Search

3D scene stylization refers to transform the appearance of a 3D scene to match a given style image, ensuring that images rendered from different viewpoints exhibit the same style as the given style image, while maintaining the 3D consistency of the stylized scene. Several existing methods have obtained impressive results in stylizing 3D scenes. However, the models proposed by these methods need to be re-trained when applied to a new scene. In other words, their models are coupled with a specific scene and cannot adapt to arbitrary other scenes. To address this issue, we propose a novel 3D scene stylization framework to transfer an arbitrary style to an arbitrary scene, without any style-related or scene-related re-training. Concretely, we first map the appearance of the 3D scene into a 2D style pattern space, which realizes complete disentanglement of the geometry and appearance of the 3D scene and makes our model be generalized to arbitrary 3D scenes. Then we stylize the appearance of the 3D scene in the 2D style pattern space via a prompt-based 2D stylization algorithm. Experimental results demonstrate that our proposed framework is superior to SOTA methods in both visual quality and generalization., Comment: Accepted to AAAI 2024

Existing generative adversarial network (GAN) based conditional image generative models typically produce fixed output for the same conditional input, which is unreasonable for highly subjective tasks, such as large-mask image inpainting or style transfer. On the other hand, GAN-based diverse image generative methods require retraining/fine-tuning the network or designing complex noise injection functions, which is computationally expensive, task-specific, or struggle to generate high-quality results. Given that many deterministic conditional image generative models have been able to produce high-quality yet fixed results, we raise an intriguing question: is it possible for pre-trained deterministic conditional image generative models to generate diverse results without changing network structures or parameters? To answer this question, we re-examine the conditional image generation tasks from the perspective of adversarial attack and propose a simple and efficient plug-in projected gradient descent (PGD) like method for diverse and controllable image generation. The key idea is attacking the pre-trained deterministic generative models by adding a micro perturbation to the input condition. In this way, diverse results can be generated without any adjustment of network structures or fine-tuning of the pre-trained models. In addition, we can also control the diverse results to be generated by specifying the attack direction according to a reference text or image. Our work opens the door to applying adversarial attack to low-level vision tasks, and experiments on various conditional image generation tasks demonstrate the effectiveness and superiority of the proposed method., Comment: 9 pages, 7 figures, accepted by AAAI24

Current serverless platforms struggle to optimize resource utilization due to their dynamic and fine-grained nature. Conventional techniques like overcommitment and autoscaling fall short, often sacrificing utilization for practicability or incurring performance trade-offs. Overcommitment requires predicting performance to prevent QoS violation, introducing trade-off between prediction accuracy and overheads. Autoscaling requires scaling instances in response to load fluctuations quickly to reduce resource wastage, but more frequent scaling also leads to more cold start overheads. This paper introduces Jiagu, which harmonizes efficiency with practicability through two novel techniques. First, pre-decision scheduling achieves accurate prediction while eliminating overheads by decoupling prediction and scheduling. Second, dual-staged scaling achieves frequent adjustment of instances with minimum overhead. We have implemented a prototype and evaluated it using real-world applications and traces from the public cloud platform. Our evaluation shows a 54.8% improvement in deployment density over commercial clouds (with Kubernetes) while maintaining QoS, and 81.0%--93.7% lower scheduling costs and a 57.4%--69.3% reduction in cold start latency compared to existing QoS-aware schedulers in research work., Comment: 17 pages, 17 figures

GPU remoting is a promising technique for supporting AI applications. Networking plays a key role in enabling remoting. However, for efficient remoting, the network requirements in terms of latency and bandwidth are unknown. In this paper, we take a GPU-centric approach to derive the minimum latency and bandwidth requirements for GPU remoting, while ensuring no (or little) performance degradation for AI applications. Our study including theoretical model demonstrates that, with careful remoting design, unmodified AI applications can run on the remoting setup using commodity networking hardware without any overhead or even with better performance, with low network demands.

Checkpointing (C) and restoring (R) are key components for GPU tasks. POS is an OS-level GPU C/R system: It can transparently checkpoint or restore processes that use the GPU, without requiring any cooperation from the application, a key feature required by modern systems like the cloud. Moreover, POS is the first OS-level C/R system that can concurrently execute C/R with the application execution: a critical feature that can be trivially achieved when the processes only running on the CPU, but becomes challenging when the processes use GPU. The problem is how to ensure consistency during concurrent execution with the lack of application semantics due to transparency. CPU processes can leverage OS and hardware paging to fix inconsistency without application semantics. Unfortunately, GPU bypasses OS and paging for high performance. POS fills the semantic gap by speculatively extracting buffer access information of GPU kernels during runtime. Thanks to the simple and well-structured nature of GPU kernels, our speculative extraction (with runtime validation) achieves 100% accuracy on applications from training to inference whose domains span from vision, large language models, and reinforcement learning. Based on the extracted semantics, we systematically overlap C/R with application execution, and achieves orders of magnitude higher performance under various tasks compared with the state-of-the-art OS-level GPU C/R, including training fault tolerance, live GPU process migration, and cold starts acceleration in GPU-based serverless computing.

