Search

Semantic relevance calculation is crucial for e-commerce search engines, as it ensures that the items selected closely align with customer intent. Inadequate attention to this aspect can detrimentally affect user experience and engagement. Traditional text-matching techniques are prevalent but often fail to capture the nuances of search intent accurately, so neural networks now have become a preferred solution to processing such complex text matching. Existing methods predominantly employ representation-based architectures, which strike a balance between high traffic capacity and low latency. However, they exhibit significant shortcomings in generalization and robustness when compared to interaction-based architectures. In this work, we introduce a robust interaction-based modeling paradigm to address these shortcomings. It encompasses 1) a dynamic length representation scheme for expedited inference, 2) a professional terms recognition method to identify subjects and core attributes from complex sentence structures, and 3) a contrastive adversarial training protocol to bolster the model's robustness and matching capabilities. Extensive offline evaluations demonstrate the superior robustness and effectiveness of our approach, and online A/B testing confirms its ability to improve relevance in the same exposure position, resulting in more clicks and conversions. To the best of our knowledge, this method is the first interaction-based approach for large e-commerce search relevance calculation. Notably, we have deployed it for the entire search traffic on alibaba.com, the largest B2B e-commerce platform in the world., Comment: Accepted by ECML-PKDD'24 as Outstanding Paper. 8 pages, 2 figures, 7 tables

The cosmological event horizons are observer-dependent, which might bring a paradox. As an example, in dS$_{2}$ multiverse model there are entanglement islands in crunching regions encoding the information of regions near future infinity of inflating or Minkowski bubbles, however, for two observers in different bubbles, since their island regions overlap, both observers will be able to get access to the information encoded in the overlapping region, indicating a violation of no-cloning theorem. In this paper, we present a different resolution to this paradox. Based on the Petz $\mathrm{R\acute{e}nyi}$ mutual information, we show that besides the quantum extremal surfaces there might be another boundary for the island in corresponding spacetime so that the island regions are bounded by ``division points" rather than extending to the rest of the entire spacetime. We also discuss the implications of our result., Comment: 23 pages, 8 figures

This work proposes a novel approach to bolster both the robot's risk assessment and safety measures while deepening its understanding of 3D scenes, which is achieved by leveraging Radiance Field (RF) models and 3D Gaussian Splatting. To further enhance these capabilities, we incorporate additional sampled views from the environment with the RF model. One of our key contributions is the introduction of Risk-aware Environment Masking (RaEM), which prioritizes crucial information by selecting the next-best-view that maximizes the expected information gain. This targeted approach aims to minimize uncertainties surrounding the robot's path and enhance the safety of its navigation. Our method offers a dual benefit: improved robot safety and increased efficiency in risk-aware 3D scene reconstruction and understanding. Extensive experiments in real-world scenarios demonstrate the effectiveness of our proposed approach, highlighting its potential to establish a robust and safety-focused framework for active robot exploration and 3D scene understanding.

We investigate theoretically tunable non-Hermitian skin effect in systems with gain and loss, and find that bipolar (quadripolar) non-Hermitian skin effect characterized by topological invariants in one (two)-dimensional system. We also find the partial non-Hermitian skin effect with the coexistence of localized states and extended states. Both types of the non-Hermitian skin effect have not yet been predicted together in a single system. A feasible experimental scheme of our model is proposed to realize in electric circuits. Our investigation unveils a new type of non-Hermitian skin effect and enhance the tunability of the non-Hermitian systems by gain and loss other than the conventional non-reciprocal hopping., Comment: 7 pages, 6 figures

Existing Neural Machine Translation (NMT) models mainly handle translation in the general domain, while overlooking domains with special writing formulas, such as e-commerce and legal documents. Taking e-commerce as an example, the texts usually include amounts of domain-related words and have more grammar problems, which leads to inferior performances of current NMT methods. To address these problems, we collect two domain-related resources, including a set of term pairs (aligned Chinese-English bilingual terms) and a parallel corpus annotated for the e-commerce domain. Furthermore, we propose a two-step fine-tuning paradigm (named G2ST) with self-contrastive semantic enhancement to transfer one general NMT model to the specialized NMT model for e-commerce. The paradigm can be used for the NMT models based on Large language models (LLMs). Extensive evaluations on real e-commerce titles demonstrate the superior translation quality and robustness of our G2ST approach, as compared with state-of-the-art NMT models such as LLaMA, Qwen, GPT-3.5, and even GPT-4., Comment: 4 pages, 1 figure, WWW2024 accepted

