Search

Multimodal sentiment analysis aims to learn representations from different modalities to identify human emotions. However, existing works often neglect the frame-level redundancy inherent in continuous time series, resulting in incomplete modality representations with noise. To address this issue, we propose temporal-invariant learning for the first time, which constrains the distributional variations over time steps to effectively capture long-term temporal dynamics, thus enhancing the quality of the representations and the robustness of the model. To fully exploit the rich semantic information in textual knowledge, we propose a semantic-guided fusion module. By evaluating the correlations between different modalities, this module facilitates cross-modal interactions gated by modality-invariant representations. Furthermore, we introduce a modality discriminator to disentangle modality-invariant and modality-specific subspaces. Experimental results on two public datasets demonstrate the superiority of our model. Our code is available at https://github.com/X-G-Y/SATI., Comment: change Title, Authors, Abstract

The SuperKEKB/Belle II experiment aims to collect high-statistics data of B meson pairs to explore new physics beyond the Standard Model (SM). SuperKEKB, an upgraded version of the KEKB accelerator, has achieved a world-record luminosity of $4.71 \times 10^{34} \, \mathrm{cm^{-2}s^{-1}}$ in 2022 but continues to strive for higher luminosities. One of the major obstacles is Sudden Beam Loss (SBL) events, which cause substantial beam losses and damage to the Belle~II detector. To find a hint for addressing SBL challenges, advanced beam diagnostic systems and enhanced beam abort systems have been developed. The diagnostic system aims to accurately pinpoint the start of beam losses, while the upgraded abort system quickly disposes of anomalous beams to minimize damage. This paper details the development and implementation of these systems, including high-speed loss monitors, time synchronization with the White Rabbit system, and data acquisition systems. Efforts to understand the mechanisms of SBL events, using acoustic sensors to detect discharges, are also discussed. These measures aim to improve the operational stability and luminosity of SuperKEKB, contributing to the experiment's success., Comment: 17 pages, 25 figures

Traditional approaches to estimating beta in finance often involve rigid assumptions and fail to adequately capture beta dynamics, limiting their effectiveness in use cases like hedging. To address these limitations, we have developed a novel method using neural networks called NeuralBeta, which is capable of handling both univariate and multivariate scenarios and tracking the dynamic behavior of beta. To address the issue of interpretability, we introduce a new output layer inspired by regularized weighted linear regression, which provides transparency into the model's decision-making process. We conducted extensive experiments on both synthetic and market data, demonstrating NeuralBeta's superior performance compared to benchmark methods across various scenarios, especially instances where beta is highly time-varying, e.g., during regime shifts in the market. This model not only represents an advancement in the field of beta estimation, but also shows potential for applications in other financial contexts that assume linear relationships., Comment: 8 pages, 9 figures

JavaScript packages are notoriously prone to bloat, a factor that significantly impacts the performance and maintainability of web applications. While web bundlers and tree-shaking can mitigate this issue in client-side applications at the function level, they cannot effectively detect and remove bloat in server-side applications. In this paper, we conduct an empirical study to investigate the bloated dependencies that are entirely unused within server-side applications. Our study focuses on applications built with the widely used and highly dynamic CommonJS module system. We propose a trace-based dynamic analysis that monitors file access, to determine which dependencies are not accessed during runtime. To conduct our study, we curate an original dataset of 92 CommonJS packages with a median test coverage of 96.9% and a total of 50,661 dependencies. Our dynamic analysis identifies and successfully removes 50.7% of these dependencies while maintaining the correct build of all packages. Furthermore, we find that 14.9% of directly used dependencies and 51.3% of indirect dependencies are bloated. A key insight is that focusing on removing only the direct bloated dependencies by cleaning the package.json file, also removes a significant share of unnecessary bloated indirect dependencies. Compared to the state-of-the-art dynamic debloating technique, our analysis based on file accesses has fewer false positives, and demonstrates higher accuracy in detecting bloated dependencies. Our findings suggest that native support for dependency debloating in package managers could significantly alleviate the burden of maintaining dependencies., Comment: Manuscript submitted to Empirical Software Engineering (EMSE)