Vector searches on large-scale datasets are critical to modern online services like web search and RAG, which necessity storing the datasets and their index on the secondary storage like SSD. In this paper, we are the first to characterize the trade-off of performance and index size in existing SSD-based graph and cluster indexes: to improve throughput by 5.7$\times$ and 1.7$\times$, these indexes have to pay a 5.8$\times$ storage amplification and 7.7$\times$ with respect to the dataset size, respectively. The root cause is that the coarse-grained access of SSD mismatches the fine-grained random read required by vector indexes with small amplification. This paper argues that second-tier memory, such as remote DRAM/NVM connected via RDMA or CXL, is a powerful storage for addressing the problem from a system's perspective, thanks to its fine-grained access granularity. However, putting existing indexes -- primarily designed for SSD -- directly on second-tier memory cannot fully utilize its power. Meanwhile, second-tier memory still behaves more like storage, so using it as DRAM is also inefficient. To this end, we build a graph and cluster index that centers around the performance features of second-tier memory. With careful execution engine and index layout designs, we show that vector indexes can achieve optimal performance with orders of magnitude smaller index amplification, on a variety of second-tier memory devices. Based on our improved graph and vector indexes on second-tier memory, we further conduct a systematic study between them to facilitate developers choosing the right index for their workloads. Interestingly, the findings on the second-tier memory contradict the ones on SSDs.

Electric buses (EBs) are gaining popularity worldwide as a more sustainable and eco-friendly alternative to diesel buses (DBs). Electricity-saving driving plays a crucial role in minimizing an EB’s energy consumption, subsequently leading to an extended driving range. This study proposes a machine learning–based framework for identifying electricity-saving EB driving behaviors during various driving stages, including running on road segments, entering bus stops/intersections, and exiting bus stops/intersections. The proposed random forest (RF) model effectively evaluates the energy consumption level using EB drivers’ historical driving data under different scenarios. Specifically, the electricity consumption factor (ECF), as the evaluation index, is divided into three categories to determine the implicit relationship between driving behavior and energy consumption. The results indicate that the classification accuracy of RF models surpasses 90%, which highlights the effectiveness in accurately identifying energy-efficient EB driving behaviors. In addition, the Shapley additive explanations (SHAP) and partial dependency plots (PDPs) are utilized to visualize and interpret the results of RF models. A speed interval of 30–40 km/h is identified as the most energy-efficient range for EB running on a road segment. Findings from this study can be applied to targeted optimization of electricity-saving driving strategies in different driving scenarios to improve the overall efficiency and sustainability of the transportation system.

As the most popular mechanism, the generalized Snell's law has been applied extensively to design metasurfaces for wave manipulation. By modulating phase profile using metasurfaces, various novel wave transformations have been demonstrated. However, it has been found that the performance of these metasurfaces cannot be fully determined by the generalized Snell's law and in some cases, the wave fields appear to be contradictory to what predicted by the generalized Snell's law. In this work, a systematic numerical study is conducted to investigate the generalized Snell's law for elastic waves. The inherent assumptions of the generalized Snell's law are examined first followed by the study of the effects of various implementation issues on the performance of the metasurfaces. In particular, the fundamental mechanism for producing wave components that do not obey the generalized Snell's lay is identified and theoretically justified. Design guidelines for metasurfaces for improved performance are provided.

In the high-mobility scenarios of next-generation wireless communication systems (beyond 5G/6G), the performance of orthogonal frequency division multiplexing (OFDM) deteriorates drastically due to the loss of orthogonality between the subcarriers caused by large Doppler frequency shifts. Various emerging waveforms have been proposed for fast time-varying channels with excellent results. In this paper, we classify these waveforms from the perspective of their modulation domain and establish a unified framework to provide a comprehensive system structure comparison. Then we analyze bit error rate (BER) performance of each waveform in doubly selective channels. Through the discussions on their complexity and compatibility with OFDM systems, we finally give the candidate waveform suggestions.

Adaptive Random Testing (ART) enhances the testing effectiveness (including fault-detection capability) of Random Testing (RT) by increasing the diversity of the random test cases throughout the input domain. Many ART algorithms have been investigated such as Fixed-Size-Candidate-Set ART (FSCS) and Restricted Random Testing (RRT), and have been widely used in many practical applications. Despite its popularity, ART suffers from the problem of high computational costs during test-case generation, especially as the number of test cases increases. Although several strategies have been proposed to enhance the ART testing efficiency, such as the forgetting strategy and the k-dimensional tree strategy, these algorithms still face some challenges, including: (1) Although these algorithms can reduce the computation time, their execution costs are still very high, especially when the number of test cases is large; and (2) To achieve low computational costs, they may sacrifice some fault-detection capability. In this paper, we propose an approach based on Approximate Nearest Neighbors (ANNs), called Locality-Sensitive Hashing ART (LSH-ART). When calculating distances among different test inputs, LSH-ART identifies the approximate (not necessarily exact) nearest neighbors for candidates in an efficient way. LSH-ART attempts to balance ART testing effectiveness and efficiency., Comment: To be published in IEEE Transactions on Software Engineering

Road, rail, air, and sea transport generate a major fraction of outdoor ultrafine particles. However, there is no common methodology for comparable sub 100 nm particle emissions measurement. This paper presents the nPETS (grant agreement No 954377) concept to understand and mitigate the effects of emerging non-regulated nanoparticle emissions. This paper presents the concept and selected results. For example, nucleation and condensation mechanisms occur more frequently in the urban background site, leading to new particle formation, while mostly fresh emissions are measured in the traffic site.