Recommender systems have made significant strides in various industries, primarily driven by extensive efforts to enhance recommendation accuracy. However, this pursuit of accuracy has inadvertently given rise to echo chamber/filter bubble effects. Especially in industry, it could impair user's experiences and prevent user from accessing a wider range of items. One of the solutions is to take diversity into account. However, most of existing works focus on user's explicit preferences, while rarely exploring user's non-interaction preferences. These neglected non-interaction preferences are especially important for broadening user's interests in alleviating echo chamber/filter bubble effects.Therefore, in this paper, we first define diversity as two distinct definitions, i.e., user-explicit diversity (U-diversity) and user-item non-interaction diversity (N-diversity) based on user historical behaviors. Then, we propose a succinct and effective method, named as Controllable Category Diversity Framework (CCDF) to achieve both high U-diversity and N-diversity simultaneously.Specifically, CCDF consists of two stages, User-Category Matching and Constrained Item Matching. The User-Category Matching utilizes the DeepU2C model and a combined loss to capture user's preferences in categories, and then selects the top-$K$ categories with a controllable parameter $K$.These top-$K$ categories will be used as trigger information in Constrained Item Matching. Offline experimental results show that our proposed DeepU2C outperforms state-of-the-art diversity-oriented methods, especially on N-diversity task. The whole framework is validated in a real-world production environment by conducting online A/B testing., Comment: A Two-stage Controllable Category Diversity Framework for Recommendation

We present ContinuityCam, a novel approach to generate a continuous video from a single static RGB image, using an event camera. Conventional cameras struggle with high-speed motion capture due to bandwidth and dynamic range limitations. Event cameras are ideal sensors to solve this problem because they encode compressed change information at high temporal resolution. In this work, we propose a novel task called event-based continuous color video decompression, pairing single static color frames and events to reconstruct temporally continuous videos. Our approach combines continuous long-range motion modeling with a feature-plane-based synthesis neural integration model, enabling frame prediction at arbitrary times within the events. Our method does not rely on additional frames except for the initial image, increasing, thus, the robustness to sudden light changes, minimizing the prediction latency, and decreasing the bandwidth requirement. We introduce a novel single objective beamsplitter setup that acquires aligned images and events and a novel and challenging Event Extreme Decompression Dataset (E2D2) that tests the method in various lighting and motion profiles. We thoroughly evaluate our method through benchmarking reconstruction as well as various downstream tasks. Our approach significantly outperforms the event- and image- based baselines in the proposed task.

Powder metallurgy with hot isostatic pressing (PM-HIP) is an advanced manufacturing process that is envisioned to replace forging for heavy nuclear components, including the reactor pressure vessel (RPV). But PM-HIP products must at least demonstrate comparable irradiation tolerance than forgings in order to be qualified for nuclear applications. The objective of this study is to directly compare PM-HIP to forged SA508 Grade 3 Class 1 low-alloy RPV steel at two neutron irradiation conditions: ~0.5-1.0 displacements per atom (dpa) at ~270C and ~370C. PM-HIP SA508 experiences greater irradiation hardening and embrittlement (total elongation) than forged SA508. However, uniform elongation and approximate toughness are comparable across all irradiated materials, suggesting irradiated PM-HIP SA508 exhibits superior ductility at maximum load-bearing capacity. The irradiation hardening mechanism is linked to composition rather than fabrication method. Since PM-HIP SA508 has higher Mn and Ni concentration, it is more susceptible to irradiation-induced nucleation of Mn-Ni-Si-P (MNSP) nanoprecipitates and dislocation loops, which both contribute to hardening. Conversely, the forged material nucleates fewer MNSPs, causing dislocation loops to control irradiation hardening. These results show promise for the irradiation performance of PM-HIP SA508 and can motivate future nuclear code qualification of PM-HIP fabrication for RPVs.

The Giant Radio Array for Neutrino Detection (GRAND) is an envisioned observatory of ultra-high-energy particles of cosmic origin, with energies in excess of 100 PeV. GRAND uses large surface arrays of autonomous radio-detection units to look for the radio emission from extensive air showers that are triggered by the interaction of ultra-high-energy cosmic rays, gamma rays, and neutrinos in the atmosphere or underground. In particular, for ultra-high-energy neutrinos, the future final phase of GRAND aims to be sensitive enough to discover them in spite of their plausibly tiny flux. Presently, three prototype GRAND radio arrays are in operation: GRANDProto300, in China, GRAND@Auger, in Argentina, and GRAND@Nancay, in France. Their goals are to field-test the design of the radio-detection units, understand the radio background to which they are exposed, and develop tools for diagnostic, data gathering, and data analysis. This list of contributions to the 38th International Cosmic Ray Conference (ICRC 2023) presents an overview of GRAND, in its present and future incarnations, and a look at the first data collected by GRANDProto13, the first phase of GRANDProto300., Comment: Note: To access the list of contributions, please follow the "HTML" link that can be found on the arXiv page