The Event Horizon Telescope (EHT) has revolutionized our ability to study black holes by providing unprecedented spatial resolution and unveiling horizon-scale details. With advancements leading to the next-generation EHT, there is potential to probe even deeper into the black hole's dark region, especially the inner shadow characterized by low-intensity foreground emissions from the jet, thanks to a significant enhancement in dynamic range by two orders of magnitude. We demonstrate how such enhanced observations could transform supermassive black holes into powerful probes for detecting annihilating dark matter, which can form a dense profile in the vicinity of supermassive black holes, by examining the morphology of the black hole image., Comment: 19 pages, 6 figures, references updated

The recent detection of gravitational waves from a binary merger involving a potential low-mass gap black hole (LMBH) by LIGO-Virgo-KAGRA (LVK) Collaboration motivates investigations into mechanisms beyond conventional stellar evolution theories to account for their existence. We study a mechanism in which dark matter (DM), through its capture and accumulation inside main sequence stars, induces the formation of black holes within the mass range of $[3, 5]M_\odot$. We examine the distribution of these LMBHs as a function of galaxy halo mass, particularly when paired with neutron stars. This gives a distinct signature that can be tested with future gravitational wave observations. We find that a viable portion of the DM parameter space predicts a merger rate of such binaries consistent with LVK observations., Comment: 8 pages for main text, 7 pages for method, 3 figures

As the number of IoT devices increases, security concerns become more prominent. The impact of threats can be minimized by deploying Network Intrusion Detection System (NIDS) by monitoring network traffic, detecting and discovering intrusions, and issuing security alerts promptly. Most intrusion detection research in recent years has been directed towards the pair of traffic itself without considering the interrelationships among them, thus limiting the monitoring of complex IoT network attack events. Besides, anomalous traffic in real networks accounts for only a small fraction, which leads to a severe imbalance problem in the dataset that makes algorithmic learning and prediction extremely difficult. In this paper, we propose an EG-ConMix method based on E-GraphSAGE, incorporating a data augmentation module to fix the problem of data imbalance. In addition, we incorporate contrastive learning to discern the difference between normal and malicious traffic samples, facilitating the extraction of key features. Extensive experiments on two publicly available datasets demonstrate the superior intrusion detection performance of EG-ConMix compared to state-of-the-art methods. Remarkably, it exhibits significant advantages in terms of training speed and accuracy for large-scale graphs.

Dark photons, aside from constituting non-relativistic dark matter, can also be generated relativistically through the decay or annihilation of other dark matter candidates, contributing to a galactic dark photon background. The production of dark photons tends to favor specific polarization modes, determined by the microscopic coupling between dark matter and dark photons. We leverage data obtained from previous searches for dark photon dark matter using a superconducting radio-frequency cavity to explore galactic dark photon fluxes. The interplay of anisotropic directions and Earth's rotation introduces a diurnal modulation of signals within the cavities, manifesting distinct variation patterns for longitudinal and transverse modes. Our findings highlight the efficacy of superconducting radio-frequency cavities, characterized by significantly high-quality factors, as powerful telescopes for detecting galactic dark photons, unveiling a novel avenue in the indirect search for dark matter through multi-messenger astronomy., Comment: 16 pages, 3 figures

Generating fake data is an essential dimension of modern software testing, as demonstrated by the number and significance of data faking libraries. Yet, developers of faking libraries cannot keep up with the wide range of data to be generated for different natural languages and domains. In this paper, we assess the ability of generative AI for generating test data in different domains. We design three types of prompts for Large Language Models (LLMs), which perform test data generation tasks at different levels of integrability: 1) raw test data generation, 2) synthesizing programs in a specific language that generate useful test data, and 3) producing programs that use state-of-the-art faker libraries. We evaluate our approach by prompting LLMs to generate test data for 11 domains. The results show that LLMs can successfully generate realistic test data generators in a wide range of domains at all three levels of integrability.

