Comprehensive Survey
Comprehensive surveys in various scientific fields systematically review existing research, aiming to synthesize key findings, identify gaps, and guide future directions. Current research focuses on evaluating and improving the trustworthiness, efficiency, and bias mitigation of models across diverse domains, including large language models, image generation, and autonomous systems. These surveys are crucial for advancing understanding within specific subfields and facilitating the development of more robust and reliable technologies with broader practical applications.
Papers
A Practical Survey on Emerging Threats from AI-driven Voice Attacks: How Vulnerable are Commercial Voice Control Systems?
Yuanda Wang, Qiben Yan, Nikolay Ivanov, Xun Chen
Topological Data Analysis for Neural Network Analysis: A Comprehensive Survey
Rubén Ballester, Carles Casacuberta, Sergio Escalera
A Comprehensive Survey on Multi-modal Conversational Emotion Recognition with Deep Learning
Yuntao Shou, Tao Meng, Wei Ai, Nan Yin, Keqin Li
Evaluating Large Language Models: A Comprehensive Survey
Zishan Guo, Renren Jin, Chuang Liu, Yufei Huang, Dan Shi, Supryadi, Linhao Yu, Yan Liu, Jiaxuan Li, Bojian Xiong, Deyi Xiong
AI Alignment: A Comprehensive Survey
Jiaming Ji, Tianyi Qiu, Boyuan Chen, Borong Zhang, Hantao Lou, Kaile Wang, Yawen Duan, Zhonghao He, Jiayi Zhou, Zhaowei Zhang, Fanzhi Zeng, Kwan Yee Ng, Juntao Dai, Xuehai Pan, Aidan O'Gara, Yingshan Lei, Hua Xu, Brian Tse, Jie Fu, Stephen McAleer, Yaodong Yang, Yizhou Wang, Song-Chun Zhu, Yike Guo, Wen Gao