Yang Fang

Dahang Wan, Rongsheng Lu, Yang Fang et al.

Multispectral object detection, which integrates information from multiple bands, can enhance detection accuracy and environmental adaptability, holding great application potential across various fields. Although existing methods have made progress in cross-modal interaction, low-light conditions, and model lightweight, there are still challenges like the lack of a unified single-stage framework, difficulty in balancing performance and fusion strategy, and unreasonable modality weight allocation. To address these, based on the YOLOv11 framework, we present YOLOv11-RGBT, a new comprehensive multimodal object detection framework. We designed six multispectral fusion modes and successfully applied them to models from YOLOv3 to YOLOv12 and RT-DETR. After reevaluating the importance of the two modalities, we proposed a P3 mid-fusion strategy and multispectral controllable fine-tuning (MCF) strategy for multispectral models. These improvements optimize feature fusion, reduce redundancy and mismatches, and boost overall model performance. Experiments show our framework excels on three major open-source multispectral object detection datasets, like LLVIP and FLIR. Particularly, the multispectral controllable fine-tuning strategy significantly enhanced model adaptability and robustness. On the FLIR dataset, it consistently improved YOLOv11 models' mAP by 3.41%-5.65%, reaching a maximum of 47.61%, verifying the framework and strategies' effectiveness. The code is available at: https://github.com/wandahangFY/YOLOv11-RGBT.

Weixuan Sun, Jucai Zhai, Dengfeng Liu et al.

The automated repair of C++ compilation errors presents a significant challenge, the resolution of which is critical for developer productivity. Progress in this domain is constrained by two primary factors: the scarcity of large-scale, high-fidelity datasets and the limitations of conventional supervised methods, which often fail to generate semantically correct patches.This paper addresses these gaps by introducing a comprehensive framework with three core contributions. First, we present CCrepair, a novel, large-scale C++ compilation error dataset constructed through a sophisticated generate-and-verify pipeline. Second, we propose a Reinforcement Learning (RL) paradigm guided by a hybrid reward signal, shifting the focus from mere compilability to the semantic quality of the fix. Finally, we establish the robust, two-stage evaluation system providing this signal, centered on an LLM-as-a-Judge whose reliability has been rigorously validated against the collective judgments of a panel of human experts. This integrated approach aligns the training objective with generating high-quality, non-trivial patches that are both syntactically and semantically correct. The effectiveness of our approach was demonstrated experimentally. Our RL-trained Qwen2.5-1.5B-Instruct model achieved performance comparable to a Qwen2.5-14B-Instruct model, validating the efficiency of our training paradigm. Our work provides the research community with a valuable new dataset and a more effective paradigm for training and evaluating robust compilation repair models, paving the way for more practical and reliable automated programming assistants.

Wenqi Guan, Yang Fang

Large Language Models have brought a radical change in the process of remote learning students, among other aspects of educative activities. Current retrieval of remote learning resources lacks depth in contextual meaning that provides comprehensive information on complex student queries. This work proposes a novel approach to enhancing remote learning retrieval by integrating GPT-based models within the LangChain framework. We achieve this system in a more intuitive and productive manner using CoT reasoning and prompt engineering. The framework we propose puts much emphasis on increasing the precision and relevance of the retrieval results to return comprehensive and contextually enriched explanations and resources that best suit each student's needs. We also assess the effectiveness of our approach against paradigmatic LLMs and report improvements in user satisfaction and learning outcomes.

Xinlong Sun, Yangyang Qin, Xuyuan Xu et al.

As a basic task of computer vision, image similarity retrieval is facing the challenge of large-scale data and image copy attacks. This paper presents our 3rd place solution to the matching track of Image Similarity Challenge (ISC) 2021 organized by Facebook AI. We propose a multi-branch retrieval method of combining global descriptors and local descriptors to cover all attack cases. Specifically, we attempt many strategies to optimize global descriptors, including abundant data augmentations, self-supervised learning with a single Transformer model, overlay detection preprocessing. Moreover, we introduce the robust SIFT feature and GPU Faiss for local retrieval which makes up for the shortcomings of the global retrieval. Finally, KNN-matching algorithm is used to judge the match and merge scores. We show some ablation experiments of our method, which reveals the complementary advantages of global and local features.

