Explanipedia

Decoding the Ear: A Framework for Objectifying Expressiveness from Human Preference Through Efficient Alignment Open

Zhiyu Lin, Jingwen Yang, Jiale Zhao, Meng Liu, Sunzhu Li , et al. · 2025

Recent speech-to-speech (S2S) models generate intelligible speech but still lack natural expressiveness, largely due to the absence of a reliable evaluation metric. Existing approaches, such as subjective MOS ratings, low-level acoustic fe…

What Do You Mean? Exploring How Humans and AI Interact with Symbols and Meanings in Their Interactions Open

Reza Habibi, Seung Wan Ha, Zhiyu Lin, Atieh Kashani, Ala Shafia , et al. · 2025

Meaningful human-AI collaboration requires more than processing language; it demands a deeper understanding of symbols and their socially constructed meanings. While humans naturally interpret symbols through social interaction, AI systems…

TransDeeplab: A Novel Architecture for Medical Image Segmentation Open

Zhiyu Lin, Lei Guo · 2025

Early and accurate diagnosis of brain tumors plays a critical role in improving patient prognosis. Magnetic Resonance Imaging (MRI) serves as the core diagnostic modality; however, the inherent heterogeneity of brain tumors and the complex…

Exploring the Behavioral Intentions of Hemodialysis Nursing Staff Using Intelligent Information Systems Open

Hui-Fang Tsai, Yun‐Chien Tseng, Zhiyu Lin, M.-J. Hsieh · 2025

This study aims to explore the intention of nursing staff at a dialysis center in a regional hospital in Taiwan to use a smart information system for hemodialysis. A cross-sectional study design was adopted, and data were collected through…

Research on the Impact of Fintech on Green Innovation of Enterprises Open

Zhiyu Lin · 2025

The study constructed regional fintech development level indicators based on the Baidu search index of fintech keywords in each province, and conducted an empirical analysis using relevant data of A-share listed companies from 2012 to 2021…

WebUIBench: A Comprehensive Benchmark for Evaluating Multimodal Large Language Models in WebUI-to-Code Open

Zhiyu Lin, Zhengda Zhou, Zhiyuan Zhao, Tao Wan, Yong Ma , et al. · 2025

LLMs Caught in the Crossfire: Malware Requests and Jailbreak Challenges Open

Haoyang Li, Huan Gao, Zhiyuan Zhao, Zhiyu Lin, Jing Gao , et al. · 2025

Debiasing Vision-Language Models with Text-Only Training Open

Yunfan Yang, Chaoquan Jiang, Zhiyu Lin, Jinlin Xiao, Jiaming Zhang , et al. · 2025

Debiasing Vison-Language Models with Text-Only Training Open

Yunfan Yang, Chaoquan Jiang, Zhiyu Lin, Jinlin Xiao, Jiaming Zhang , et al. · 2024

Pre-trained vision-language models (VLMs), such as CLIP, have exhibited remarkable performance across various downstream tasks by aligning text and images in a unified embedding space. However, due to the imbalanced distribution of pre-tra…

Beyond Following: Mixing Active Initiative into Computational Creativity Open

Zhiyu Lin, Upol Ehsan, Rohan Agarwal, Samihan Dani, Vidushi Vashishth , et al. · 2024

Generative Artificial Intelligence (AI) encounters limitations in efficiency and fairness within the realm of Procedural Content Generation (PCG) when human creators solely drive and bear responsibility for the generative process. Alternat…

Study on the effect of carbonation treatment on concrete wash water Open

Zhiyu Lin, Jiming Lin · 2024

Wash water is a by-product of ready-mixed concrete production and currently lacks scientific recycling measures due to its high alkalinity and suspended solids content. To address this issue, this project investigated a novel approach util…

External Model Motivated Agents: Reinforcement Learning for Enhanced Environment Sampling Open

Rishav Bhagat, Jonathan Balloch, Zhiyu Lin, Julia Kim, Mark Riedl · 2024

Unlike reinforcement learning (RL) agents, humans remain capable multitaskers in changing environments. In spite of only experiencing the world through their own observations and interactions, people know how to balance focusing on tasks w…

AIGCs Confuse AI Too: Investigating and Explaining Synthetic Image-induced Hallucinations in Large Vision-Language Models Open

Yifei Gao, Jiaqi Wang, Zhiyu Lin, Jitao Sang · 2024

The evolution of Artificial Intelligence Generated Contents (AIGCs) is advancing towards higher quality. The growing interactions with AIGCs present a new challenge to the data-driven AI community: While AI-generated contents have played a…

Highly selective electrocatalytic reduction of CO2 to HCOOH over an in situ derived Ag-loaded Bi2O2CO3 electrocatalyst Open

Wei Zheng, Changlai Wang, Jing Chen, Shi Chen, Zhiyu Lin , et al. · 2024

Ag/Bi 2 O 2 CO 3 generated during the carbonatization process in KHCO 3 electrolyte achieves a high faradaic efficiency toward HCOOH in a wide potential window.

