Search

Numerical simulations play a critical role in design and development of engineering products and processes. Traditional computational methods, such as CFD, can provide accurate predictions but are computationally expensive, particularly for complex geometries. Several machine learning (ML) models have been proposed in the literature to significantly reduce computation time while maintaining acceptable accuracy. However, ML models often face limitations in terms of accuracy and scalability and depend on significant mesh downsampling, which can negatively affect prediction accuracy and generalization. In this work, we propose a novel ML model architecture, DoMINO (Decomposable Multi-scale Iterative Neural Operator) developed in NVIDIA Modulus to address the various challenges of machine learning based surrogate modeling of engineering simulations. DoMINO is a point cloudbased ML model that uses local geometric information to predict flow fields on discrete points. The DoMINO model is validated for the automotive aerodynamics use case using the DrivAerML dataset. Through our experiments we demonstrate the scalability, performance, accuracy and generalization of our model to both in-distribution and out-of-distribution testing samples. Moreover, the results are analyzed using a range of engineering specific metrics important for validating numerical simulations.

In recent decades organic electronics has entered the mainstream of consumer electronics, driven by innovations in scalability and low power applications, and low-cost fabrication methods. The potential for using organic semiconductor electronic devices as radiation detectors, and in particular for neutron detection is reported. We report results of laboratory tests using alpha particles as well as the response to thermal and fast neutrons covering the energy range 0.025 eV to 16.5 MeV. GEANT4 simulations are used to provide a detailed understanding of the performance and potential of this emerging technology for radiation detection., Comment: 2 pages

Graph Neural Networks (GNNs) have gained significant traction for simulating complex physical systems, with models like MeshGraphNet demonstrating strong performance on unstructured simulation meshes. However, these models face several limitations, including scalability issues, requirement for meshing at inference, and challenges in handling long-range interactions. In this work, we introduce X-MeshGraphNet, a scalable, multi-scale extension of MeshGraphNet designed to address these challenges. X-MeshGraphNet overcomes the scalability bottleneck by partitioning large graphs and incorporating halo regions that enable seamless message passing across partitions. This, combined with gradient aggregation, ensures that training across partitions is equivalent to processing the entire graph at once. To remove the dependency on simulation meshes, X-MeshGraphNet constructs custom graphs directly from tessellated geometry files (e.g., STLs) by generating point clouds on the surface or volume of the object and connecting k-nearest neighbors. Additionally, our model builds multi-scale graphs by iteratively combining coarse and fine-resolution point clouds, where each level refines the previous, allowing for efficient long-range interactions. Our experiments demonstrate that X-MeshGraphNet maintains the predictive accuracy of full-graph GNNs while significantly improving scalability and flexibility. This approach eliminates the need for time-consuming mesh generation at inference, offering a practical solution for real-time simulation across a wide range of applications. The code for reproducing the results presented in this paper is available through NVIDIA Modulus.

Large Language Models (LLMs) have recently demonstrated a remarkable ability to model time series data. These capabilities can be partly explained if LLMs understand basic time series concepts. However, our knowledge of what these models understand about time series data remains relatively limited. To address this gap, we introduce TimeSeriesExam, a configurable and scalable multiple-choice question exam designed to assess LLMs across five core time series understanding categories: pattern recognition, noise understanding, similarity analysis, anomaly detection, and causality analysis. TimeSeriesExam comprises of over 700 questions, procedurally generated using 104 carefully curated templates and iteratively refined to balance difficulty and their ability to discriminate good from bad models. We test 7 state-of-the-art LLMs on the TimeSeriesExam and provide the first comprehensive evaluation of their time series understanding abilities. Our results suggest that closed-source models such as GPT-4 and Gemini understand simple time series concepts significantly better than their open-source counterparts, while all models struggle with complex concepts such as causality analysis. We believe that the ability to programatically generate questions is fundamental to assessing and improving LLM's ability to understand and reason about time series data., Comment: Accepted at NeurIPS'24 Time Series in the Age of Large Models Workshop

Photo-doped Mott insulators can exhibit novel photocarrier transport and relaxation dynamics and non-equilibrium phases. However, time-resolved real-space imaging of these processes are still lacking. Here, we use scanning ultrafast electron microscopy (SUEM) to directly visualize the spatial-temporal evolution of photoexcited species in a spin-orbit assisted Mott insulator {\alpha}-RuCl3. At low optical fluences, we observe extremely long hot photocarrier transport time over one nanosecond, almost an order of magnitude longer than any known values in conventional semiconductors. At higher optical fluences, we observe nonlinear features suggesting a photo-induced insulator-to-metal transition, which is unusual in a large-gap Mott insulator. Our results demonstrate the rich physics in a photo-doped Mott insulator that can be extracted from spatial-temporal imaging and showcase the capability of SUEM to sensitively probe photoexcitations in strongly correlated electron systems., Comment: Comments are welcome. Please email feedback to bliao@ucsb.edu

Semiconductor heterojunctions have gained significant attention for efficient optoelectronic devices owing to their unique interfaces and synergistic effects. Interaction between charge carriers with the heterojunction plays a crucial role in determining device performance, while its spatial-temporal mapping remains lacking. In this study, we employ scanning ultrafast electron microscopy (SUEM), an emerging technique that combines high spatial-temporal resolution and surface sensitivity, to investigate photocarrier dynamics across a Si/Ge heterojunction. Charge dynamics are selectively examined across the junction and compared to far bulk areas, through which the impact of the built-in potential, band offsets, and surface effects is directly visualized. In particular, we find that the heterojunction drastically modifies the hot photocarrier diffusivities by up to 300%. These findings are further elucidated with insights from the band structure and surface potential measured by complementary techniques. This work demonstrates the tremendous effect of heterointerfaces on charge dynamics and showcases the potential of SUEM in characterizing realistic devices.

