Multi-Hop Question Answering (MHQA), crucial for complex information retrieval, remains challenging for current Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems, which often suffer from hallucination, reliance on incomplete knowledge, and opaque reasoning processes. Existing RAG methods, while beneficial, still struggle with the intricacies of multi-step inference and ensuring verifiable accuracy. This research introduces TreeQA, a novel framework designed to significantly enhance the reliability and interpretability of LLM-RAG systems in MHQA tasks. TreeQA addresses these limitations by decomposing complex multi-hop questions into a hierarchical logic tree of simpler, verifiable sub-questions, integrating evidence from both structured knowledge bases (e.g., Wikidata) and unstructured text (e.g., Wikipedia), and employing an iterative, evidence-based validation and self-correction mechanism at each reasoning step to dynamically rectify errors and prevent their accumulation. Extensive experiments on four benchmark datasets (WebQSP, QALD-en, AdvHotpotQA, and 2WikiMultiHopQA) demonstrate TreeQA’s superior performance, achieving Hit@1 scores of 87%, 57%, 53%, and 59%, respectively, representing improvements of 4%-12% over state-of-the-art LLM-RAG methods. These findings highlight the significant impact of structured, verifiable reasoning pathways in developing more robust, accurate, and interpretable knowledge-intensive AI systems, thereby enhancing the practical utility of LLMs in complex reasoning scenarios. Our code is publicly available at https://github.com/ACMISLab/TreeQA .

Abstract Siamese networks have attracted wide attention in visual tracking due to their competitive accuracy and speed. However, the existing Siamese trackers usually leverage a fixed linear aggregation of feature maps, which does not effectively fuse the different layers of features with attention. Besides, most of Siamese trackers calculate the similarity between the template and the search region through a cross‐correlation operation between the features of the last blocks from the two branches, which might introduce the redundant noise information. In order to solve these problems, this study proposes a novel Siamese visual tracking method via cross‐layer calibration fusion, termed SiamCCF. An attention‐based feature fusion module is employed using local attention and non‐local attention to fuse the features from the deep and shallow layers, so as to capture both local details and high‐level semantic information. Moreover, a cross‐layer calibration module can use the fused features to calibrate the features of the last network blocks and build the cross‐layer long‐range spatial and inter‐channel dependencies around each spatial location. Extensive experiments demonstrate that the proposed method has achieved competitive tracking performance compared with state‐of‐the‐art trackers on challenging benchmarks, including OTB100, OTB2013, UAV123, UAV20L, and LaSOT.

Traffic sign recognition plays an important role in driver assistant systems and intelligent autonomous vehicles. Its real-time performance is highly desirable in addition to its recognition performance. This paper aims to deal with real-time traffic sign recognition, i.e., localizing what type of traffic sign appears in which area of an input image at a fast processing time. To achieve this goal, we first propose an extremely fast detection module, which is 20 times faster than the existing best detection module. Our detection module is based on traffic sign proposal extraction and classification built upon a color probability model and a color HOG. Then, we harvest from a convolutional neural network to further classify the detected signs into their subclasses within each superclass. Experimental results on both German and Chinese roads show that both our detection and classification methods achieve comparable performance with the state-of-the-art methods, with significantly improved computational efficiency.