This paper introduces PowerInfer, a high-speed Large Language Model (LLM) inference engine on a personal computer (PC) equipped with a single consumer-grade GPU. The key underlying the design of PowerInfer is exploiting the high locality inherent in LLM inference, characterized by a power-law distribution in neuron activation. This distribution indicates that a small subset of neurons, termed hot neurons, are consistently activated across inputs, while the majority, cold neurons, vary based on specific inputs. PowerInfer exploits such an insight to design a GPU-CPU hybrid inference engine: hot-activated neurons are preloaded onto the GPU for fast access, while cold-activated neurons are computed on the CPU, thus significantly reducing GPU memory demands and CPU-GPU data transfers. PowerInfer further integrates adaptive predictors and neuron-aware sparse operators, optimizing the efficiency of neuron activation and computational sparsity. Evaluation shows that PowerInfer attains an average token generation rate of 13.20 tokens/s, with a peak of 29.08 tokens/s, across various LLMs (including OPT-175B) on a single NVIDIA RTX 4090 GPU, only 18% lower than that achieved by a top-tier server-grade A100 GPU. This significantly outperforms llama.cpp by up to 11.69x while retaining model accuracy., Comment: 15 pages, 18 figures

Mobile software engineering has been a hot research topic for decades. Our fellow researchers have proposed various approaches (with over 7,000 publications for Android alone) in this field that essentially contributed to the great success of the current mobile ecosystem. Existing research efforts mainly focus on popular mobile platforms, namely Android and iOS. OpenHarmony, a newly open-sourced mobile platform, has rarely been considered, although it is the one requiring the most attention as OpenHarmony is expected to occupy one-third of the market in China (if not in the world). To fill the gap, we present to the mobile software engineering community a research roadmap for encouraging our fellow researchers to contribute promising approaches to OpenHarmony. Specifically, we start by presenting a literature review of mobile software engineering, attempting to understand what problems have been targeted by the mobile community and how they have been resolved. We then summarize the existing (limited) achievements of OpenHarmony and subsequently highlight the research gap between Android/iOS and OpenHarmony. This research gap eventually helps in forming the roadmap for conducting software engineering research for OpenHarmony.

Artistic style transfer aims to create new artistic images by rendering a given photograph with the target artistic style. Existing methods learn styles simply based on global statistics or local patches, lacking careful consideration of the drawing process in practice. Consequently, the stylization results either fail to capture abundant and diversified local style patterns, or contain undesired semantic information of the style image and deviate from the global style distribution. To address this issue, we imitate the drawing process of humans and propose a Two-Stage Statistics-Aware Transformation (TSSAT) module, which first builds the global style foundation by aligning the global statistics of content and style features and then further enriches local style details by swapping the local statistics (instead of local features) in a patch-wise manner, significantly improving the stylization effects. Moreover, to further enhance both content and style representations, we introduce two novel losses: an attention-based content loss and a patch-based style loss, where the former enables better content preservation by enforcing the semantic relation in the content image to be retained during stylization, and the latter focuses on increasing the local style similarity between the style and stylized images. Extensive qualitative and quantitative experiments verify the effectiveness of our method., Comment: Accepted by ACM MM 2023

The failure atomic and isolated execution of clients operations is a default requirement for a system that serve multiple loosely coupled clients at a server. However, disaggregated memory breaks this requirement in remote indexes because a client operation is disaggregated to multiple remote reads/writes. Current indexes focus on performance improvements and largely ignore tolerating client failures. We argue that a practical DM index should be transactional: each index operation should be failure atomic and isolated in addition to being concurrency isolated. We present repairable transaction (rTX), a lightweight primitive to execute DM index operations. Each rTX can detect other failed rTXes on-the-fly with the help of concurrency control. Upon detection, it will repair their non-atomic updates online with the help of logging, thus hiding their failures from healthy clients. By further removing unnecessary logging and delegating concurrency control to existing carefully-tuned index algorithms, we show that transactional indexes can be built at a low performance overhead on disaggregated memory. We have refactored two state-of-the-art DM indexes, RaceHashing and Sherman (B+Tree), with rTX. Evaluations show that rTX is 1.2 to 2X faster than other alternatives, e.g., distributed transaction. Meanwhile, its overhead is up to 42% compared to non-fault-tolerant indexes.

Various metasurfaces have been designed based on the generalized Snell’s law (GSL), but their performances are undermined by extra propagating waves that do not follow the GSL, especially when the phase gradient is large [1]. Although a modified version of GSL has been proposed for acoustic metasurfaces to describe the extra waves [2], the underlying mechanism of extra wave generation remains unclear. For elastic metasurfaces, such extra waves also exist as shown in Figure 1, indicating that the GSL might be invalid under some circumstances. In light of this, a systematic numerical study on the GSL for elastic waves is performed. It is found that mismatched impedance, material discontinuity, and phase discontinuity are the sources of the extra waves. The generation mechanisms of the extra waves from these sources are identified and theoretically justified. Based on these results, a guideline on metasurface design for improved performance is devised.

SmartNICs have recently emerged as an appealing device for accelerating distributed systems. However, there has not been a comprehensive characterization of SmartNICs, and existing designs typically only leverage a single communication path for workload offloading. This paper presents the first holistic study of a representative off-path SmartNIC, specifically the Bluefield-2, from a communication-path perspective. Our experimental study systematically explores the key performance characteristics of communication among the client, on-board SoC, and host, and offers insightful findings and advice for designers. Moreover, we propose the concurrent use of multiple communication paths of a SmartNIC and present a pioneering guideline to expose new optimization opportunities for various distributed systems. To demonstrate the effectiveness of our approach, we conducted case studies on a SmartNIC-based distributed file system (LineFS) and an RDMA-based disaggregated key-value store (DrTM-KV). Our experimental results show improvements of up to 30% and 25% for LineFS and DrTM-KV, respectively., Comment: Published at OSDI23

