Boyue Wang

Tld-yolo: an enhanced YOLO framework for accurate and real-time UAV inspection of transmission line defects

Shengli Du, Cong Guo, Wei Lou, Boyue Wang

cn, us (code pays fourni par la source)

Speaker-Mediated Route Knowledge Transfer for Goal-Oriented Vision-and-Language Navigation

Ju Han, Xiaoyan Li, Boyue Wang, Yongli Hu et autres

Goal-oriented vision-and-language navigation (VLN) requires an agent to reach a target from a high-level instruction that does not prescribe a route. Training therefore faces two problems. First, terminal and distance-based feedback leave partial trajectories without route-semantic supervision. Second, a single annotated path …

cn (code pays fourni par la source)

Training-free counterfactual hallucination mitigation method for large vision-language models

Xilin Li, Boyue Wang, Xiaoqian Ju, Y. Charlie Hu et autres

cn (code pays fourni par la source)

Virtual Kernel SegFormer: A Hybrid Architecture for Point Cloud Segmentation

Bowen Wu, Xiaoyan Li, Ju Han, Boyue Wang et autres

cn (code pays fourni par la source)

Adaptive low-quality negative samples partition and weakening for temporal knowledge graph completion

Yihan Gao, Boyue Wang, Simin Hu, Lan Zhao et autres

cn (code pays fourni par la source)

Case2Knowledge: Structured Knowledge-Infused Prompting for Faithful Radiology Report Generation

Qi Gao, T Liu, Zhongfan Sun, Boyue Wang et autres

Radiology report generation (RRG) aims to automatically describe imaging studies, reducing radiologists’ workload and improving diagnostic reliability. Despite recent advances, current methods still suffer from hallucinations and semantic inconsistencies, limiting clinical adoption. To address these issues, we present Case2Knowledge (C2K), a retrieval-augmented …

cn (code pays fourni par la source)

MFC: Mixed Federated Clustering based on Cross-modal Feature Decoupling

Xiaxia He, Boyue Wang, Junbin Gao, Yongli Hu et autres

Existing federated clustering methods typically assume that either all clients supply the same type of single-modal/multi-modal data, or that different clients provide various modalities describing the same object. However, a prevalent real-world scenario involves clients contributing data from diverse and unrelated modalities. …

cn, au (code pays fourni par la source)

Quadruplet Augmentation With Attribute and Structure Invariance for Online Continual Learning

Jiamin Wu, Shaofan Wang, Yanan Sun, Boyue Wang et autres

Online Continual Learning (OCL) learns from non-independently and identically distributed streaming data with unknown task boundaries during training and testing. Previous methods suffer from the shortcut feature trap and limited plasticity, leading to two requirements: attribute invariance and structure invariance. The former …

cn (code pays fourni par la source)

Sim2Real-AD: A Modular Sim-to-Real Framework for Deploying VLM-Guided Reinforcement Learning in Real-World Autonomous Driving

Zilin Huang, Zhengyang Wan, Zihao Sheng, Boyue Wang et autres

Vision-language-model (VLM)-guided reinforcement learning (RL) has recently attracted significant attention for it, replacing brittle hand-crafted rewards with semantically grounded signals; however, deploying such simulation-trained policies on real vehicles remains a fundamental challenge, because they rely on simulator-native observations and simulator-coupled action semantics …

Sim2Real-AD: A Modular Sim-to-Real Framework for Deploying VLM-Guided Reinforcement Learning in Real-World Autonomous Driving

Zilin Huang, Zhengyang Wan, Zihao Sheng, Boyue Wang et autres

Vision-language-model (VLM)-guided reinforcement learning (RL) has recently attracted significant attention for it, replacing brittle hand-crafted rewards with semantically grounded signals; however, deploying such simulation-trained policies on real vehicles remains a fundamental challenge, because they rely on simulator-native observations and simulator-coupled action semantics …

Emergency Events Traffic Flow Forecasting Using Text-Prompt-Guided Multimodal Large Language Models

Yujie Lu, Guangyu Huo, Xiaohui Cui, Boyue Wang et autres

Emergency events like traffic accidents and natural disasters frequently cause severe disruptions to urban traffic patterns, posing challenges to conventional forecasting methods based on historical data. Recent progress has explored integrating auxiliary textual information from social media, news reports, and incident details …

cn (code pays fourni par la source)

MARE: Multimodal Analogical Reasoning for Disease Evolution-Aware Radiology Report Generation

Qingqing Gao, Tengfei Liu, Xiaoyan Li, Xiaodan Zhang et autres

Radiology report generation from longitudinal medical data is critical for assessing disease progression and automating diagnostic workflows. While recent methods incorporate longitudinal information, they primarily rely on multimodal feature fusion, with limited capacity for explicit disease evolution modeling and temporal reasoning. To …

cn (code pays fourni par la source)