In continual learning, a learner has to keep learning from the data over its whole life time. A key issue is to decide what knowledge to keep and what knowledge to let go. In a neural network, this can be implemented by using a step-size vector to scale how much gradient samples change network weights. Common algorithms, like RMSProp and Adam, use heuristics, specifically normalization, to adapt this step-size vector. In this paper, we show that those heuristics ignore the effect of their adaptation on the overall objective function, for example by moving the step-size vector away from better step-size vectors. On the other hand, stochastic meta-gradient descent algorithms, like IDBD (Sutton, 1992), explicitly optimize the step-size vector with respect to the overall objective function. On simple problems, we show that IDBD is able to consistently improve step-size vectors, where RMSProp and Adam do not. We explain the differences between the two approaches and their respective limitations. We conclude by suggesting that combining both approaches could be a promising future direction to improve the performance of neural networks in continual learning.

This paper introduces a novel approach to synthesize texture to dress up a given 3D object, given a text prompt. Based on the pretrained text-to-image (T2I) diffusion model, existing methods usually employ a project-and-inpaint approach, in which a view of the given object is first generated and warped to another view for inpainting. But it tends to generate inconsistent texture due to the asynchronous diffusion of multiple views. We believe such asynchronous diffusion and insufficient information sharing among views are the root causes of the inconsistent artifact. In this paper, we propose a synchronized multi-view diffusion approach that allows the diffusion processes from different views to reach a consensus of the generated content early in the process, and hence ensures the texture consistency. To synchronize the diffusion, we share the denoised content among different views in each denoising step, specifically blending the latent content in the texture domain from views with overlap. Our method demonstrates superior performance in generating consistent, seamless, highly detailed textures, comparing to state-of-the-art methods.

Computer Aided Design (CAD), especially the feature-based parametric CAD, plays an important role in modern industry and society. However, the reconstruction of featured CAD model is more challenging than the reconstruction of other CAD models. To this end, this paper proposes an end-to-end network to reconstruct featured CAD model from point cloud (P2CADNet). Initially, the proposed P2CADNet architecture combines a point cloud feature extractor, a CAD sequence reconstructor and a parameter optimizer. Subsequently, in order to reconstruct the featured CAD model in an autoregressive way, the CAD sequence reconstructor applies two transformer decoders, one with target mask and the other without mask. Finally, for predicting parameters more precisely, we design a parameter optimizer with cross-attention mechanism to further refine the CAD feature parameters. We evaluate P2CADNet on the public dataset, and the experimental results show that P2CADNet has excellent reconstruction quality and accuracy. To our best knowledge, P2CADNet is the first end-to-end network to reconstruct featured CAD model from point cloud, and can be regarded as baseline for future works. Therefore, we open the source code at https://github.com/Blice0415/P2CADNet.

Electromagnetic resonant systems, such as cavities or LC circuits, have emerged as powerful detectors for probing ultralight boson dark matter and high-frequency gravitational waves. However, the limited resonant bandwidth of conventional single-mode resonators, imposed by quantum fluctuations, necessitates numerous scan steps to cover broad unexplored frequency regions. The incorporation of multiple auxiliary modes can realize a broadband detector while maintaining a substantial signal response. The broadened sensitive width can be on the same order as the resonant frequency, encompassing several orders of the source frequency for heterodyne detection, where a background cavity mode transitions into another. Consequently, our approach enables significantly deeper exploration of the parameter space within the same integration time compared to single-mode detection., Comment: 18 pages, 6 figures

The global spin alignment of the vector meson has been observed in relativistic heavy ion collisions, but is still on hot debates in the theoretical community. Here we propose to apply the light front framework to explain this phenomenon since the light front form explicitly describes the hadron spin including both the quark spin and the orbital angular momentum. After applying the light front spinor, we find that the spin alignment in the polarization of vector mesons with $\rho_{00}>1/3$ can be naturally manifested and in particular, the obtained spin alignment for $\phi$ meson is in good agreement with the experimental data. This implies that to explain the spin alignment it is important to properly include the contribution from the gluon interactions that are presented in terms of the orbital angular momentum of the hadron bound state., Comment: 7 pages, 2 figures, matched to the published version

