The critical role of personnel security screening (PSS) devices in modern public transportation has driven a growing demand for real-time, lightweight, noninteractive, and high-performance screening systems. Currently, the predominant methods involve handheld metal scanners that require active cooperation by the subject, generally suffering from low efficiency, limited detection range, and blind spots for nonmetallic objects. Millimeter-wave-based PSS technology, featured by its speediness, harmlessness, and capability of detecting nonmetallic materials, represents an emerging trend in security screening. However, traditional millimeter-wave system-wide dynamic scanning schemes face challenges such as bulky size, high complexity, and poor integration. To address these problems, we develop a wide-angle metalens based on a neural-network-assisted end-to-end inverse design method, aiming to replace thick and heavy dielectric lenses in traditional millimeter-wave PSS systems, thereby enhancing system integration and lightweight capabilities while improving wide-angle scanning performance. As proof of concept, we propose a system-wide static noninteractive wide-angle dual-polarized meta-detector, which consists of a dynamic beam steering transmitter, dual-polarized receivers, and a data acquisition module. This meta-detector can rapidly, precisely, and statically identify concealed objects of various materials on the human body in a noninteractive manner within a 32° horizontal and 26.8° vertical field-of-view at an operating range of 15–25 m. The proposed PSS system offers long detection range, high integration, and noninteractive operation, highlighting its potential for practical deployment in real-world public security screening scenarios.

The trade-off between computation time and path optimality is a key consideration in motion planning algorithms. While classical sampling based algorithms fall short of computational efficiency in high dimensional planning, learning based methods have shown great potential in achieving time efficient and optimal motion planning. The SOTA learning based motion planning algorithms utilize paths generated by sampling based methods as expert supervision data and train networks via regression techniques. However, these methods often overlook the important multimodal property of the optimal paths in the training set, making them incapable of finding good paths in some scenarios. In this paper, we propose a Multimodal Neuron Planner (MNP) based on the mixture density networks that explicitly takes into account the multimodality of the training data and simultaneously achieves time efficiency and path optimality. For environments represented by point clouds, MNP first efficiently compresses point clouds into a latent vector by encoding networks that are suitable for processing point clouds. We then design multimodal planning networks which enables MNP to learn and predict multiple optimal solutions. Simulation results show that our method outperforms SOTA learning based method MPNet and advanced sampling based methods IRRT* and BIT*.

Aiming at a better understanding of the search goals in the user search sessions, recent query recommender systems explicitly model the reformulations of queries, which hopes to estimate the intents behind these reformulations and thus benefit the next-query recommendation. However, in real-world e-commercial search scenarios, user intents are much more complicated and may evolve dynamically. Existing methods merely consider trivial reformulation intents from semantic aspects and fail to model dynamic reformulation intent flows in search sessions, leading to sub-optimal capacities to recommend desired queries. To deal with these limitations, we first explicitly define six types of query reformulation intents according to the desired products of two consecutive queries. We then apply two self-attentive encoders on top of two pre-trained large language models to learn the transition dynamics from semantic query and intent reformulation sequences, respectively. We develop an intent-aware query decoder to utilize the predicted intents for suggesting the next queries. We instantiate such a framework with an Intent-aware Variational AutoEncoder (IVAE) under deployment at Amazon. We conduct comprehensive experiments on two real-world e-commercial datasets from Amazon and one public dataset from BestBuy. Specifically, IVAE improves the Recall@15 by 25.44% and 60.47% on two Amazon datasets and 13.91% on BestBuy, respectively.

Graph Neural Networks (GNNs) have achieved great success in modeling graph-structured data. However, recent works show that GNNs are vulnerable to adversarial attacks which can fool the GNN model to make desired predictions of the attacker. In addition, training data of GNNs can be leaked under membership inference attacks. This largely hinders the adoption of GNNs in high-stake domains such as e-commerce, finance and bioinformatics. Though investigations have been made in conducting robust predictions and protecting membership privacy, they generally fail to simultaneously consider the robustness and membership privacy. Therefore, in this work, we study a novel problem of developing robust and membership privacy-preserving GNNs. Our analysis shows that Information Bottleneck (IB) can help filter out noisy information and regularize the predictions on labeled samples, which can benefit robustness and membership privacy. However, structural noises and lack of labels in node classification challenge the deployment of IB on graph-structured data. To mitigate these issues, we propose a novel graph information bottleneck framework that can alleviate structural noises with neighbor bottleneck. Pseudo labels are also incorporated in the optimization to minimize the gap between the predictions on the labeled set and unlabeled set for membership privacy. Extensive experiments on real-world datasets demonstrate that our method can give robust predictions and simultaneously preserve membership privacy.

