Despite the progress in quantum computing, one major bottleneck against the practical utility is its susceptibility to noise, which frequently occurs in current quantum systems. Existing quantum error mitigation (QEM) methods either lack generality to noise and circuit types or fail to capture the global dependencies of entire systems in addition to circuit structure. In this work, we first propose a unique circuit-to-graph encoding scheme with qubit-wise noisy measurement aggregated. Then, we introduce GTranQEM, a non-message passing graph transformer designed to mitigate errors in expected circuit measurement outcomes effectively. GTranQEM is equipped with a quantum-specific positional encoding, a structure matrix as attention bias guiding nonlocal aggregation, and a virtual quantum-representative node to further grasp graph representations, which guarantees to model the long-range entanglement. Experimental evaluations demonstrate that GTranQEM outperforms state-of-the-art QEM methods on both random and structured quantum circuits across noise types and scales among diverse settings.

Graph-structured data is ubiquitous, and graph learning models have recently been extended to address complex problems like mixed-integer linear programming (MILP). However, studies have shown that the vanilla message-passing based graph neural networks (GNNs) suffer inherent limitations in learning MILP instance representation, i.e., GNNs may map two different MILP instance graphs to the same representation. In this paper, we introduce an expressive quantum graph learning approach, leveraging quantum circuits to recognize patterns that are difficult for classical methods to learn. Specifically, the proposed General Quantum Graph Learning Architecture (GQGLA) is composed of a node feature layer, a graph message interaction layer, and an optional auxiliary layer. Its generality is reflected in effectively encoding features of nodes and edges while ensuring node permutation equivariance and flexibly creating different circuit structures for various expressive requirements and downstream tasks. GQGLA is well suited for learning complex graph tasks like MILP representation. Experimental results highlight the effectiveness of GQGLA in capturing and learning representations for MILPs. In comparison to traditional GNNs, GQGLA exhibits superior discriminative capabilities and demonstrates enhanced generalization across various problem instances, making it a promising solution for complex graph tasks.

Quantum Error Mitigation (QEM) has emerged as a pivotal technique for enhancing the reliability of noisy quantum devices in the *Noisy Intermediate-Scale Quantum* (NISQ) era. Recently, machine learning (ML)-based QEM approaches have demonstrated strong generalization capabilities without sampling overheads compared to conventional methods. However, evaluating these techniques is often hindered by a lack of standardized datasets and inconsistent experimental settings across different studies. In this work, we present **QEM-Bench**, a comprehensive benchmark suite of *twenty-two* datasets covering diverse circuit types and noise profiles, which provides a unified platform for comparing and advancing ML-based QEM methods. We further propose a refined ML-based QEM pipeline **QEMFormer**, which leverages a feature encoder that preserves local, global, and topological information, along with a two-branch model that captures short-range and long-range dependencies within the circuit. Empirical evaluations on QEM-Bench illustrate the superior performance of QEMFormer over existing baselines, underscoring the potential of integrated ML-QEM strategies.

Tensor network has been a promising numerical tool for computational problems across science and AI. For their emerging and fast development especially in the intersection between AI and science, this paper tries to present a compact review, regarding both their applications and its own recent technical development including open-source tools. Specifically, we make the observations that tensor network plays a functional role in matrix compression and representation, information fusion, as well as quantum-inspired algorithms, which can be generally regarded as Science4AI in our survey. On the other hand, there is an emerging line of research in tensor network in AI4Science especially like learning quantum many-body physics by using e.g. neural network quantum state. Importantly, we unify tensorization methodologies across classical and modern architectures, and particularly show how tensorization bridges low-order parameter spaces to high-dimensional representations without exponential parameter growth, and further point out their potential use in scientific computing. We conclude the paper with outlook for future trends.