Text-to-video generative AI models such as Sora OpenAI have the potential to disrupt multiple industries. In this paper, we report a qualitative social media analysis aiming to uncover people's perceived impact of and concerns about Sora's integration. We collected and analyzed comments (N=292) under popular posts about Sora-generated videos, comparison between Sora videos and Midjourney images, and artists' complaints about copyright infringement by Generative AI. We found that people were most concerned about Sora's impact on content creation-related industries. Emerging governance challenges included the for-profit nature of OpenAI, the blurred boundaries between real and fake content, human autonomy, data privacy, copyright issues, and environmental impact. Potential regulatory solutions proposed by people included law-enforced labeling of AI content and AI literacy education for the public. Based on the findings, we discuss the importance of gauging people's tech perceptions early and propose policy recommendations to regulate Sora before its public release.

Since 1772, when Euler first described two methods of obtaining two pairs of biquadrates with equal sums, several methods of solving the diophantine equation $x^4+y^4=z^4+w^4$ have been published. All these methods yield parametric solutions in terms of homogeneous bivariate polynomials of odd degrees. In this paper we describe a method that yields three parametric solutions of the aforesaid diophantine equation in terms of homogeneous bivariate polynomials of even degrees, namely degrees~$74$, $88$ and $132$ respectively., Comment: 8 pages

We introduce MOMENT, a family of open-source foundation models for general-purpose time series analysis. Pre-training large models on time series data is challenging due to (1) the absence of a large and cohesive public time series repository, and (2) diverse time series characteristics which make multi-dataset training onerous. Additionally, (3) experimental benchmarks to evaluate these models, especially in scenarios with limited resources, time, and supervision, are still in their nascent stages. To address these challenges, we compile a large and diverse collection of public time series, called the Time series Pile, and systematically tackle time series-specific challenges to unlock large-scale multi-dataset pre-training. Finally, we build on recent work to design a benchmark to evaluate time series foundation models on diverse tasks and datasets in limited supervision settings. Experiments on this benchmark demonstrate the effectiveness of our pre-trained models with minimal data and task-specific fine-tuning. Finally, we present several interesting empirical observations about large pre-trained time series models. Pre-trained models (AutonLab/MOMENT-1-large) and Time Series Pile (AutonLab/Timeseries-PILE) are available on Huggingface., Comment: Accepted at ICML'24. This is a revision. See changelog in the Appendix

Large Language Models (LLMs) are advancing quickly and impacting people's lives for better or worse. In higher education, concerns have emerged such as students' misuse of LLMs and degraded education outcomes. To unpack the ethical concerns of LLMs for higher education, we conducted a case study consisting of stakeholder interviews (n=20) in higher education computer science. We found that students use several distinct mental models to interact with LLMs - LLMs serve as a tool for (a) writing, (b) coding, and (c) information retrieval, which differ somewhat in ethical considerations. Students and teachers brought up ethical issues that directly impact them, such as inaccurate LLM responses, hallucinations, biases, privacy leakage, and academic integrity issues. Participants emphasized the necessity of guidance and rules for the use of LLMs in higher education, including teaching digital literacy, rethinking education, and having cautious and contextual policies. We reflect on the ethical challenges and propose solutions.

In this paper we prove that there exist infinitely many integers which can be expressed as a sum of four cubes of polynomials with integer coefficients. We give several identities that express the integers 1 and 2 as a sum of four cubes of polynomials. We also show that every integer can be expressed as a sum of five cubes of polynomials with integer coefficients., Comment: 6 pages

A set of rational points on a curve is said to be in geometric progression if either the abscissae or the ordinates of the points are in geometric progression. Examples of three points in geometric progression on a circle are already known. In this paper we obtain infinitely many examples of four points in geometric progression on a circle with rational radius., Comment: 11 pages

This paper is concerned with finite sequences of integers that may be written as sums of squares of two nonzero integers. We first find infinitely many integers $n$ such that $n, n+h$ and $n+k$ are all sums of two squares where $h$ and $k$ are two arbitrary integers, and as an immediate corollary obtain, in parametric terms, three consecutive integers that are sums of two squares. Similarly we obtain $n$ in parametric terms such that all the four integers $n, n+1, n+2, n+4$ are sums of two squares. We also find infinitely many integers $n$ such that all the five integers $n, n+1, n+2, n+4, n+5$ are sums of two squares, and finally, we find infinitely many arithmetic progressions, with common difference $4$, of five integers all of which are sums of two squares., Comment: We have removed Section 4 from the earlier version as there was an error. Accepted in Int. J. Number Theory