An Ontology of Co-Creative AI Systems Open

Zhiyu Lin, Mark Riedl · 2023

The term co-creativity has been used to describe a wide variety of human-AI assemblages in which human and AI are both involved in a creative endeavor. In order to assist with disambiguating research efforts, we present an ontology of co-c…

Simulation analysis of electrical characteristics of P-gate enhanced HEMT with C-doped buffer layer Open

Xiao Wang, Zhiyu Lin, Yumin Zhang, Jianfeng Wang, Ke Xu · 2023

The C-doped P-gate-enhanced HEMT (PEHEMT) is simulated by using the Silvaco T-CAD tool. The interaction among the C acceptor trap, electron, and hole in the buffer layer at different voltages promotes interesting electrical characteristic …

Laser Photovoltaic Effect on InGaN / GaN MQWs Structure Photocells Open

Hengsheng Shan, Shengwei Liu, Zhiyu Lin, Xiaoya Li · 2023

In this paper, the laser photovoltaic effect of InGaN photocells under 405 nm, 450 nm, and 488 nm laser irradiation was studied. It found that the photovoltaic conversion efficiency of InGaN photocells gradually decreases with the increase…

A Controllable Co-Creative Agent for Game System Design Open

Rohan Agarwal, Zhiyu Lin, Mark Riedl · 2023

Many advancements have been made in procedural content generation for games, and with mixed-initiative co-creativity, have the potential for great benefits to human designers. However, co-creative systems for game generation are typically …

Different reverse leakage current transport mechanismsof planar Schottky barrier diodes(SBDs) on Sapphire and GaN Substrate Open

Xiao Wang, Zhiyu Lin, Yumin Zhang, Guoqiang Ren, Ke Xu · 2023

The effects of different substrates on the off state leakage current in gallium nitride planar diodes are experimentally demonstrated and studied by analyzing temperature-dependent current voltage characteristics.

Near-IR Embedded in a Physiological Signal Monitoring System Open

Chih‐Wei Peng, Chen‐Chia Chou, Zhiyu Lin, Jian‐Chiun Liou · 2023

Towards Black-box Adversarial Example Detection: A Data Reconstruction-based Method Open

Yifei Gao, Zhiyu Lin, Yunfan Yang, Jitao Sang · 2023

Adversarial example detection is known to be an effective adversarial defense method. Black-box attack, which is a more realistic threat and has led to various black-box adversarial training-based defense methods, however, does not attract…

Analyzing the Electrical Characteristics of P-gate Enhanced HEMT with C-doped Buffer Layer through Silvaco Open

Xiao Wang, Zhiyu Lin, Yumin Zhang, Jianfeng Wang, Ke Xu · 2023

The C-doped P-gate-enhanced HEMT (PEHEMT) is simulated by using the Silvaco T-CAD tool. The interaction among the C acceptor trap, electron and hole in the buffer layer at different voltages promotes interesting electrical characteristic w…

Beyond Prompts: Exploring the Design Space of Mixed-Initiative Co-Creativity Systems Open

Zhiyu Lin, Upol Ehsan, Rohan Agarwal, Samihan Dani, Vidushi Vashishth , et al. · 2023

Generative Artificial Intelligence systems have been developed for image, code, story, and game generation with the goal of facilitating human creativity. Recent work on neural generative systems has emphasized one particular means of inte…

Neuro-Symbolic World Models for Adapting to Open World Novelty Open

Jonathan Balloch, Zhiyu Lin, Robert Wright, Xiangyu Peng, Mustafa Hussain , et al. · 2023

Open-world novelty--a sudden change in the mechanics or properties of an environment--is a common occurrence in the real world. Novelty adaptation is an agent's ability to improve its policy performance post-novelty. Most reinforcement lea…

Efficacy and safety of lenvatinib versus sorafenib in first-line treatment of advanced hepatocellular carcinoma: A meta-analysis Open

Jia Luo, Benjian Gao, Zhiyu Lin, Hua Fan, Wen Ma , et al. · 2022

Objective Lenvatinib and sorafenib are first-line oral multikinase inhibitors approved for the treatment of advanced hepatocellular carcinoma (HCC). However, the choice of the primary therapeutic agent among these two remains controversial…

Artificial Intelligence Security Competition (AISC) Open

Yinpeng Dong, Peng Chen, Senyou Deng, L Lianji, Yi Sun , et al. · 2022

The security of artificial intelligence (AI) is an important research area towards safe, reliable, and trustworthy AI systems. To accelerate the research on AI security, the Artificial Intelligence Security Competition (AISC) was organized…

Comprehensive Assessment of Eutrophication in Xiamen Bay and Its Implications for Management Strategy in Southeast China Open

Yang Luo, Jinwen Liu, Jian Wu, Zheng Yuan, Jiwei Zhang , et al. · 2022

The eutrophication of coastal water has been a critical environmental problem in China’s offshore areas. How to effectively assess the status of coastal waters is key for pollution treatment and environmental protection. In recent years, e…

Creative Wand: A System to Study Effects of Communications in Co-Creative Settings Open

Zhiyu Lin, Rohan Agarwal, Mark Riedl · 2022

Recent neural generation systems have demonstrated the potential for procedurally generating game content, images, stories, and more. However, most neural generation algorithms are "uncontrolled" in the sense that the user has little say i…

Application of trans-sutural distraction osteogenesis based on an optical surgical navigation system to correct midfacial dysplasia Open

Yujie Chen, Shanshan Du, Zhiyu Lin, PeiYang Zhang, XinLing Zhang , et al. · 2022

Midfacial hypoplasia is a common maxillofacial deformity in patients with cleft lip and palate, which requires surgical treatment. However, trans-sutural distraction osteogenesis (TSDO) remains some disadvantages, including difficulty in a…

Investigating and Explaining the Frequency Bias in Image Classification Open

Zhiyu Lin, Yifei Gao, Jitao Sang · 2022

CNNs exhibit many behaviors different from humans, one of which is the capability of employing high-frequency components. This paper discusses the frequency bias phenomenon in image classification tasks: the high-frequency components are a…

Zhiyu Lin YOU? Author Swipe