access the required pairs (determined according to the control qubits imposed on the gate) are scheduled. We show that this approach results in a significant reduction in the time required to simulate a gate for each added control qubit. We also show that this approach benefits the simulation time on FPGAs more than CPUs and GPUs and allows to outperform both CPU and GPU platforms in terms of energy efficiency, which is the main factor for scalability of the simulations.

quant-ph↗

arXiv2024

Fault-tolerant quantum computation with a neutral atom processor

Quantum computing experiments are transitioning from running on physical qubits to using encoded, logical qubits. Fault-tolerant computation can identify and correct errors, and has the potential to enable the dramatically reduced logical error rates required for valuable algorithms. However, it requires flexible control of high-fidelity operations performed on large numbers of qubits. We demonstrate fault-tolerant quantum computation on a quantum processor with 256 qubits, each an individual neutral Ytterbium atom. The operations are designed so that key error sources convert to atom loss, which can be detected by imaging. Full connectivity is enabled by atom movement. We demonstrate the entanglement of 24 logical qubits encoded into 48 atoms, at once catching errors and correcting for, on average 1.8, lost atoms. We also implement the Bernstein-Vazirani algorithm with up to 28 logical qubits encoded into 112 atoms, showing better-than-physical error rates. In both cases, "erasure conversion," changing errors into a form that can be detected independently from qubit state, improves circuit performance. These results begin to clear a path for achieving scientific quantum advantage with a programmable neutral atom quantum processor.

quant-ph↗

arXiv2024

Movie Gen: A Cast of Media Foundation Models

We present Movie Gen, a cast of foundation models that generates high-quality, 1080p HD videos with different aspect ratios and synchronized audio. We also show additional capabilities such as precise instruction-based video editing and generation of personalized videos based on a user's image. Our models set a new state-of-the-art on multiple tasks: text-to-video synthesis, video personalization, video editing, video-to-audio generation, and text-to-audio generation. Our largest video generation model is a 30B parameter transformer trained with a maximum context length of 73K video tokens, corresponding to a generated video of 16 seconds at 16 frames-per-second. We show multiple technical innovations and simplifications on the architecture, latent spaces, training objectives and recipes, data curation, evaluation protocols, parallelization techniques, and inference optimizations that allow us to reap the benefits of scaling pre-training data, model size, and training compute for training large scale media generation models. We hope this paper helps the research community to accelerate progress and innovation in media generation models. All videos from this paper are available at https://go.fb.me/MovieGenResearchVideos.

cs.CV↗

arXiv2024

The VoxCeleb Speaker Recognition Challenge: A Retrospective

The VoxCeleb Speaker Recognition Challenges (VoxSRC) were a series of challenges and workshops that ran annually from 2019 to 2023. The challenges primarily evaluated the tasks of speaker recognition and diarisation under various settings including: closed and open training data; as well as supervised, self-supervised, and semi-supervised training for domain adaptation. The challenges also provided publicly available training and evaluation datasets for each task and setting, with new test sets released each year. In this paper, we provide a review of these challenges that covers: what they explored; the methods developed by the challenge participants and how these evolved; and also the current state of the field for speaker verification and diarisation. We chart the progress in performance over the five installments of the challenge on a common evaluation dataset and provide a detailed analysis of how each year's special focus affected participants' performance. This paper is aimed both at researchers who want an overview of the speaker recognition and diarisation field, and also at challenge organisers who want to benefit from the successes and avoid the mistakes of the VoxSRC challenges. We end with a discussion of the current strengths of the field and open challenges. Project page : https://mm.kaist.ac.kr/datasets/voxceleb/voxsrc/workshop.html

cs.SD↗

arXiv2024

AIFS -- ECMWF's data-driven forecasting system

Machine learning-based weather forecasting models have quickly emerged as a promising methodology for accurate medium-range global weather forecasting. Here, we introduce the Artificial Intelligence Forecasting System (AIFS), a data driven forecast model developed by the European Centre for Medium-Range Weather Forecasts (ECMWF). AIFS is based on a graph neural network (GNN) encoder and decoder, and a sliding window transformer processor, and is trained on ECMWF's ERA5 re-analysis and ECMWF's operational numerical weather prediction (NWP) analyses. It has a flexible and modular design and supports several levels of parallelism to enable training on high-resolution input data. AIFS forecast skill is assessed by comparing its forecasts to NWP analyses and direct observational data. We show that AIFS produces highly skilled forecasts for upper-air variables, surface weather parameters and tropical cyclone tracks. AIFS is run four times daily alongside ECMWF's physics-based NWP model and forecasts are available to the public under ECMWF's open data policy.

physics.ao-ph↗

arXiv2024

Generation, Distillation and Evaluation of Motivational Interviewing-Style Reflections with a Foundational Language Model

Large Foundational Language Models are capable of performing many tasks at a high level but are difficult to deploy in many applications because of their size and proprietary ownership. Many will be motivated to distill specific capabilities of foundational models into smaller models that can be owned and controlled. In the development of a therapeutic chatbot, we wish to distill a capability known as reflective listening, in which a therapist produces reflections of client speech. These reflections either restate what a client has said, or connect what was said to a relevant observation, idea or guess that encourages and guides the client to continue contemplation. In this paper, we present a method for distilling the generation of reflections from a Foundational Language Model (GPT-4) into smaller models. We first show that GPT-4, using zero-shot prompting, can generate reflections at near 100% success rate, superior to all previous methods. Using reflections generated by GPT-4, we fine-tune different sizes of the GPT-2 family. The GPT-2-small model achieves 83% success on a hold-out test set and the GPT-2 XL achieves 90% success. We also show that GPT-4 can help in the labor-intensive task of evaluating the quality of the distilled models, using it as a zero-shot classifier. Using triple-human review as a guide, the classifier achieves a Cohen-Kappa of 0.66, a substantial inter-rater reliability figure.

cs.CL↗

arXiv2023

Motion-Conditioned Image Animation for Video Editing

We introduce MoCA, a Motion-Conditioned Image Animation approach for video editing. It leverages a simple decomposition of the video editing problem into image editing followed by motion-conditioned image animation. Furthermore, given the lack of robust evaluation datasets for video editing, we introduce a new benchmark that measures edit capability across a wide variety of tasks, such as object replacement, background changes, style changes, and motion edits. We present a comprehensive human evaluation of the latest video editing methods along with MoCA, on our proposed benchmark. MoCA establishes a new state-of-the-art, demonstrating greater human preference win-rate, and outperforming notable recent approaches including Dreamix (63%), MasaCtrl (75%), and Tune-A-Video (72%), with especially significant improvements for motion edits.

cs.GR↗

arXiv2023

Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning

We present Emu Video, a text-to-video generation model that factorizes the generation into two steps: first generating an image conditioned on the text, and then generating a video conditioned on the text and the generated image. We identify critical design decisions--adjusted noise schedules for diffusion, and multi-stage training that enable us to directly generate high quality and high resolution videos, without requiring a deep cascade of models as in prior work. In human evaluations, our generated videos are strongly preferred in quality compared to all prior work--81% vs. Google's Imagen Video, 90% vs. Nvidia's PYOCO, and 96% vs. Meta's Make-A-Video. Our model outperforms commercial solutions such as RunwayML's Gen2 and Pika Labs. Finally, our factorizing approach naturally lends itself to animating images based on a user's text prompt, where our generations are preferred 96% over prior work.

cs.CV↗