Arbitrary style transfer (AST) transfers arbitrary artistic styles onto content images. Despite the recent rapid progress, existing AST methods are either incapable or too slow to run at ultra-resolutions (e.g., 4K) with limited resources, which heavily hinders their further applications. In this paper, we tackle this dilemma by learning a straightforward and lightweight model, dubbed MicroAST. The key insight is to completely abandon the use of cumbersome pre-trained Deep Convolutional Neural Networks (e.g., VGG) at inference. Instead, we design two micro encoders (content and style encoders) and one micro decoder for style transfer. The content encoder aims at extracting the main structure of the content image. The style encoder, coupled with a modulator, encodes the style image into learnable dual-modulation signals that modulate both intermediate features and convolutional filters of the decoder, thus injecting more sophisticated and flexible style signals to guide the stylizations. In addition, to boost the ability of the style encoder to extract more distinct and representative style signals, we also introduce a new style signal contrastive loss in our model. Compared to the state of the art, our MicroAST not only produces visually superior results but also is 5-73 times smaller and 6-18 times faster, for the first time enabling super-fast (about 0.5 seconds) AST at 4K ultra-resolutions. Code is available at https://github.com/EndyWon/MicroAST., Comment: Accepted by AAAI 2023

Serverless platforms essentially face a tradeoff between container startup time and provisioned concurrency (i.e., cached instances), which is further exaggerated by the frequent need for remote container initialization. This paper presents MITOSIS, an operating system primitive that provides fast remote fork, which exploits a deep codesign of the OS kernel with RDMA. By leveraging the fast remote read capability of RDMA and partial state transfer across serverless containers, MITOSIS bridges the performance gap between local and remote container initialization. MITOSIS is the first to fork over 10,000 new containers from one instance across multiple machines within a second, while allowing the new containers to efficiently transfer the pre-materialized states of the forked one. We have implemented MITOSIS on Linux and integrated it with FN, a popular serverless platform. Under load spikes in real-world serverless workloads, MITOSIS reduces the function tail latency by 89% with orders of magnitude lower memory usage. For serverless workflow that requires state transfer, MITOSIS improves its execution time by 86%., Comment: To appear in OSDI'23

In this work, two fast multipole boundary element formulations for the linear time-harmonic acoustic analysis of finite periodic structures are presented. Finite periodic structures consist of a bounded number of unit cell replications in one or more directions of periodicity. Such structures can be designed to efficiently control and manipulate sound waves and are referred to as acoustic metamaterials or sonic crystals. Our methods subdivide the geometry into boxes which correspond to the unit cell. A boundary element discretization is applied and interactions between well separated boxes are approximated by a fast multipole expansion. Due to the periodicity of the underlying geometry, certain operators of the expansion become block Toeplitz matrices. This allows to express matrix-vector products as circular convolutions which significantly reduces the computational effort and the overall memory requirements. The efficiency of the presented techniques is shown based on an acoustic scattering problem. In addition, a study on the design of sound barriers is presented where the performance of a wall-like sound barrier is compared to the performance of two sonic crystal sound barriers.

Today's mainstream virtualization systems comprise of two cooperative components: a kernel-resident driver that accesses virtualization hardware and a user-level helper process that provides VM management and I/O virtualization. However, this virtualization architecture has intrinsic issues in both security (a large attack surface) and performance. While there is a long thread of work trying to minimize the kernel-resident driver by offloading functions to user mode, they face a fundamental tradeoff between security and performance: more offloading may reduce the kernel attack surface, yet increase the runtime ring crossings between the helper process and the driver, and thus more performance cost. This paper explores a new design called delegated virtualization, which completely separates the control plane (the kernel driver) from the data plane (the helper process) and thus eliminates the kernel driver from runtime intervention. The resulting user-level hypervisor, called DuVisor, can handle all VM operations without trapping into the kernel once the kernel driver has done the initialization. DuVisor retrofits existing hardware virtualization support with a new delegated virtualization extension to directly handle VM exits, configure virtualization registers, manage the stage-2 page table and virtual devices in user mode. We have implemented the hardware extension on an open-source RISC-V CPU and built a Rust-based hypervisor atop the hardware. Evaluation on FireSim shows that DuVisor outperforms KVM by up to 47.96\% in a variety of real-world applications and significantly reduces the attack surface., Comment: 17 pages, 9 figures

We present KRCORE, an RDMA library with a microsecond-scale control plane on commodity RDMA hardware for elastic computing. KRCORE can establish a full-fledged RDMA connection within 10{\mu}s (hundreds or thousands of times faster than verbs), while only maintaining a (small) fixed-sized connection metadata at each node, regardless of the cluster scale. The key ideas include virtualizing pre-initialized kernel-space RDMA connections instead of creating one from scratch, and retrofitting advanced RDMA dynamic connected transport with static transport for both low connection overhead and high networking speed. Under load spikes, KRCORE can shorten the worker bootstrap time of an existing disaggregated key-value store (namely RACE Hashing) by 83%. In serverless computing (namely Fn), KRCORE can also reduce the latency for transferring data through RDMA by 99%., Comment: To appear in USENIX ATC'2022 (https://www.usenix.org/conference/atc22/presentation/wei)

In this paper, we present the texture reformer, a fast and universal neural-based framework for interactive texture transfer with user-specified guidance. The challenges lie in three aspects: 1) the diversity of tasks, 2) the simplicity of guidance maps, and 3) the execution efficiency. To address these challenges, our key idea is to use a novel feed-forward multi-view and multi-stage synthesis procedure consisting of I) a global view structure alignment stage, II) a local view texture refinement stage, and III) a holistic effect enhancement stage to synthesize high-quality results with coherent structures and fine texture details in a coarse-to-fine fashion. In addition, we also introduce a novel learning-free view-specific texture reformation (VSTR) operation with a new semantic map guidance strategy to achieve more accurate semantic-guided and structure-preserved texture transfer. The experimental results on a variety of application scenarios demonstrate the effectiveness and superiority of our framework. And compared with the state-of-the-art interactive texture transfer algorithms, it not only achieves higher quality results but, more remarkably, also is 2-5 orders of magnitude faster. Code is available at https://github.com/EndyWon/Texture-Reformer., Comment: Accepted by AAAI2022

