We present a Chain-of-Action (CoA) framework for multimodal and retrieval-augmented Question-Answering (QA). Compared to the literature, CoA overcomes two major challenges of current QA applications: (i) unfaithful hallucination that is inconsistent with real-time or domain facts and (ii) weak reasoning performance over compositional information. Our key contribution is a novel reasoning-retrieval mechanism that decomposes a complex question into a reasoning chain via systematic prompting and pre-designed actions. Methodologically, we propose three types of domain-adaptable `Plug-and-Play' actions for retrieving real-time information from heterogeneous sources. We also propose a multi-reference faith score to verify conflicts in the answers. In addition, our system demonstrates that detecting the knowledge boundaries of LLMs can significantly reduce both LLM interaction frequency and tokens usage in QA tasks. Empirically, we exploit both public benchmarks and a Web3 case study to demonstrate the capability of CoA over other methods.

We present MetaFind, a scene-aware multi-modal retrieval framework designed to enhance scene generation in the metaverse by retrieving 3D assets from large-scale repositories. MetaFind addresses two core challenges: (i) inconsistent asset retrieval that overlooks spatial, semantic, and stylistic constraints, and (ii) the absence of a standardized retrieval paradigm specifically tailored for 3D asset retrieval, as existing approaches predominantly rely on general-purpose 3D shape representation models. Our key innovation is a retrieval mechanism that enhances both spatial reasoning and style consistency by jointly modeling object-level features (including appearance) and scene-level layout structures. Methodologically, MetaFind introduces a plug-and-play layout encoder that captures both spatial relationships and object appearance features, ensuring retrieved 3D assets are contextually and stylistically coherent with the existing scene. The framework supports iterative scene construction by continuously adapting retrieval results to current scene updates. Empirical evaluations demonstrate the improved spatial and stylistic consistency of MetaFind in various retrieval tasks compared to baseline methods.

Smart contract security is one of the core issues in any application based on blockchain. There are many techniques focusing on smart contract security, however, due to the diversity of Solidity versions and limitations of detection time, it is difficult for them to comprehensively localize defects in different versions of smart contracts. In this article, we propose a static defect detection method based on the knowledge graph of the Solidity language and present a defect detection tool calledSoliDetector. First, we define the ontology layer of the knowledge graph and construct the instance layer in which syntactic and logical relationships are captured. Second, we introduce the defect pattern to describe each defect and design inference rules to infer complex relationships and judge whether a defect exists. Finally, we localize defects by executing SPARQL queries.SoliDetectorcan support the detection of 20 kinds of defects and the automatic SPARQL query generation. We conducted several experiments on multiple datasets.SoliDetectorobtains a highF-score(i.e., 92.97% on Dataset1 and 91.54% on the SmartBug dataset). To compareSoliDetectorwithSmartCheck,Slither, andMythril, we conducted experiments on a labeled benchmark Dataset3 and real-world contracts.SoliDetectorhas a highF-scoreof 94.04% and is faster than other tools with an average time of 0.37 s for each contract.

This paper addresses the challenges in accurate and real-time traffic congestion prediction under uncertainty by proposing Ising-Traffic, a dual-model Ising-based traffic prediction framework that delivers higher accuracy and lower latency than SOTA solutions. While traditional solutions face the dilemma from the trade-off between algorithm complexity and computational efficiency, our Ising-based method breaks away from the trade-off leveraging the Ising model's strong expressivity and the Ising machine's strong computation power. In particular, Ising-Traffic formulates traffic prediction under uncertainty into two Ising models: Reconstruct-Ising and Predict-Ising. Reconstruct-Ising is mapped onto modern Ising machines and handles uncertainty in traffic accurately with negligible latency and energy consumption, while Predict-Ising is mapped onto traditional processors and predicts future congestion precisely with only at most 1.8% computational demands of existing solutions. Our evaluation shows Ising-Traffic delivers on average 98X speedups and 5% accuracy improvement over SOTA.

Due to the Ising model’s strong expressivity and Ising machines’ unique computational power, it is highly desired if Ising-based learning can be used in real-world applications. Unfortunately, the challenges in learning the Ising model and gaps between the practical accuracy of Ising machines and the theoretical accuracy of the Ising model impede the realization of Ising machines’ potential. Hence, we propose an Ising Machine Learning framework, Ising-CF, for collaborative filtering, a widely-used recommendation method. Specifically, Ising-CF uses Linear Neural Networks with Besag’s pseudo-likelihood and voltage polarization for fast, accurate Ising model learning and an Ising-specific logarithmic quantization for ns-level Ising machine inference with near-theoretical accuracy, 7.3% over SOTA.

