Quantum adversarial machine learning: from classical adaptations to quantum-native methods [0.03%]
从经典适应方法到本地量子方法的量子对抗机器学习
Roozbeh Razavi-Far,Mohammad Meymani,Erfan Mahmoudinia et al.
Roozbeh Razavi-Far et al.
Machine learning has revolutionized numerous industrial domains. Despite recent advances, machine learning models remain vulnerable to adversarial threats. Adversarial machine learning is a field that studies these vulnerabilities to build ...
Super greedy trees [0.03%]
超级贪婪树
Hemant Ishwaran
Hemant Ishwaran
We introduce Super Greedy Trees (SGTs), a decision-tree framework that extends CART by constructing tree splits from lasso-penalized parametric models. At each tree node, a model fitted to the local data induces an adaptive multivariate geo...
Artificial neural networks fighting real neural decline: a systematic review of AI in Alzheimer's research [0.03%]
人工神经网络对抗真正的神经衰退：阿尔茨海默病研究中AI的系统性回顾
Farzana Sharmin Mou,Tanvir Ahmed,Md Nazmul Huda et al.
Farzana Sharmin Mou et al.
Alzheimer's disease (AD) is a major global health challenge, with Artificial Intelligence (AI) increasingly recognized as a transformative tool for early detection, disease progression modeling, and therapeutic discovery. This systematic re...
Topological data analysis and topological deep learning beyond persistent homology: a review [0.03%]
持久同源下拓扑数据分析与拓扑深度学习综述
Zhe Su,Xiang Liu,Layal Bou Hamdan et al.
Zhe Su et al.
Topological data analysis (TDA) is a rapidly evolving field in applied mathematics and data science that leverages tools from topology to uncover robust, shape-driven, and explainable insights in complex datasets. The main workhorse is pers...
Advances in artificial intelligence: a review for the creative industries [0.03%]
人工智能的发展：创意产业的回顾与研究
Nantheera Anantrasirichai,Fan Zhang,David Bull
Nantheera Anantrasirichai
Artificial intelligence (AI) has undergone transformative advances since 2022, particularly through generative AI, large language models (LLMs), and diffusion models, fundamentally reshaping the creative industries. However, existing review...
Exploring unanswerability in machine reading comprehension: approaches, benchmarks, and open challenges [0.03%]
探索阅读理解中不可回答性：方法、基准和公开挑战
Hadiseh Moradisani,Fattane Zarrinkalam,Zeinab Noorian et al.
Hadiseh Moradisani et al.
The challenge of unanswerable questions in Machine Reading Comprehension (MRC) has drawn considerable attention, as current MRC systems are typically designed under the assumption that every question has a valid answer within the provided c...
Knowledge distillation and dataset distillation of large language models: emerging trends, challenges, and future directions [0.03%]
大型语言模型的知识蒸馏和数据集蒸馏：新兴趋势、挑战及未来方向
Luyang Fang,Xiaowei Yu,Jiazhang Cai et al.
Luyang Fang et al.
The exponential growth of Large Language Models (LLMs) continues to highlight the need for efficient strategies to meet ever-expanding computational and data demands. This survey provides a comprehensive analysis of two complementary paradi...
Validation is the central challenge for generative social simulation: a critical review of LLMs in agent-based modeling [0.03%]
验证是生成式社会模拟的核心挑战：对LLM在基于代理建模中的批判性审查
Maik Larooij,Petter Törnberg
Maik Larooij
Recent advances in Large Language Models (LLMs) have revitalized interest in Agent-Based Models (ABMs) by enabling "generative" simulations, with agents that can plan, reason, and interact through natural language. These developments promis...
Individual variable priority: a model-independent local gradient method for variable importance [0.03%]
个体变量优先级：一种模型无关的局部梯度变量重要性方法
Min Lu,Hemant Ishwaran
Min Lu
Traditional variable importance measures quantify overall feature contributions but often overlook individual-level heterogeneity. Several new procedures attempt to address this limitation but remain model dependent and may introduce biases...
Yi Dong,Ronghui Mu,Yanghao Zhang et al.
Yi Dong et al.
In the burgeoning field of Large Language Models (LLMs), developing a robust safety mechanism, colloquially known as "safeguards" or "guardrails", has become imperative to ensure the ethical use of LLMs within prescribed boundaries. This ar...