Publications (15)
Quantum coherence and non-Markovianity of atom in dissipative cavity under weak measurement
Liu Yu, Zou Hong-Mei, Fang Mao-Fa
Quantum coherence and non-Markovianity of an atom in dissipative cavity under weak measurement are investigated in this work. We find that, the quantum coherence obviously depends…
Liaohe-CobotMagic-PnP: an Imitation Learning Dataset of Intelligent Robot for Industrial Applications
Chen Yizhe, Wang Qi, Hu Dongxiao +10
In Industry 4.0 applications, dynamic environmental interference induces highly nonlinear and strongly coupled interactions between the environmental state and robotic behavior. Ef…
Beyond Detection: A Structure-Aware Framework for Scene Text Tracking
Chenmin Yu, Liu Yu, Daiqing Wu +3
Modern visual object trackers show impressive results on general targets, yet their performance drops substantially when dealing with scene text. Although currently underexplored,…
Stateful protocol fuzzing with statemap-based reverse state selection
Liu Yu, Shen Yanlong, Zhou Ying
Stateful Coverage-Based Greybox Fuzzing (SCGF) is considered the state-of-the-art method for network protocol greybox fuzzing. During the protocol fuzzing process, SCGF constructs…
Study on electromagnetically induced transparency effects in Dirac and VO hybrid material structure
Di Ke, Xie Meng, Xia Hua Rong +3
In this paper, we present a metamaterial structure of Dirac and vanadium dioxide and investigate its optical properties using the finite-difference time-domain (FDTD) technique. Us…
Causally-Grounded Dual-Path Attention Intervention for Object Hallucination Mitigation in LVLMs
Liu Yu, Zhonghao Chen, Ping Kuang +4
Object hallucination remains a critical challenge in Large Vision-Language Models (LVLMs), where models generate content inconsistent with visual inputs. Existing language-decoder…
Memory-Augmented Reinforcement Learning Agent for CAD Generation
Yin Xiaolong, Liu Yu, Shen Jiahang +4
Automatic generation of computer-aided design (CAD) models is a core technology for enabling intelligence in advanced manufacturing. Existing generation methods based on large lang…
DRS-GUI: Dynamic Region Search for Training-Free GUI Grounding
Yichao Liu, Huawen Shen, Liu Yu +3
GUI agents powered by Multimodal Large Language Models (MLLMs) have demonstrated impressive capability in understanding and executing user instructions. However, accurately groundi…
Expert-Guided Multimodal Fusion for Unified Emotion and Sentiment Analysis
Jiaqi Qiao, Xiujuan Xu, Xinran Li +3
Multimodal emotion understanding requires the integration of heterogeneous data sources, including text, audio, and visual modalities, while simultaneously addressing discrete emot…
Development and validation of a short form of the medication literacy scale for Chinese College Students
Chen Zhenzhen, Ren Jiabao, Duan Tingyu +7
Medication literacy is integral to health literacy, pivotal for medication safety and adherence. It denotes an individual's capacity to discern, comprehend, and convey medication-r…
StyleTextGen: Style-Conditioned Multilingual Scene Text Generation
Zeyu Chen, Fangmin Zhao, Yan Shu +3
Style-conditioned scene text generation faces unique challenges in extracting precise text styles from complex backgrounds and maintaining fine-grained style consistency across cha…
Experimental determination of the propulsion matrix of the body of helical Magnetospirillum magneticum cells
Liu Yu, Lucas Le Nagard, Solomon Barkley +2
Helical-shaped magnetotactic bacteria provide a rare opportunity to precisely measure both the translational and rotational friction coefficients of micron-sized chiral particles.…
Bridging the Fairness Gap: Enhancing Pre-trained Models with LLM-Generated Sentences
Liu Yu, Ludie Guo, Ping Kuang +1
Pre-trained language models (PLMs) are trained on data that inherently contains gender biases, leading to undesirable impacts. Traditional debiasing methods often rely on external…
Dismantling Pathological Shortcuts: A Causal Framework for Faithful LVLM Decoding
Liu Yu, Can Chen, Ping Kuang +3
Large Vision-Language Models (LVLMs) exhibit sophisticated reasoning but remain susceptible to object hallucination. Deviating from the prevailing attention intensity assumption, w…
Transferring Vision-Language-Action Models to Industry Applications: Architectures, Performance, and Challenges
Shuai Li, Chen Yizhe, Li Dong +4
The application of artificial intelligence (AI) in industry is accelerating the shift from traditional automation to intelligent systems with perception and cognition. Vision langu…