Yang Fang, Geun-Sik Jo, Chang-Hee Lee

Most Siamese network-based trackers perform the tracking process without model update, and cannot learn targetspecific variation adaptively. Moreover, Siamese-based trackers infer the new state of tracked objects by generating axis-aligned bounding boxes, which contain extra background noise, and are unable to accurately estimate the rotation and scale transformation of moving objects, thus potentially reducing tracking performance. In this paper, we propose a novel Rotation-Scale Invariant Network (RSINet) to address the above problem. Our RSINet tracker consists of a target-distractor discrimination branch and a rotation-scale estimation branch, the rotation and scale knowledge can be explicitly learned by a multi-task learning method in an end-to-end manner. In addtion, the tracking model is adaptively optimized and updated under spatio-temporal energy control, which ensures model stability and reliability, as well as high tracking efficiency. Comprehensive experiments on OTB-100, VOT2018, and LaSOT benchmarks demonstrate that our proposed RSINet tracker yields new state-of-the-art performance compared with recent trackers, while running at real-time speed about 45 FPS.

Yang Fang, Xiang Zhao, Yifan Chen et al.

In network representation learning we learn how to represent heterogeneous information networks in a low-dimensional space so as to facilitate effective search, classification, and prediction solutions. Previous network representation learning methods typically require sufficient task-specific labeled data to address domain-specific problems. The trained model usually cannot be transferred to out-of-domain datasets. We propose a self-supervised pre-training and fine-tuning framework, PF-HIN, to capture the features of a heterogeneous information network. Unlike traditional network representation learning models that have to train the entire model all over again for every downstream task and dataset, PF-HIN only needs to fine-tune the model and a small number of extra task-specific parameters, thus improving model efficiency and effectiveness. During pre-training, we first transform the neighborhood of a given node into a sequence. PF-HIN is pre-trained based on two self-supervised tasks, masked node modeling and adjacent node prediction. We adopt deep bi-directional transformer encoders to train the model, and leverage factorized embedding parameterization and cross-layer parameter sharing to reduce the parameters. In the fine-tuning stage, we choose four benchmark downstream tasks, i.e., link prediction, similarity search, node classification, and node clustering. PF-HIN consistently and significantly outperforms state-of-the-art alternatives on each of these tasks, on four datasets.

Hao Xu, Lei Zhang, Oluwakayode Onireti et al.

The outbreak of COVID-19 pandemic has exposed an urgent need for effective contact tracing solutions through mobile phone applications to prevent the infection from spreading further. However, due to the nature of contact tracing, public concern on privacy issues has been a bottleneck to the existing solutions, which is significantly affecting the uptake of contact tracing applications across the globe. In this paper, we present a blockchain-enabled privacy-preserving contact tracing scheme: BeepTrace, where we propose to adopt blockchain bridging the user/patient and the authorized solvers to desensitize the user ID and location information. Compared with recently proposed contract tracing solutions, our approach shows higher security and privacy with the additional advantages of being battery friendly and globally accessible. Results show viability in terms of the required resource at both server and mobile phone perspectives. Through breaking the privacy concerns of the public, the proposed BeepTrace solution can provide a timely framework for authorities, companies, software developers and researchers to fast develop and deploy effective digital contact tracing applications, to conquer COVID-19 pandemic soon. Meanwhile, the open initiative of BeepTrace allows worldwide collaborations, integrate existing tracing and positioning solutions with the help of blockchain technology.

Yifan Chen, Xiang Zhao, Junjiao Gan et al.

Top-$N$ recommender systems have been extensively studied. However, the sparsity of user-item activities has not been well resolved. While many hybrid systems were proposed to address the cold-start problem, the profile information has not been sufficiently leveraged. Furthermore, the heterogeneity of profiles between users and items intensifies the challenge. In this paper, we propose a content-based top-$N$ recommender system by learning the global term weights in profiles. To achieve this, we bring in PathSim, which could well measures the node similarity with heterogeneous relations (between users and items). Starting from the original TF-IDF value, the global term weights gradually converge, and eventually reflect both profile and activity information. To facilitate training, the derivative is reformulated into matrix form, which could easily be paralleled. We conduct extensive experiments, which demonstrate the superiority of the proposed method.