Accelerating AI for science: open data science for science
Unknown
This paper presents a research agenda for AI for science, focusing on building technical foundations to leverage data for scientific discovery.
A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
This paper presents a research agenda for AI for science, focusing on building technical foundations to leverage data for scientific discovery.
Unknown
A survey of the mathematical foundations of geometric deep learning, focusing on group equivariant and gauge equivariant neural networks.
Unknown
This book part establishes foundational concepts and modern approaches for multi-agent reinforcement learning, defining the learning problem and building upon prior work.
Unknown
This survey provides a comprehensive overview of generative diffusion models, covering their theoretical foundations, key methodologies, and applications in computer vision.
Unknown
This survey systematically reviews the data foundations of long-context language models, covering data sources, curation strategies, and their impact on model performance.
Priyanka Kargupta, S. Li, Haocheng Wang, et al.
This paper synthesizes cognitive science into a taxonomy of 28 cognitive elements, evaluates 192K LLM traces across modalities, and develops test-time guidance improving performance by up to 66.7%.
Cynthia Dwork, Aaron Roth
This monograph provides a thorough introduction to differential privacy, covering its definition, fundamental techniques, and applications in query-release, mechanism design, and machine learning.
Zhi‐Hua Zhou
A comprehensive textbook covering ensemble methods including Boosting, Bagging, Random Forest, and diversity measures.
Kenneth P. Burnham, David R. Anderson
This paper clarifies the philosophical and statistical foundations of AIC versus BIC for model selection and advocates for multimodel inference including model averaging.
Unknown
This survey explores the foundations, challenges, and future directions of neuro-symbolic methods integrated with agentic foundation models for computer use agents.
Unknown
This paper introduces Opencua, an open framework for building computer-use agents that leverage vision-language models to automate diverse computer tasks.