Privacy-preserving machine learning: Threats and solutions
Unknown
This paper bridges the knowledge gap between ML and privacy communities by surveying threats and solutions for privacy-preserving machine learning.
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 bridges the knowledge gap between ML and privacy communities by surveying threats and solutions for privacy-preserving machine learning.
Unknown
This paper provides a comprehensive exploration of LLM evaluation from a metrics perspective, offering a pragmatic guide for effective metric selection.
Zhisheng Chen
This study addresses algorithmic discrimination in AI-enabled recruitment, proposing technical and managerial solutions to mitigate bias.
Ranjan Sapkota, Konstantinos I. Roumeliotis, Manoj Karkee
This review distinguishes AI Agents from Agentic AI, providing a taxonomy, application mapping, and analysis of challenges and solutions.
Rui Wang, Hongru Wang, Boyang Xue, et al.
This survey analyzes reasoning economy in LLMs, covering causes of inefficiency, behavior patterns, and solutions to balance performance and computational costs.
Bozheng Dou, Zailiang Zhu, Ekaterina Merkurjev, et al.
This review summarizes machine learning and deep learning solutions for small data challenges in molecular science, covering both basic and advanced techniques.
Karl R. Weiss, Taghi M. Khoshgoftaar, Dingding Wang
This survey formally defines transfer learning, reviews current solutions and applications, and discusses future work for big data environments.
Léonard Boussioux, Jacqueline N. Lane, Miaomiao Zhang, et al.
Human-AI collaborative solutions for creative problem-solving show superior strategic viability and quality over human-only ideas, though human ideas are more novel.
Unknown
rStar-Coder constructs a large-scale verified dataset of 418K competition-level code problems with 580K long-reasoning solutions to improve LLM code reasoning.
Unknown
V-STaR iteratively improves LLM reasoning by training a DPO verifier on correct and incorrect solutions, boosting generator and verifier performance.
Unknown
DeepMath-103K is a large-scale dataset of 103K challenging math problems with verifiable answers and diverse solutions for training reasoning models.
Unknown
Eagle systematically explores the design space for multimodal LLMs using a mixture of vision encoders and resolutions, revealing key principles for effective fusion.