Keyphrase generation aims to summarize long documents with a collection of salient phrases. Deep neural models have demonstrated remarkable success in this task, with the capability of predicting keyphrases that are even absent from a document. However, such abstractiveness is acquired at the expense of a substantial amount of annotated data. In this paper, we present a novel method for keyphrase generation, AutoKeyGen, without the supervision of any annotated doc-keyphrase pairs. Motivated by the observation that an absent keyphrase in a document may appear in other places, in whole or in part, we construct a phrase bank by pooling all phrases extracted from a corpus. With this phrase bank, we assign phrase candidates to new documents by a simple partial matching algorithm, and then we rank these candidates by their relevance to the document from both lexical and semantic perspectives. Moreover, we bootstrap a deep generative model using these top-ranked pseudo keyphrases to produce more absent candidates. Extensive experiments demonstrate that AutoKeyGen outperforms all unsupervised baselines and can even beat a strong supervised method in certain cases.

We propose Visual News Captioner, an entityaware model for the task of news image captioning.We also introduce Visual News, a large-scale benchmark consisting of more than one million news images along with associated news articles, image captions, author information, and other metadata.Unlike the standard image captioning task, news images depict situations where people, locations, and events are of paramount importance.Our proposed method can effectively combine visual and textual features to generate captions with richer information such as events and entities.More specifically, built upon the Transformer architecture, our model is further equipped with novel multi-modal feature fusion techniques and attention mechanisms, which are designed to generate named entities more accurately.Our method utilizes much fewer parameters while achieving slightly better prediction results than competing methods.Our larger and more diverse Visual News dataset further highlights the remaining challenges in captioning news images.

The 2019 novel coronavirus (SARS-CoV-2) has spread rapidly worldwide and was declared a pandemic by the WHO in March 2020. The evolution of SARS-CoV-2, either in its natural reservoir or in the human population, is still unclear, but this knowledge is essential for effective prevention and control. We propose a new framework to systematically identify recombination events, excluding those due to noise and convergent evolution. We found that several recombination events occurred for SARS-CoV-2 before its transfer to humans, including a more recent recombination event in the receptor-binding domain. We also constructed a probabilistic mutation network to explore the diversity and evolution of SARS-CoV-2 after human infection. Clustering results show that the novel coronavirus has diverged into several clusters that cocirculate over time in various regions and that several mutations across the genome are fixed during transmission throughout the human population, including D614G in the S gene and two accompanied mutations in ORF1ab. Together, these findings suggest that SARS-CoV-2 experienced a complicated evolution process in the natural environment and point to its continuous adaptation to humans. The new framework proposed in this study can help our understanding of and response to other emerging pathogens.

Electric vehicle charging is becoming more commonplace, but a number of challenges remain. For example, the wireless communications between vehicle users and aggregators can be subject to exploitation and hence, several authentication schemes have been designed to support varying levels of privacy protection. However, there are a number of limitations observed in existing authentication schemes, and examples include lack of anonymity and not considering charging peak in their design (and consequently, not meeting low energy consumption requirement in smart grid environments). More recently, there have been attempts to utilize Chevyshev chaotic map in the design of authentication mechanism, with the aims of reducing computational costs yet achieving high security. However, the security requirements of Chebyshev polynomials pose new challenges to the construction of Chebyshev chaotic maps-based authentication schemes. To solve these limitations, we propose an efficient Chebyshev polynomials algorithm by adopting a square matrix-based binary exponentiation algorithm to provide secure and efficient Chebyshev polynomial computation. We further construct an energy-efficient authentication and key negotiation scheme for the smart grid environments based on the proposed algorithm. Compared with five other competing schemes, our proposed authentication scheme achieves reduced computational and communication costs. In addition, the ProVerif tool is used to analyze the security of our proposed authentication scheme. The results show that the proposed scheme outperforms these five other schemes in terms of computation and communication overheads while achieving privacy preserving.