In the context of proxy modeling for process systems, traditional data-driven deep learning approaches frequently encounter significant challenges, such as substantial training costs induced by large amounts of data, and limited generalization capabilities. As a promising alternative, physics-aware models incorporate partial physics knowledge to ameliorate these challenges. Although demonstrating efficacy, they fall short in terms of exploration depth and universality. To address these shortcomings, we introduce a physics-aware proxy model (PAPM) that fully incorporates partial prior physics of process systems, which includes multiple input conditions and the general form of conservation relations, resulting in better out-of-sample generalization. Additionally, PAPM contains a holistic temporal-spatial stepping module for flexible adaptation across various process systems. Through systematic comparisons with state-of-the-art pure data-driven and physics-aware models across five two-dimensional benchmarks in nine generalization tasks, PAPM notably achieves an average performance improvement of 6.7%, while requiring fewer FLOPs, and just 1% of the parameters compared to the prior leading method. The code is available at https://github.com/pengwei07/PAPM.

Vibration sensors are essential in acquiring seismic activity for an accurate earthquake assessment. The state-of-the-art sensors can provide the best signal quality and the highest bandwidth; however, their high cost usually hinders a wide range of applicability and coverage, which is otherwise possible with their basic and cheap counterparts. But, their poor quality and low bandwidth can significantly degrade the signal fidelity and result in an imprecise analysis. To address these drawbacks, in this study, we propose a novel, high-quality, and full bandwidth seismic signal synthesis by transforming the signal acquired from an inferior sensor. We employ 1D Operational Generative Adversarial Networks (Op-GANs) with novel loss functions to achieve this. Therefore, the study's key contributions include releasing a new dataset, addressing operational constraints in seismic monitoring, and pioneering a deep-learning transformation technique to create the first virtual seismic sensor. The proposed method is extensively evaluated over the Simulated Ground Motion (SimGM) benchmark dataset, and the results demonstrated that the proposed approach significantly improves the quality and bandwidth of seismic signals acquired from a variety of sensors, including a cheap seismic sensor, the CSN-Phidgets, and the integrated accelerometers of an Android, and iOS phone, to the same level as the state-of-the-art sensor (e.g., Kinemetrics-Episensor). The SimGM dataset, our results, and the optimized PyTorch implementation of the proposed approach are publicly shared.

This paper presents the design of a hardware accelerator for Transformers, optimized for on-device time-series forecasting in AIoT systems. It integrates integer-only quantization and Quantization-Aware Training with optimized hardware designs to realize 6-bit and 4-bit quantized Transformer models, which achieved precision comparable to 8-bit quantized models from related research. Utilizing a complete implementation on an embedded FPGA (Xilinx Spartan-7 XC7S15), we examine the feasibility of deploying Transformer models on embedded IoT devices. This includes a thorough analysis of achievable precision, resource utilization, timing, power, and energy consumption for on-device inference. Our results indicate that while sufficient performance can be attained, the optimization process is not trivial. For instance, reducing the quantization bitwidth does not consistently result in decreased latency or energy consumption, underscoring the necessity of systematically exploring various optimization combinations. Compared to an 8-bit quantized Transformer model in related studies, our 4-bit quantized Transformer model increases test loss by only 0.63%, operates up to 132.33x faster, and consumes 48.19x less energy.

Summarization is a fundamental task in natural language processing (NLP) and since large language models (LLMs), such as GPT-4 and Claude, come out, increasing attention has been paid to long-form summarization whose input sequences are much longer, indicating more information contained. The current evaluation metrics either use similarity-based metrics like ROUGE and BERTScore which rely on similarity and fail to consider informativeness or LLM-based metrics, lacking quantitative analysis of information richness and are rather subjective. In this paper, we propose a new evaluation metric called EVA-Score using Atomic Fact Chain Generation and Document-level Relation Extraction together to automatically calculate the informativeness and give a definite number as an information score. Experiment results show that our metric shows a state-of-the-art correlation with humans. We also re-evaluate the performance of LLMs on long-form summarization comprehensively from the information aspect, forecasting future ways to use LLMs for long-form summarization.