The pursuit of power-efficiency is popularizing asymmetric multicore processors (AMP) such as ARM big.LITTLE, Apple M1 and recent Intel Alder Lake with big and little cores. However, we find that existing scalable locks fail to scale on AMP and cause collapses in either throughput or latency, or both, because their implicit assumption of symmetric cores no longer holds. To address this issue, we propose the first asymmetry-aware scalable lock named LibASL. LibASL provides a new lock ordering guided by applications' latency requirements, which allows big cores to reorder with little cores for higher throughput under the condition of preserving applications' latency requirements. Using LibASL only requires linking the applications with it and, if latency-critical, inserting few lines of code to annotate the coarse-grained latency requirement. We evaluate LibASL in various benchmarks including five popular databases on Apple M1. Evaluation results show that LibASL can improve the throughput by up to 5 times while precisely preserving the tail latency designated by applications.

Concurrency control algorithms are key determinants of the performance of in-memory databases. Existing algorithms are designed to work well for certain workloads. For example, optimistic concurrency control (OCC) is better than two-phase-locking (2PL) under low contention, while the converse is true under high contention. To adapt to different workloads, prior works mix or switch between a few known algorithms using manual insights or simple heuristics. We propose a learning-based framework that instead explicitly optimizes concurrency control via offline training to maximize performance. Instead of choosing among a small number of known algorithms, our approach searches in a "policy space" of fine-grained actions, resulting in novel algorithms that can outperform existing algorithms by specializing to a given workload. We build Polyjuice based on our learning framework and evaluate it against several existing algorithms. Under different configurations of TPC-C and TPC-E, Polyjuice can achieve throughput numbers higher than the best of existing algorithms by 15% to 56%.

This technical report contains material accompanying our work with same title published at ASPLOS'21. We start in Sec. 1 with a detailed presentation of the core innovation of this work, Await Model Checking (AMC). The correctness proofs of AMC can be found in Sec. 2. Next, we discuss three study cases in Sec. 3, presenting bugs found and challenges encountered when applying VSync to existing code bases. Finally, in Sec. 4 we describe the setup details of our evaluation and report further experimental results.

Gram-based and patch-based approaches are two important research lines of style transfer. Recent diversified Gram-based methods have been able to produce multiple and diverse stylized outputs for the same content and style images. However, as another widespread research interest, the diversity of patch-based methods remains challenging due to the stereotyped style swapping process based on nearest patch matching. To resolve this dilemma, in this paper, we dive into the crux of existing patch-based methods and propose a universal and efficient module, termed DivSwapper, for diversified patch-based arbitrary style transfer. The key insight is to use an essential intuition that neural patches with higher activation values could contribute more to diversity. Our DivSwapper is plug-and-play and can be easily integrated into existing patch-based and Gram-based methods to generate diverse results for arbitrary styles. We conduct theoretical analyses and extensive experiments to demonstrate the effectiveness of our method, and compared with state-of-the-art algorithms, it shows superiority in diversity, quality, and efficiency., Comment: Accepted by IJCAI 2022 (AI, Arts & Creativity Track)

Tao Wang,1,* Haibo Chen,2,* Shuyun Xia,3 Xiaofang Chen,1 Hu Sun,1 Zhixin Xu1 1Department of Anesthesiology, the Second Affiliated Hospital of Hainan Medical University, Haikou, Hainan, 570311, People’s Republic of China; 2Department of Blood Transfusion, the Second Affiliated Hospital of Hainan Medical University, Haikou, Hainan, 570311, People’s Republic of China; 3Department of Respiratory Medicine, Pingdu People’s Hospital, Pingdu, Shandong, 266700, People’s Republic of China*These authors contributed equally to this workCorrespondence: Zhixin XuThe Second Affiliated Hospital of Hainan Medical University, 368 Yehai Av, Haikou, Hainan, 570311, People’s Republic of ChinaEmail xuzhix2011@163.comBackground: Gastrodia elata Blume (Orchidaceae) is a widely used traditional Chinese herbal medicine in the clinical practice of China, to treat nervous headache, convulsions, dizziness, neurasthenia, and so on. Parishin C (Par C), one of the major bioactive components of Gastrodia elata Blume, is known to exert many different biological activities, including antipsychotic and neuroprotective effects. However, there is little research about its neuroprotective effect in an ischemic stroke model. The objective of the present study is thus to investigate the neuroprotective effects of Par C against cerebral ischemia damage.Methods: Rats were pretreated with Par C (25, 50, or 100 mg/kg/day, i.p.) for 21 days, then subjected to 2 h of middle cerebral artery occlusion (MCAO) and 22 h of reperfusion. Neurological deficient scores, brain water content, histopathology, TCC staining were performed to assess the neuroprotective effects of Par C. Meanwhile, the oxidative stress, inflammation and apoptosis-related markers of brain tissue were evaluated by corresponding assay kits. Besides, the antioxidant and pro-inflammatory expression was measured by real-time quantification PCR (RT-qPCR).Results: Our findings indicated that the pre-tre

Multimodal image-to-image translation (I2IT) aims to learn a conditional distribution that explores multiple possible images in the target domain given an input image in the source domain. Conditional generative adversarial networks (cGANs) are often adopted for modeling such a conditional distribution. However, cGANs are prone to ignore the latent code and learn a unimodal distribution in conditional image synthesis, which is also known as the mode collapse issue of GANs. To solve the problem, we propose a simple yet effective method that explicitly estimates and maximizes the mutual information between the latent code and the output image in cGANs by using a deep mutual information neural estimator in this paper. Maximizing the mutual information strengthens the statistical dependency between the latent code and the output image, which prevents the generator from ignoring the latent code and encourages cGANs to fully utilize the latent code for synthesizing diverse results. Our method not only provides a new perspective from information theory to improve diversity for I2IT but also achieves disentanglement between the source domain content and the target domain style for free.