Recent advances in multi-modal generative models have enabled significant progress in instruction-based image editing. However, while these models produce visually plausible outputs, their capacity for knowledge-based reasoning editing tasks remains under-explored. In this paper, We introduce KRIS-Bench (Knowledge-based Reasoning in Image-editing Systems Benchmark), a diagnostic benchmark designed to assess models through a cognitively informed lens. Drawing from educational theory, KRIS-Bench categorizes editing tasks across three foundational knowledge types: Factual, Conceptual, and Procedural. Based on this taxonomy, we design 22 representative tasks spanning 7 reasoning dimensions and release 1,267 high-quality annotated editing instances. To support fine-grained evaluation, we propose a comprehensive protocol that incorporates a novel Knowledge Plausibility metric, enhanced by knowledge hints and calibrated through human studies. Empirical results on nine state-of-the-art models reveal significant gaps in reasoning performance, highlighting the need for knowledge-centric benchmarks to advance the development of intelligent image editing systems.

For the essential operation, namely inner product (IP) as widely adopted in classic computing e.g. matrix multi-plication, its quantum counterpart: quantum inner product (QIP), has also been recently theoretically explored with a verifiable lower complexity on quantum computers. How-ever, it remains unclear for the embodiment of the quantum circuits (QC) for QIP, let alone a (thorough) evaluation of the QIP circuits, especially in a practical context in the NISQ era by applying QIP to ML via hybrid quantum-classic pipelines. In this paper, we carefully design the QIP circuits from scratch, whose complexity is in accordance with the theoretical complexity. To make the simulation tractable on classic computers, especially when it is integrated in the gradient-based hybrid ML pipelines, we further devise a highly-efficient simulation scheme by directly simulates the output state. Experiments show that the scheme acceler-ates the simulation for more than 68k times compared with the previous circuit simulator. This allows our empirical evaluation on typical machine learning tasks, ranging from supervised and self-supervised learning via neural nets, to K-Means clustering. The results show that the calculation error brought by typical quantum mechanisms would incur in general little influence on the final numerical results given sufficient qubits. However, certain tasks e.g. ranking in K-Means could be more sensitive to quantum noise.

Molecule generation ideally in its 3-D form has enjoyed wide applications in material, chemistry, life science, etc. We propose the first quantum parametric circuit for 3-D molecule generation for its potential quantum advantage especially considering the arrival of Noisy Intermediate-Scale Quantum (NISQ) era. We choose the Variational AutoEncoder (VAE) scheme for its simplicity and one-shot generation ability, which we believe is more quantum-friendly compared with the auto-regressive generative models or diffusion models as used in classic approaches. Specifically, we present a quantum encoding scheme designed for 3-D molecules with qubits complexity $\mathcal{O}(C\log n)$ ($n$ is the number of atoms) and adopt a von Mises-Fisher (vMF) distributed latent space to meet the inherent coherence of the quantum system. We further design to encode conditions into quantum circuits for property-specified generation. Experimentally, our model could generate plausible 3-D molecules and achieve competitive quantitative performance with significantly reduced circuit parameters compared with their classic counterparts. The source code will be released upon publication.

Everyone is unique. Given the same visual stimuli, people's attention is driven by both salient visual cues and their own inherent preferences. Knowledge of visual preferences not only facilitates understanding of fine-grained attention patterns of diverse users, but also has the potential of benefiting the development of customized applications. Nevertheless, existing saliency models typically limit their scope to attention as it applies to the general population and ignore the variability between users' behaviors. In this paper, we identify the critical roles of visual preferences in attention modeling, and for the first time study the problem of user-aware saliency modeling. Our work aims to advance attention research from three distinct perspectives: (1) We present a new model with the flexibility to capture attention patterns of various combinations of users, so that we can adaptively predict personalized attention, user group attention, and general saliency at the same time with one single model; (2) To augment models with knowledge about the composition of attention from different users, we further propose a principled learning method to understand visual attention in a progressive manner; and (3) We carry out extensive analyses on publicly available saliency datasets to shed light on the roles of visual preferences. Experimental results on diverse stimuli, including naturalistic images and web pages, demonstrate the advantages of our method in capturing the distinct visual behaviors of different users and the general saliency of visual stimuli.