Same-style products retrieval plays an important role in e-commerce platforms, aiming to identify the same products which may have different text descriptions or images. It can be used for similar products retrieval from different suppliers or duplicate products detection of one supplier. Common methods use the image as the detected object, but they only consider the visual features and overlook the attribute information contained in the textual descriptions, and perform weakly for products in image less important industries like machinery, hardware tools and electronic component, even if an additional text matching module is added. In this paper, we propose a unified vision-language modeling method for e-commerce same-style products retrieval, which is designed to represent one product with its textual descriptions and visual contents. It contains one sampling skill to collect positive pairs from user click log with category and relevance constrained, and a novel contrastive loss unit to model the image, text, and image+text representations into one joint embedding space. It is capable of cross-modal product-to-product retrieval, as well as style transfer and user-interactive search. Offline evaluations on annotated data demonstrate its superior retrieval performance, and online testings show it can attract more clicks and conversions. Moreover, this model has already been deployed online for similar products retrieval in alibaba.com, the largest B2B e-commerce platform in the world., Comment: Accepted in The Web Conference (WWW2023) Industry Track. 5 pages, 3 figures

The complete elliptic integral of the first kind (CEI-1) plays in a significant role in mathematics, physics and engineering. There is no simple formula for its computation, thus numerical algorithms are essential for coping with practical problems involved. The commercial implementations for the numerical solutions, such as the functions ellipticK and EllipticK provided by MATLAB and Mathematica respectively, are based on $\mathcal{K}_{\mathrm{cs}}(m)$ instead of the usual form $K(k)$ such that $m = k^2$ and $\mathcal{K}_{\mathrm{cs}}(k^2) = K(k)$. It is necessary to develop open source implementations for the computation of the CEI-1 in order to avoid potential risks of using commercial software and possible limitations due to the unknown factors. In this paper, the infinite series method, arithmetic-geometric mean (AGM) method, Gauss-Chebyshev method and Gauss-Legendre methods are discussed in details with a top-down strategy. The four key algorithms for computing CEI-1 are designed, verified, validated and tested, which can be utilized in R\& D and be reused properly. Numerical results show that our open source implementations based on $K(k)$ are equivalent to the commercial implementation based on $\mathcal{K}_{\mathrm{cs}}(m)$. The general algorithms for computing orthogonal polynomials developed are significant byproducts in the sense of STEM education and scientific computation., Comment: 22 pages, 11 figures, 5 tables

Estimating the probability of failure for complex real-world systems using high-fidelity computational models is often prohibitively expensive, especially when the probability is small. Exploiting low-fidelity models can make this process more feasible, but merging information from multiple low-fidelity and high-fidelity models poses several challenges. This paper presents a robust multi-fidelity surrogate modeling strategy in which the multi-fidelity surrogate is assembled using an active learning strategy using an on-the-fly model adequacy assessment set within a subset simulation framework for efficient reliability analysis. The multi-fidelity surrogate is assembled by first applying a Gaussian process correction to each low-fidelity model and assigning a model probability based on the model's local predictive accuracy and cost. Three strategies are proposed to fuse these individual surrogates into an overall surrogate model based on model averaging and deterministic/stochastic model selection. The strategies also dictate which model evaluations are necessary. No assumptions are made about the relationships between low-fidelity models, while the high-fidelity model is assumed to be the most accurate and most computationally expensive model. Through two analytical and two numerical case studies, including a case study evaluating the failure probability of Tristructural isotropic-coated (TRISO) nuclear fuels, the algorithm is shown to be highly accurate while drastically reducing the number of high-fidelity model calls (and hence computational cost).

We propose a novel method for 3D shape completion from a partial observation of a point cloud. Existing methods either operate on a global latent code, which limits the expressiveness of their model, or autoregressively estimate the local features, which is highly computationally extensive. Instead, our method estimates the entire local feature field by a single feedforward network by formulating this problem as a tensor completion problem on the feature volume of the object. Due to the redundancy of local feature volumes, this tensor completion problem can be further reduced to estimating the canonical factors of the feature volume. A hierarchical variational autoencoder (VAE) with tiny MLPs is used to probabilistically estimate the canonical factors of the complete feature volume. The effectiveness of the proposed method is validated by comparing it with the state-of-the-art method quantitatively and qualitatively. Further ablation studies also show the need to adopt a hierarchical architecture to capture the multimodal distribution of possible shapes., Comment: 10 pages, 5 figures

The Tristructural isotropic (TRISO)-coated particle fuel is a robust nuclear fuel proposed to be used for multiple modern nuclear technologies. Therefore, characterizing its safety is vital for the reliable operation of nuclear technologies. However, the TRISO fuel failure probabilities are small and the computational model is time consuming to evaluate them using traditional Monte Carlo-type approaches. In the paper, we present a multifidelity active learning approach to efficiently estimate small failure probabilities given an expensive computational model. Active learning suggests the next best training set for optimal subsequent predictive performance and multifidelity modeling uses cheaper low-fidelity models to approximate the high-fidelity model output. After presenting the multifidelity active learning approach, we apply it to efficiently predict TRISO failure probability and make comparisons to the reference results.