Random testing (RT) is a well-studied testing method that has been widely applied to the testing of many applications, including embedded software systems, SQL database systems, and Android applications. Adaptive random testing (ART) aims to enhance RT's failure-detection ability by more evenly spreading the test cases over the input domain. Since its introduction in 2001, there have been many contributions to the development of ART, including various approaches, implementations, assessment and evaluation methods, and applications. This paper provides a comprehensive survey on ART, classifying techniques, summarizing application areas, and analyzing experimental evaluations. This paper also addresses some misconceptions about ART, and identifies open research challenges to be further investigated in the future work.

A method is presented for the real-time optimal control of the journey of a truck, travelling between a pair of pick-up/drop-off locations in a time-varying traffic network, in order to reduce fuel consumption. The method, when applied during the journey, encapsulates the choice of route, choice of speeds on the links, and choice of stop locations/durations; when applied pre-trip, it additionally incorporates choice of departure time. The problem is formulated by using a modified form of space-time extended network, in such a way that a shortest path in this network corresponds to an optimal choice of not only route, stops and (when relevant) departure time, but also of speeds. A series of simple illustrative examples are presented to illustrate the formulation. Finally, the method is applied to a realistic-size case study.

Brain computer interface (BCI) has been popular as a key approach to monitor our brains recent year. Mental states monitoring is one of the most important BCI applications and becomes increasingly accessible. However, the mental state prediction accuracy and generality through encephalogram (EEG) are not good enough for everyday use. Here in this paper we present a deep learning-based EEG decoding method to read mental states. We propose a novel 1D convolutional neural network with different filter lengths to capture different frequency bands information. To improve the prediction accuracy, we also used a resnet-like structure to train a relatively deep convolutional neural network to promote feature extraction. Compared with traditional ways of predictions such as KNN and SVM, we achieved a significantly better result with an accuracy of 96.40%. Also, in contrast with some already published open source deep neural network structures, our methods achieved the state of art prediction accuracy on a mental state recognition dataset. Our results demonstrate using only 1D convolution could extract the features of EEG and the possibility of mental state prediction using portable EEG devices., Comment: 5 pages, 2 figures, published in AIIPCC 2019

Image style transfer is an underdetermined problem, where a large number of solutions can satisfy the same constraint (the content and style). Although there have been some efforts to improve the diversity of style transfer by introducing an alternative diversity loss, they have restricted generalization, limited diversity and poor scalability. In this paper, we tackle these limitations and propose a simple yet effective method for diversified arbitrary style transfer. The key idea of our method is an operation called deep feature perturbation (DFP), which uses an orthogonal random noise matrix to perturb the deep image feature maps while keeping the original style information unchanged. Our DFP operation can be easily integrated into many existing WCT (whitening and coloring transform)-based methods, and empower them to generate diverse results for arbitrary styles. Experimental results demonstrate that this learning-free and universal method can greatly increase the diversity while maintaining the quality of stylization., Comment: Accepted by CVPR2020

With the rapid development of deep learning algorithms, action recognition in video has achieved many important research results. One issue in action recognition, Zero-Shot Action Recognition (ZSAR), has recently attracted considerable attention, which classify new categories without any positive examples. Another difficulty in action recognition is that untrimmed data may seriously affect model performance. We propose a composite two-stream framework with a pre-trained model. Our proposed framework includes a classifier branch and a composite feature branch. The graph network model is adopted in each of the two branches, which effectively improves the feature extraction and reasoning ability of the framework. In the composite feature branch, a 3-channel self-attention models are constructed to weight each frame in the video and give more attention to the key frames. Each self-attention models channel outputs a set of attention weights to focus on a particular aspect of the video, and a set of attention weights corresponds to a one-dimensional vector. The 3-channel self-attention models can evaluate key frames from multiple aspects, and the output sets of attention weight vectors form an attention matrix, which effectively enhances the attention of key frames with strong correlation of action. This model can implement action recognition under zero-shot conditions, and has good recognition performance for untrimmed video data. Experimental results on relevant data sets confirm the validity of our model., Comment: Accepted to ACPR 2019

In recent years, Raft has overtaken Paxos as the consensus algorithm of choice. [53] While many have pointed out similarities between the two protocols, no one has formally mapped out their relationships. In this paper, we show how Raft and Paxos are formally related despite their surface differences. Based on the formal mapping between the two protocols, we show how to automatically port a certain class of optimizations from Paxos to Raft with guaranteed correctness. As case studies, we port and evaluate two optimizations, Mencius and Paxos Quorum Lease to Raft.

