Male factors account for almost half of all infertility cases and afflict approximately 186 million men globally, presenting a substantial and increasing public health burden. Semen analysis is the standard of care for assessing male fertility, but subjective visual interpretation results in > 25–30% inter-observer var...
ElasticScale is presented, an elastic orchestration system that organizes heterogeneous accelerators into disaggregated rollout and trainer instances, via a HeterogeneousRayWorkerGroup abstraction that manages non-uniform hardware topologies and a multi-instance Federated Weight Averaging protocol that aggregates updat...
Wei-An Lin, M. Reza, Talha Nayyar et al.· 0 citations
The prototype demonstrates a practical institution-local distributed file system (DFS) for content-addressed acquisition staging that supports verifiable digital collection objects and a federated storage model for collaborating GLAM institutions.
Joachim Snellings, Jasper Funk-Smit, Margot Belot et al.· 0 citations
This work proposes the graph-based learning individual intrinsic reward heterogeneous-agent proximal policy optimization (GLIIR-HAPPO) algorithm, a novel heterogeneous multi-agent reinforcement learning (MARL) framework that fundamentally overcomes this impasse by systematically decomposing the original coupled optimiz...
Bo-Kai Xu, Jia-Yi Zhang, Shuai-Fei Chen et al.· 0 citations
A federated Bayesian protocol for learning population-scale adverse-event surveillance as a distinct belief layer of the surgical digital twin is proposed, and a federated Bayesian protocol for learning it under formal privacy guarantees is evaluated.
This work quantifies privacy posture with k-anonymity, l-diversity and t-closeness, aggregate them into a composite Privacy-Posture Index (PPI), and measures residual re-identification across eight transformation configurations on internal PCAP captures and the public Idaho Labs 5GAD corpus.
Nikolaos Kekatos, Apostolos Valiakos, Alexios Lekidis et al.· 0 citations
TwinFedSeg, a federated learning framework guided by an anatomical twin state for multimodal medical image segmentation, is proposed, which consistently outperforms representative federated methods.
Hao-Ran Zhou, Ying-Zhi Qin, Peng-Fei Mu et al.· IEEE journal of biomedical a...· 0 citations
MediNet is a comprehensive server-client Federated learning (FL) platform that allows hospitals and research centers to train Machine Learning (ML) and DL models without moving or exposing sensitive data.
Ramon Mateo-Navarro, David Sarrat-González, Dolors Pelegrí-Sisó et al.· Bioinformatics· 0 citations
Skin cancer is a major global health concern, and early detection and accurate lesion delineation are important for effective diagnosis and treatment planning. Automated skin lesion analysis can assist dermatologists, with lesion segmentation serving as a fundamental step in computer-aided diagnostic systems. Conventio...
Conventional decentralized federated learning (DFL) often focuses on clients, with each client maintaining a model copy, performing updates individually, and undertaking model exchange and integration. While fully leveraging computational resources can shorten training times, it can also lead to significant computation...
Kota Maejima, Takayuki Nishio, Asato Yamazaki et al.· 0 citations
A PRISMA-based Systematic Literature Review was conducted to synthesize evidence from 37 peer-reviewed studies focusing on blockchain-enabled federated learning for healthcare data privacy, security, and preservation, indicating that the integration of blockchain and federated learning offers significant potential for...
Ismail Abdulatiff Mohammed, M. Rusli, Salman Yussof et al.· Discover Computing· 0 citations
Students in MIT’s Concourse program delve deeply into the human condition, debate challenging questions, and learn to develop judgment about issues that can’t be quantified.
Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it easier to improve them without rebuilding them. The post Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduOct 6, 2026