The Environmental Extended Multi-Regional Input-Output analysis is the predominant framework in Ecological Economics for assessing the environmental impact of economic activities. This paper introduces ExioML, the first Machine Learning benchmark dataset designed for sustainability analysis, aimed at lowering barriers and fostering collaboration between Machine Learning and Ecological Economics research. A crucial greenhouse gas emission regression task was conducted to evaluate sectoral sustainability and demonstrate the usability of the dataset. We compared the performance of traditional shallow models with deep learning models, utilizing a diverse Factor Accounting table and incorporating various categorical and numerical features. Our findings reveal that ExioML, with its high usability, enables deep and ensemble models to achieve low mean square errors, establishing a baseline for future Machine Learning research. Through ExioML, we aim to build a foundational dataset supporting various Machine Learning applications and promote climate actions and sustainable investment decisions.

Components of cyber physical systems, which affect real-world processes, are often exposed to the internet. Replacing conventional control methods with Deep Reinforcement Learning (DRL) in energy systems is an active area of research, as these systems become increasingly complex with the advent of renewable energy sources and the desire to improve their efficiency. Artificial Neural Networks (ANN) are vulnerable to specific perturbations of their inputs or features, called adversarial examples. These perturbations are difficult to detect when properly regularized, but have significant effects on the ANN's output. Because DRL uses ANN to map optimal actions to observations, they are similarly vulnerable to adversarial examples. This work proposes a novel attack technique for continuous control using Group Difference Logits loss with a bifurcation layer. By combining aspects of targeted and untargeted attacks, the attack significantly increases the impact compared to an untargeted attack, with drastically smaller distortions than an optimally targeted attack. We demonstrate the impacts of powerful gradient-based attacks in a realistic smart energy environment, show how the impacts change with different DRL agents and training procedures, and use statistical and time-series analysis to evaluate attacks' stealth. The results show that adversarial attacks can have significant impacts on DRL controllers, and constraining an attack's perturbations makes it difficult to detect. However, certain DRL architectures are far more robust, and robust training methods can further reduce the impact.

Unit testing is crucial in software engineering for ensuring quality. However, it's not widely used in parallel and high-performance computing software, particularly scientific applications, due to their smaller, diverse user base and complex logic. These factors make unit testing challenging and expensive, as it requires specialized knowledge and existing automated tools are often ineffective. To address this, we propose an automated method for generating unit tests for such software, considering their unique features like complex logic and parallel processing. Recently, large language models (LLMs) have shown promise in coding and testing. We explored the capabilities of Davinci (text-davinci-002) and ChatGPT (gpt-3.5-turbo) in creating unit tests for C++ parallel programs. Our results show that LLMs can generate mostly correct and comprehensive unit tests, although they have some limitations, such as repetitive assertions and blank test cases.

One evening in the spring of 2015, I filmed a 15-second video out the window of an Amtrak train as it rattled across the barren flatlands of southern New Jersey. All you see is a slanted rush of white and yellow lights. I can't remember why I made it. Until a few days ago, I had never even watched it. And yet for the past nine years, that video has been sitting on a server in a data center somewhere, silently and invisibly taking a very small toll on our planet.

The task of conditional generation is one of the most important applications of generative models, and numerous methods have been developed to date based on the celebrated flow-based models. However, many flow-based models in use today are not built to allow one to introduce an explicit inductive bias to how the conditional distribution to be generated changes with respect to conditions. This can result in unexpected behavior in the task of style transfer, for example. In this research, we introduce extended flow matching (EFM), a direct extension of flow matching that learns a "matrix field" corresponding to the continuous map from the space of conditions to the space of distributions. We show that we can introduce inductive bias to the conditional generation through the matrix field and demonstrate this fact with MMOT-EFM, a version of EFM that aims to minimize the Dirichlet energy or the sensitivity of the distribution with respect to conditions. We will present our theory along with experimental results that support the competitiveness of EFM in conditional generation.

Spinal fixation procedures are currently limited by the rigidity of the existing instruments and pedicle screws leading to fixation failures and rigid pedicle screw pull out. Leveraging our recently developed Concentric Tube Steerable Drilling Robot (CT-SDR) in integration with a robotic manipulator, to address the aforementioned issue, here we introduce the transformative concept of Spatial Spinal Fixation (SSF) using a unique Flexible Pedicle Screw (FPS). The proposed SSF procedure enables planar and out-of-plane placement of the FPS throughout the full volume of the vertebral body. In other words, not only does our fixation system provide the option of drilling in-plane and out-of-plane trajectories, it also enables implanting the FPS inside linear (represented by an I-shape) and/or non-linear (represented by J-shape) trajectories. To thoroughly evaluate the functionality of our proposed robotic system and the SSF procedure, we have performed various experiments by drilling different I-J and J-J drilling trajectory pairs into our custom-designed L3 vertebral phantoms and analyzed the accuracy of the procedure using various metrics.