我们的工作：
[1] Our new amazing work! 大模型的出现颠覆了人类使用工具的方式。我们提出ScreenAgent，首次探索在无需辅助定位标签的情况下，利用 VLM Agent 直接控制电脑鼠标和键盘，实现大模型直接操控电脑的目标。该工作是对人机交互方式的一次全新探索，同时开源了具备精准定位信息的数据集、控制器、训练代码等。欢迎大家阅读，转发和指正！
论文地址：https://arxiv.org/abs/2402.07945; 项目地址：https://github.com/niuzaisheng/ScreenAgent
已发表论文:
[1] ScreenAgent: A Vision Language Model-driven Computer Control Agent, International Joint Conference on Artificial Intelligence (IJCAI), 2024.07, CCF-A
[2] CVTGAD: Simplified Transformer with Cross-View Attention for Unsupervised Graph-Level Anomaly Detection, European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2023)，pp.185-200，2023.09，CCF-B, 机器学习旗舰会议
[3] ATTEXPLAINER: Explain Transformer via Attention by Reinforcement Learning, International Joint Conference on Artificial Intelligence (IJCAI)，pp.724–731，2022.07，CCF-A
[4] Contrastive Learning for Extracting Transferable User Profiles in Cross-Domain Recommendation System，The International Joint Conference on Neural Networks (IJCNN), 2024.06, 清华推荐B类会议
[5] Wang Qi, Zhao W, Yang J, Jia W, Shan X, Qianli Xing, Philp S. Yu. C-DeepTrust: A Context-aware Deep Trust Prediction Model in Online Social Networks. IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2021. Full paper, Accepted. CORE Rank A*, JCR: Q1, IF= 10.451, CCF B.
[6] Wang Qi, Zhao W, Yang J, Jia W, Chuan Zhou, Qianli Xing. AtNE-Trust: Attributed Trust Network Embedding for Trust Prediction in Online Social Networks. IEEE International Conference on Data Mining (ICDM), Sorrento, Italy, November, 2020. Full paper, CORE Rank A*, CCF B, Acceptance Rate: 9. 81%.
[7] Wang Qi, Zhao W, Yang J, Jia W, Wenbin H, Qianli Xing. DeepTrust: A Deep User Model of Homophily Effect for Trust Prediction. IEEE International Conference on Data Mining (ICDM), Beijing, China, November, 2019. Full paper, CORE Rank A*, CCF B, Acceptance Rate: 9.08%.
[8] Qianli Xing, Weiliang Zhao, Jian Yang, Jia Wu, and Qi Wang. TWLR: A Novel Truth Inference Approach based on Worker Representations for Crowdsourcing in the Low Redundancy Situation, IEEE International Conference on Web Services (ICWS), Virtual, September, 2021. Full paper, CORE Rank A, CCF B, Acceptance Rate: 23.7%.
[9] Qianli Xing, Weiliang Zhao, Jian Yang, Jia Wu, and Qi Wang. WorP: A Novel Worker Performance Prediction Model for General Tasks on Crowdsourcing Platforms, IEEE International Conference on Web Services (ICWS), Virtual, September, 2021. Short paper, CORE Rank A, CCF B, Acceptance Rate: 23.7%.
[10] Qianli Xing, Weiliang Zhao, Jian Yang, Jia Wu, and Qi Wang. PB-Worker: A Novel Participating Behavior-based Worker Ability Model for General Tasks on Crowdsourcing Platforms. IEEE International Conference on Web Services (ICWS), Beijing, China, October, 2020. Full paper, CORE Rank A, CCF B, Acceptance Rate: 18.1%.
[11] Qianli Xing, Weiliang Zhao, Jian Yang, Jia Wu, Qi Wang, and Mei Wang. Groexpert: A novel group-aware experts identification approach in crowdsourcing, International Conference on Web Information Systems Engineering (WISE), Hong Kong, China, January, 2020. Full paper, CORE Rank A, CCF C, Acceptance Rate: 23%.