Millions of people with severe speech disorders around the world may regain their communication capabilities through techniques of silent speech recognition (SSR). Using electroencephalography (EEG) as a biomarker for speech decoding has been popular for SSR. However, the lack of SSR text corpus has impeded the development of this technique. Here, we construct a novel task-oriented text corpus, which is utilized in the field of SSR. In the process of construction, we propose a task-oriented hybrid construction method based on natural language generation algorithm. The algorithm focuses on the strategy of data-to-text generation, and has two advantages including linguistic quality and high diversity. These two advantages use template-based method and deep neural networks respectively. In an SSR experiment with the generated text corpus, analysis results show that the performance of our hybrid construction method outperforms the pure method such as template-based natural language generation or neural natural language generation models., Comment: Accepted for publication in the 3rd International Conference on Natural Language Processing and Information Retrieval, 2019

The recent proposal of learned index structures opens up a new perspective on how traditional range indexes can be optimized. However, the current learned indexes assume the data distribution is relatively static and the access pattern is uniform, while real-world scenarios consist of skew query distribution and evolving data. In this paper, we demonstrate that the missing consideration of access patterns and dynamic data distribution notably hinders the applicability of learned indexes. To this end, we propose solutions for learned indexes for dynamic workloads (called Doraemon). To improve the latency for skew queries, Doraemon augments the training data with access frequencies. To address the slow model re-training when data distribution shifts, Doraemon caches the previously-trained models and incrementally fine-tunes them for similar access patterns and data distribution. Our preliminary result shows that, Doraemon improves the query latency by 45.1% and reduces the model re-training time to 1/20.

Decentralized Internet is booming. People are fascinated by its promise that users can truly own their data. However, in a decentralized Internet, completing a task usually involves multiple nodes with mutual distrust. Such distrust might eventually become a major obstacle for the growth of the decentralized Internet. In this paper, we analyze the distrust using a simple model and highlight the properties required to faithfully accomplish one task in a decentralized Internet. We also introduce our draft solution -- PIXIU, a framework to mitigate the distrust among different nodes. In PIXIU, we design and utilize trust-{\lambda} and decentralized executor to achieve the above-needed properties.

This study investigates the transmission coefficient of coupled beam structure which has been widely used in engineering problems. Although the power flow is continuous at the coupled point, the waveform and energy density often show sudden changes. These changes can be utilized to create an understanding of the system. By treating the two-beam coupled structure as two infinite beams and considering the coupling between the bending wave and the torsion one, the conversion of wave types at the coupled interface is discussed. Further, the transmission coefficient is also computed. Furthermore, investigate the effects of coupling angle, beam height and the excitation frequency of incident wave on the conversion of wave type and energy transmission. Numerical results indicate that the coupling angle and beam height have great influences on the conversion of wave type. The component of torsion wave grows with the excitation frequency and cannot be ignored in high frequencies.

The wind induced responses of transmission tower line system are studied by finite element method. Firstly, a slip model considering eccentricity and bolt joint slippage in diagonal bracings, tower legs and tower head is built by ANSYS. The slip model has a more accurate result compared with conventional models. Secondly, the finite element models of tower line systems are established and the wind speed time histories are simulated using MATLAB. Finally, the wind induced responses of different tower line systems are studied. The results of a single tower and the tower line systems are compared to study the effects of tower-line coupling effects and bolt slippage on wind induced responses of transmission tower line systems.

The thermo-elastic vibration response of simple supported axially moving Euler beam is investigated. The differential equation of moving beam is established by recourse to Hamilton principle and the thermal effects is considered by introducing the equivalent thermal bending moment. A 2-D transient temperature field is calculated by the alternating-directional implicit (ADI) method and the equivalent thermal moment is calculated numerically. The dimensionless equation is discretized by Galerkin method and the modal analysis of gyroscopic system is used to calculate the forced vibration response. The time-history curve of the beam’s upper middle point is obtained for thermal or non-thermal situations.

An optimization based on sequential quadratic programming (SQP) algorithm to increase the thermal insulation and sound transmission loss of honeycomb panel in thermal environments is presented. First, heat transfer analysis is performed to reveal the steady-state thermal performance of hexagonal aluminum honeycomb sandwich panel, by using the semi-empirical Swann and Pittman formula. Next, the influences of temperature on acoustic performance of honeycomb panel based on statistical energy analysis method (SEA) is performed. Results show that increasing the thickness of the honeycomb core can improve the acoustic performance and heat insulation behavior.

Fast, byte-addressable non-volatile memory (NVM) embraces both near-DRAM latency and disk-like persistence, which has generated considerable interests to revolutionize system software stack and programming models. However, it is less understood how NVM can be combined with managed runtime like Java virtual machine (JVM) to ease persistence management. This paper proposes Espresso, a holistic extension to Java and its runtime, to enable Java programmers to exploit NVM for persistence management with high performance. Espresso first provides a general persistent heap design called Persistent Java Heap (PJH) to manage persistent data as normal Java objects. The heap is then strengthened with a recoverable mechanism to provide crash consistency for heap metadata. It then provides a new abstraction called Persistent Java Object (PJO) to provide an easy-to-use but safe persistent programming model for programmers to persist application data. The evaluation confirms that Espresso significantly outperforms state-of-art NVM support for Java (i.e., JPA and PCJ) while being compatible to existing data structures in Java programs.

Recently, deep learning techniques have enjoyed success in various multimedia applications, such as image classification and multi-modal data analysis. Large deep learning models are developed for learning rich representations of complex data. There are two challenges to overcome before deep learning can be widely adopted in multimedia and other applications. One is usability, namely the implementation of different models and training algorithms must be done by non-experts without much effort especially when the model is large and complex. The other is scalability, that is the deep learning system must be able to provision for a huge demand of computing resources for training large models with massive datasets. To address these two challenges, in this paper, we design a distributed deep learning platform called SINGA which has an intuitive programming model based on the common layer abstraction of deep learning models. Good scalability is achieved through flexible distributed training architecture and specific optimization techniques. SINGA runs on GPUs as well as on CPUs, and we show that it outperforms many other state-of-the-art deep learning systems. Our experience with developing and training deep learning models for real-life multimedia applications in SINGA shows that the platform is both usable and scalable., Comment: submitted to TOMM (under review)