Creating a vivid video from the event or scenario in our imagination is a truly fascinating experience. Recent advancements in text-to-video synthesis have unveiled the potential to achieve this with prompts only. While text is convenient in conveying the overall scene context, it may be insufficient to control precisely. In this paper, we explore customized video generation by utilizing text as context description and motion structure (e.g. frame-wise depth) as concrete guidance. Our method, dubbed Make-Your-Video, involves joint-conditional video generation using a Latent Diffusion Model that is pre-trained for still image synthesis and then promoted for video generation with the introduction of temporal modules. This two-stage learning scheme not only reduces the computing resources required, but also improves the performance by transferring the rich concepts available in image datasets solely into video generation. Moreover, we use a simple yet effective causal attention mask strategy to enable longer video synthesis, which mitigates the potential quality degradation effectively. Experimental results show the superiority of our method over existing baselines, particularly in terms of temporal coherence and fidelity to users' guidance. In addition, our model enables several intriguing applications that demonstrate potential for practical usage., Comment: 13 pages, 8 figures. Project page: https://doubiiu.github.io/projects/Make-Your-Video/

Reinforcement learning (RL) has been widely used in text generation to alleviate the exposure bias issue or to utilize non-parallel datasets. The reward function plays an important role in making RL training successful. However, previous reward functions are typically task-specific and sparse, restricting the use of RL. In our work, we propose a task-agnostic approach that derives a step-wise reward function directly from a model trained with teacher forcing. We additionally propose a simple modification to stabilize the RL training on non-parallel datasets with our induced reward function. Empirical results show that our method outperforms self-training and reward regression methods on several text generation tasks, confirming the effectiveness of our reward function., Comment: Accepted at NeurIPS 2022

In the age of big data, the demand for hidden information mining in technological intellectual property is increasing in discrete countries. Definitely, a considerable number of graph learning algorithms for technological intellectual property have been proposed. The goal is to model the technological intellectual property entities and their relationships through the graph structure and use the neural network algorithm to extract the hidden structure information in the graph. However, most of the existing graph learning algorithms merely focus on the information mining of binary relations in technological intellectual property, ignoring the higherorder information hidden in non-binary relations. Therefore, a hypergraph neural network model based on dual channel convolution is proposed. For the hypergraph constructed from technological intellectual property data, the hypergraph channel and the line expanded graph channel of the hypergraph are used to learn the hypergraph, and the attention mechanism is introduced to adaptively fuse the output representations of the two channels. The proposed model outperforms the existing approaches on a variety of datasets.

To improve the overall performance of processors, computer architects use various performance optimization techniques in modern processors, such as speculative execution, branch prediction, and chaotic execution. Both now and in the future, these optimization techniques are critical for improving the execution speed of processor instructions. However, researchers have discovered that these techniques introduce hidden inherent security flaws, such as meltdown and ghost attacks in recent years. They exploit techniques such as chaotic execution or speculative execution combined with cache-based side-channel attacks to leak protected data. The impact of these vulnerabilities is enormous because they are prevalent in existing or future processors. However, until today, meltdown and ghost have not been effectively addressed, but instead, multiple attack variants and different attack implementations have evolved from them. This paper proposes to optimize four different hardware performance events through feature selection and use machine learning algorithms to build a real-time detection mechanism for Spectre v1,v2,v4, and different implementations of meltdown attacks, ultimately achieving an accuracy rate of over 99\%. In order to verify the practicality of the attack detection model, this paper is tested with a variety of benign programs and different implementations of Spectre attacks different from the modeling process, and the absolute accuracy also exceeds 99\%, showing that this paper can cope with different attack variants and different implementations of the same attack that may occur daily.