Deep Learning Recommendation Models (DLRMs) are important applications in various domains and have evolved into one of the largest and most important machine learning applications. With their trillions of parameters necessarily exceeding the high bandwidth memory (HBM) capacity of GPUs, ever more massive DLRMs require large-scale multi-node systems for distributed training and inference. However, these all suffer from the all-to-all communication bottleneck, which limits scalability.

The rapid growth in the size of Graph Convolutional Neural Networks (GCNs) encounters both computational- and memory-wall on classical computing platforms (e.g., CPU, GPU, FPGA, etc.). Quantum computing, on the other hand, provides extremely high parallelism for computation. Although quantum neural networks have been recently studied, the research on quantum graph neural networks is still in its infancy. The key challenge here is how to integrate both the graph topology information and the learning ability of GCNs into quantum circuits. In this work, we leverage the Givens rotations and its quantum implementation to encode graph information; in addition, we employ the widely used variational quantum circuit to bring the learnable parameters. On top of these, we present a full-quantum design of Graph Convolutional Neural Networks, namely "QuGCN", for semi-supervised learning on graph-structured data. Experiment results show our design is competitive with classical GCNs in terms of node classification accuracy on Cora sub-dataset. More importantly, we show the potential advantages that can be achieved by the proposed quantum GCN design when the number of features grows.

As one of the most complex types of vulnerabilities, reentrancy poses a significant threat to smart contract development. Indeed, millions of dollars have evaporated due to reentrancy vulnerabilities of smart contracts in past years. In this article, we propose a new approach to detect reentrancy vulnerabilities using fuzz testing and develop a novel tool named ReDefender. Our approach consists of three main steps: 1)preprocess contract to be detected:when a contract is uploaded, its source code will be preprocessed to extract candidate pool for fuzzing and dependency graph which guides the automatic deployment of contracts; 2)fuzzing input generation:fuzzing input is generated to constitute transactions which will be sent to an agent contract to stimulate attacks, where runtime information is collected and recorded in the execution log during each execution; and 3)vulnerability verification:the execution log is analyzed to determine whether a reentrancy process occurs and whether the reentrancy process is malicious. We conduct comparative experiments on 204 tagged smart contracts and 90 injected contracts. The results show higher accuracy and lower false negative rate of ReDefender than that of the other three famous tools. Moreover, we conduct an experiment on 4776 real-world contracts demonstrating the ability of ReDefender to find reentrancy vulnerabilities that really cause economic losses.

Reentrancy, one of the most complex type of vulner-abilities, poses significant threat to smart contract development. Indeed, millions of dollars have evaporated due to reentrancy vulnerabilities of smart contracts in past years. In this paper, we propose a new approach to detect reentrancy vulnerabilities using fuzz testing and develop a novel tool named ReDefender. Our approach and tool consists of four main steps: (1)preprocess contract to be detected: when a contract uploaded, its source code will be preprocessed by ReDefender to extract candidate pool for fuzzing; (2) generate fuzzing input: fuzzing input will be generated by fuzz engine; (3) collect runtime information: an agent contract is constructed to interact with and attack all contracts to be detected. Runtime information is collected during the execution of every fuzzing input; (4) analyze execution log and find reentrancy: the execution log is analyzed to determine whether a malicious reentrancy occurs. We conduct experiments on 204 tagged smart contracts and show the higher accuracy and lower false positive rate of ReDefender than that of other three famous tools. Moreover, we conduct a new experiment and find 4 reentrancy vulnerabilities in 395 on-chain contract accounts which have managed more than 1000 transactions.

Smart contract security is one of core security issues in the application of blockchain.In recent years, attacks on smart contracts occur frequently, there are a lot of researches concerning on smart contract security issues.However, almost all solutions proposed in these researches are low precision and high False Negative Rate(FNR).In this paper, we propose a defect detection method for checking security of Solidity smart contract based on knowledge graph.Therefore, we first construct knowledge graph of smart contracts by fully integrating syntax and semantic information of Solidity source code; then, we define defect patterns by analyzing defect characteristics; furthermore, we define inference rules for defects based on knowledge graph and defect patterns; finally, we detect defects by SPARQL query.We also implement a tool named SolDetector and perform experiment on three different datasets, which shows that SolDetector is effective and efficient.