Combinatorial optimization (CO) on the graph is a crucial but challenging research topic. Recent quantum algorithms provide a new perspective for solving CO problems and have the potential to demonstrate quantum advantage. Quantum Approximate Optimization Algorithm (QAOA) is a well-known quantum heuristic for CO constructed by a parametric quantum circuit. However, QAOA is originally designed for unconstrained problems and the circuit parameters and solutions are jointly solved with time-consuming iterations. In this paper, we propose a novel quantum neural network (QNN) for learning CO problems in a supervised manner to achieve better and faster results. We focus on the Quadratic Assignment Problem (QAP) with matching constraints and the node permutation invariance property. To this end, a quantum neural network called QAP-QNN is devised to translate the QAP into a constrained vertex classification task. Moreover, we study two QAP tasks: Graph Matching and Traveling Salesman Problem on TorchQauntum simulators, and empirically show the effectiveness of our approach.

Learning of network embedding with vector-based node representation has attracted wide attention over the decade. It differs from the general setting of graph node embedding whereby the node attributes are also considered and yet may incur privacy issues. In this paper, we depart from the classic CPU/GPU architecture to consider the well-established network alignment problem based on network embedding, and develop a quantum machine learning approach with a low qubit cost for its near-future applicability on Noisy Intermediate-Scale Quantum (NISQ) devices. Specifically, our model adopts the discrete-time quantum walk (QW) and conducts the QW on the tailored merged network to extract structure information from the two aligning networks without the need for quantum state preparation which otherwise requires high quantum gate cost. Then the quantum states from QW are fed to a quantum embedding ansatz (i.e., parameterized circuit) to learn the latent representation of each node. The key part of our approach is to connect these two quantum modules to achieve a pure quantum paradigm without involving classical modules. To our best knowledge, there has not been any classic-quantum hybrid approach to network embedding, let alone a pure quantum paradigm being free from the bottleneck of communication between classic devices and quantum devices, which is still an open problem. Experimental results on two real-world datasets show the effectiveness of our quantum embedding approach in comparison with classical embedding approaches. Our model is readily and efficiently implemented in Python with a full-amplitude simulation of the QW and the quantum circuit. Therefore, our model can be readily deployed on an existing NISQ device with all the circuits provided, and only 13 qubits are needed in the experiments, which is rarely attained in existing quantum graph learning works.

This article proposes an effective and efficient visual place recognition (VPR) approach, which can make full use of semantic, sequential, and spatial geometric information in VPR tasks. Rather than previous methods focusing on extracting discriminative and compact features to represent images, we improve VPR performance from candidate selection and geometric verification. To this end, we propose a fast feature matching algorithm for real-time geometrical verification of candidate places, termed neighborhood manifold preserving matching (NMP). To generate high-quality candidates, we design a dynamic sequence partitioning strategy based on NMP, which is able to utilize the inherently sequential nature of spatial data to cluster images into places. By sequence-to-sequence matching, the ambiguity of single frame matching can be reduced. Extensive experiments demonstrate that our VPR method outperforms the current state-of-the-art methods, and our geometric verification and candidate selection strategies are easily plugged into other VPR pipelines to significantly improve the VPR performance.

As a fundamental and essential task in the field of remote sensing and photogrammetry, feature matching endeavors to establish reliable correspondences between two sets of feature points extracted from an image pair of the same scene. In this article, we propose an efficient and general algorithm, which is called local affine preservation (LAP) matching, for robust feature matching of remote sensing images. We start by constructing the putative point correspondences according to the similarity of well-designed feature descriptors and then focus on removing false matches from the putative set. The key idea of LAP is to search motion-consistent neighborhoods and maintain the local neighborhood topological structures of the true putative matches. To this end, we present a local geometric constraint, which exploits the property of affine invariance to measure the preservation degree of neighborhood topology, since the property is still held under both rigid and complex nonrigid transformations for a minimum topological unit. Moreover, in order to avoid the random distribution of outliers to destroy the neighborhood structure preservation of inliers, a neighbor mining strategy is introduced to search motion-consistent neighbors for each correspondence. We formulate the problem into an optimization model and derive a closed-form solution with linearithmic time complexity. Extensive experimental results on remote sensing images demonstrate that our LAP is able to achieve better performance over the current state-of-the-art approaches.