In this paper, we present a novel vision of large scale of empirical password sets available and improve the understanding of passwords by revealing their interconnections and considering the security on a level of the whole password set instead of one single password level. Through the visualization of Yahoo, Phpbb, 12306, etc. we, for the first time, show what the spatial structure of empirical password sets are like and take the community and clustering patterns of the passwords into account to shed lights on the definition of popularity of a password based on their frequency and degree separately. Furthermore, we propose a model of statistical guessing attack from the perspective of the data's topological space, which provide an explanation of the "cracking curve". We also give a lower bound of the minimum size of the dictionary needed to compromise arbitrary ratio of any given password set by proving that it is equivalent to the minimum dominating set problem, which is a NP-complete problem. Hence the minimal dictionary problem is also NP-complete., Comment: 9 pages, 14 figures

Jiali Cheng,1,* Xin Sun,1,2,* Shuyuan Guo,1,* Wei Cao,1 Haibo Chen,1 Yinghua Jin,1 Bo Li,1 Qiannan Li,1 Huan Wang,1 Zhu Wang,3 Qi Zhou,3 Peng Wang,3 Zhiguo Zhang,3 Wenwu Cao,3,4 Ye Tian1,21Division of Cardiology, the First Affiliated Hospital, Cardiovascular Institute, Harbin Medical University, Harbin, People’s Republic of China; 2Division of Pathophysiology, the State-Province Key Laboratories of Biomedicine-Pharmaceutics of China, Key Laboratory of Cardiovascular Research, Ministry of Education, Harbin, People’s Republic of China; 3Laboratory of Photo- and Sono-theranostic Technologies and Condensed Matter Science and Technology Institute, Harbin Institute of Technology, Harbin, People’s Republic of China; 4Materials Research Institute, The Pennsylvania State University, University Park, PA, USA*These authors contributed equally to this workBackground: Inflammatory cells exhibit an elevated level of protoporphyrin IX (PpIX) after the administration of 5-aminolevulinic acid (ALA). Here, we investigate the sonodynamic effects of ALA-derived PpIX (ALA-PpIX) on macrophages, which are the pivotal inflammatory cells in atherosclerosis.Methods and results: Cultured THP-1 macrophages were incubated with ALA. Fluorescence microscope and fluorescence spectrometer detection showed that intracellular PpIX increased with the concentration of ALA in the incubation solution in a time dependent manner; the highest level of intracellular PpIX was observed after 3-hour incubation. 3-[4,5-dimethylthiazol-2-yl]-2,5-diphenyltetrazolium bromide assays demonstrated that lower concentrations (less than 2 mM) of ALA have no influence on cell viability (more than 90% of cells survived), but sonodynamic therapy (SDT) with a low concentration of ALA significantly decreased the survival rate of cells, and the effect was increased with both ALA concentration and ultrasound exposure time. Cell apoptosis and necrosis induced by ALA-mediated SDT (ALA-SDT) were measu

Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Nuclear Engineering, February 2005., Includes bibliographical references (leaf 102)., This work developed an approach to diagnose problems and identify good practices in the operation of nuclear power plants using the system dynamics technique. The research began with construction of the ORSIM (Nuclear Power Plant Operations and Risk Simulator) model, with its operational component modified from an existing model, and its risk component newly created in this research. A matrix of high-level performance indices was also created to measure plant performance as a function of continuous operation. The research continued with development of an interface program to provide a user-friendly environment, and then culminated with a report of the results obtained from a pilot project, and a demonstration of using ORSIM to investigate EPRI (Electric Power Research Institute) good practices. Both problem diagnosis and policy investigations were conducted in the pilot project. It was found that the performance matrix developed in this work was able to measure stability, reliability, and economic performance in a concise and clear manner. With this matrix, ORSIM was able to pinpoint bottlenecks of current operations and to project into the future what would be the implications of various policy changes., (cont.) It was also found that the tracking capability of ORSIM makes it easy to locate the root causes of problems and aids in identifying places where operational improvements might be implemented. In the EPRI good practices investigation, it was demonstrated that ORSIM is a good tool that assists plant managers in evaluating the benefits and risks of applying new practices. The pilot project and EPRI practices study showed that ORSIM is a good tool for plant managers to identify potential problems and to better understand the implications of their policy changes. It therefore can help improve the quality of decision-making and help achieve more stable, reliable, and economic operations of nuclear power plants., by Haibo Chen., Ph.D.

Random testing (RT) is a well-studied testing method that has been widely applied to the testing of many applications, including embedded software systems, SQL database systems, and Android applications. Adaptive random testing (ART) aims to enhance RT's failure-detection ability by more evenly spreading the test cases over the input domain. Since its introduction in 2001, there have been many contributions to the development of ART, including various approaches, implementations, assessment and evaluation methods, and applications. This paper provides a comprehensive survey on ART, classifying techniques, summarizing application areas, and analyzing experimental evaluations. This paper also addresses some misconceptions about ART, and identifies open research challenges to be further investigated in the future work.

Random testing (RT) is a well-studied testing method that has been widely applied to the testing of many applications, including embedded software systems, SQL database systems, and Android applications. Adaptive random testing (ART) aims to enhance RT's failure-detection ability by more evenly spreading the test cases over the input domain. Since its introduction in 2001, there have been many contributions to the development of ART, including various approaches, implementations, assessment and evaluation methods, and applications. This paper provides a comprehensive survey on ART, classifying techniques, summarizing application areas, and analyzing experimental evaluations. This paper also addresses some misconceptions about ART, and identifies open research challenges to be further investigated in the future work.