From the 1 of 16 papers with an AI index.
12 citations
- Xiamen UniversityCN10 papers
- Peking UniversityCN3 papers
- Astronomy and SpaceAU2 papers
- Astrophysique, Instrumentation et ModélisationFR2 papers
- CEA Paris-SaclayFR2 papers
- Centre National de la Recherche ScientifiqueFR2 papers
- Chinese Academy of SciencesCN2 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR2 papers
- Huazhong University of Science and TechnologyCN2 papers
- Institute of SoftwareCN2 papers
- Kavli Institute for Theoretical SciencesCN2 papers
- Nanjing UniversityCN2 papers
16 papers
OPERA: Offline Policy-guided Expert Routing and Adaptation for Universal Biomedical Image Analysis
Zihan Li, Feiyang Liu, Dandan Shan +2
Biomedical image analysis spans diverse modalities and tasks, yet real-world deployment is hindered by severe distribution shifts across scanners, protocols, and patient population…
Fe-doping-induced band structure modification and cryogenic phase stability in Cs2AgBiBr6 single crystals
Yanan Li, Xuejiao Wu, Jidong Deng +1
Despite its promise as a lead-free alternative, the practical application of Cs2AgBiBr6 in optoelectronics is limited by its wide band gap and detrimental intrinsic defects. To ove…
Megaparsec-Scale Neutral Hydrogen Flows in the Neighborhood of Hickson Compact Group 100
Qingzheng Yu, Taotao Fang, Enrico M. Di Teodoro +2
The evolution of galaxies is strongly influenced by their ability to exchange gas with their surroundings, yet direct observational constraints on these processes remain scarce. Us…
The TopCoW Challenge -- Topology-Aware Circle of Willis Segmentation for CT and MR Angiography
Kaiyuan Yang, Fabio Musio, Yihui Ma +112
The paper introduces the TopCoW Challenge, a benchmark for automatically segmenting the Circle of Willis in CT and MR angiography using deep learning, and provides a new annotated…
Learning Robot Visual Navigation in Crowds via Intention-Aware Scene Representations
Han Bao, Bingyi Xia, Hanjing Ye +5
Robot crowd navigation requires the ability to infer human intentions while accounting for the structural constraints of the environment. Currently, deep reinforcement learning (DR…
Federated Learning with Enhanced Privacy via Model Splitting and Random Client Participation
Yiwei Li, Shuai Wang, Zhuojun Tian +2
Federated Learning (FL) often adopts differential privacy (DP) to protect client data, but the added noise required for privacy guarantees can substantially degrade model accuracy.…