Loop-closure detection (LCD), which aims to recognize a previously visited location, is a crucial component of the simultaneous localization and mapping system. In this paper, a novel appearance-based LCD method is presented. In particular, we propose a simple yet surprisingly useful feature matching algorithm for real-time geometrical verification of candidate loop-closures, termed aslocal relative orientationmatching (LRO). It aims to efficiently establish reliable feature correspondences based on preserving local topological structures between the query image and candidate frame. To effectively retrieve candidate loop closures, we introduce the aggregated selective match kernel framework into the LCD task, which can effectively represent images and reduce the quantization noise of the traditional bag-of-words framework. In addition, the SuperPoint neural network is employed to extract reliable interest points and feature descriptors. Extensive experimental results demonstrate that our LRO can significantly improve the LCD performance, and the proposed overall LCD method can achieve much better performance over the current state-of-the-art on six publicly available datasets.

Nowadays, the rise of the Internet of Vehicles (IoV) has led to the rapid development of smart transportation. To increase the computing capacity of mobile vehicles and decrease the content delivery latency of suppliers, mobile edge computing (MEC) is considered as an indispensable solution. However, there are some essential issues to be considered: 1) security and privacy of data transmission, and 2) reasonable resource allocation for collaborative computing and caching. In this paper, to solve above issues, blockchain technology is adopted to ensure reliable transmission and interaction of data. Meanwhile, we develop an intelligent resource framework about computing and caching for blockchain-enabled MEC systems in IoV. Through jointly considering and optimizing offloading decision of computation task carried by vehicle, caching decision, the number of offloaded consensus nodes, block interval and block size, the energy consumption and computation overheads can be decreased, and the data throughput of the blockchain can be increased significantly. Moreover, the proposed optimization problem is modeled and formulated as a Markov decision process. Facing the complexity and dynamic of resource allocation, the asynchronous advantage actor-critic approach is considered and applied to solve the optimization problem. Experiment results demonstrate that the advantages of the proposed optimization scheme are obvious compared with other existing schemes.

Recently, electric vehicles (EVs) have been widely used under the call of green travel and environmental protection, and diverse requirements for charging are also increasing gradually. In order to ensure the authenticity and privacy of charging information interaction, blockchain technology is proposed and applied in charging station billing systems. However, there are some issues in blockchain itself, including lower computing efficiency of the nodes and higher energy consumption in the consensus process. To handle the above issues, in this paper, combining blockchain and mobile edge computing, we develop a reliable billing data transmission scheme to improve the computing capacity of nodes and reduce the energy consumption of the consensus process. By jointly optimizing the primary and replica nodes offloading decisions, block size and block interval, the transaction throughput of the blockchain system is maximized, as well as the consumption costs of latency and energy consumption is minimized. Moreover, we formulate the joint optimization problem as Markov decision process (MDP). To tackle this dynamic and continuity of the system state, the actor–critic reinforcement learning is introduced to solve the MDP problem. Finally, simulation results demonstrate that the performance improvement of the proposed scheme through comparison with other existing schemes.

Visual Place Recognition (VPR) is a crucial component for long-term mobile robot autonomy. In this paper, we exploit a coarse-to-fine paradigm to recognize places. In particular, we first select candidate frames for each query image, and then check the spatial geometric relationship between the query and its candidate frames to determine the final place match. In the coarse match stage, we employ the deep learning network to extract global features that encode semantic information of images, then by comparing the similarity between features to obtain a candidate list of the query place. In the fine match stage, we propose an effective and efficient feature matching algorithm for real-time geometrical verification of candidate places, termed as local affine preserving matching (LAP). Extensive experimental results demonstrate that our LAP can significantly promote the VPR performance, and the proposed overall VPR method can achieve much better performance over the current state-of-the-art approaches.