Results 121 to 130 of about 38,613 (267)

Zero-shot Decentralized Federated Learning

2025 International Joint Conference on Neural Networks (IJCNN)
CLIP has revolutionized zero-shot learning by enabling task generalization without fine-tuning. While prompting techniques like CoOp and CoCoOp enhance CLIP's adaptability, their effectiveness in Federated Learning (FL) remains an open challenge. Existing federated prompt learning approaches, such as FedCoOp and FedTPG, improve performance but face ...
Masano A., Pennisi M., Salanitri F. P., Spampinato C., Bellitto G.   +4 more
openaire   +3 more sources

Bioinspired Adaptive Surfaces for Intelligent Liquid Manipulation: Progressing From Passive and Active to Hybrid Strategies

Advanced Materials, EarlyView.
This review examines passive, active, and hybrid liquid manipulation strategies, highlighting hybrid approaches as an emerging route to reconcile energy efficiency with adaptive control. By actively reconstructing passive surfaces to store programmable interfacial energy, hybrid systems enable flexible yet low‐power liquid transport, with perspectives ...
Jiaqi Miao, Yiyuan Zhang, Liqiu Wang, Alan C. H. Tsang   +3 more
wiley   +1 more source

From Fiber Bundles to Architected Membranes: Triply Periodic Minimal Surface Architectures for Biohybrid Artificial Lungs

Advanced Materials, EarlyView.
Additively manufactured triply periodic minimal surface (TPMS) membranes offer an architecture‐driven alternative to hollow fiber bundles in artificial lungs. Multiphysics simulations and endothelialized prototypes show that the 3D‐printable membrane architecture improves gas exchange, blood flow distribution, and hemocompatibility, enabling ...
Michael Pflaum, Kai P. Barbian, Florian Neuhaus, Gerrit Sitarz, Carolin Nölke, Sebastian V. Jansen, John Linkhorst, Lukas T. Hirschwald, Sebastian Brosch, Christian Certa, Ulrich Steinseifer, Matthias Wessling, Jutta Arens, Arjang Ruhparwar, Bettina Wiegmann   +14 more
wiley   +1 more source

PointBLIP: Zero-Training Point Cloud Classification Network Based on BLIP-2 Model

Remote Sensing
Leveraging the open-world understanding capacity of large-scale visual-language pre-trained models has become a hot spot in point cloud classification. Recent approaches rely on transferable visual-language pre-trained models, classifying point clouds by
Yunzhe Xiao, Yong Dou, Shaowu Yang
doaj   +1 more source

Origin of Dark Current Robustness in Photomultiplication Organic Photodetectors Enabled by Ionic Conjugated Electron‐Blocking Layers

Advanced Materials, EarlyView.
Ionic conjugated polyelectrolyte electron‐blocking layers enable photomultiplication organic photodetectors with dark current robustness up to −10 V and external quantum efficiencies exceeding 3000%. Fowler–Nordheim tunneling, interfacial dipole, trap density of states, and noise analyses reveal how ionic conjugated polyelectrolytes suppress electron ...
Yelim Kang, Min Hun Jee, Shuai Zhang, Sang Heon Lee, Jung Min Ha, Xingchao Zhao, Xiaoling Ma, Huiseong Shin, Changhwan Shin, Soonyong Lee, Fujun Zhang, Jae Won Shim, Han Young Woo   +12 more
wiley   +1 more source

Zero‐shot insect detection via weak language supervision

Plant Phenome Journal
Cheap and ubiquitous sensing has made collecting large agricultural datasets relatively straightforward. These large datasets (for instance, citizen science data curation platforms like iNaturalist) can pave the way for developing powerful artificial ...
Benjamin Feuer, Ameya Joshi, Minsu Cho, Shivani Chiranjeevi, Zi Kang Deng, Aditya Balu, Asheesh K. Singh, Soumik Sarkar, Nirav Merchant, Arti Singh, Baskar Ganapathysubramanian, Chinmay Hegde   +11 more
doaj   +1 more source

Data‐Driven Materials Science for Energy‐Sustainable Applications

Advanced Materials, EarlyView.
Data‐driven approaches powered by artificial intelligence are transforming materials discovery for energy sustainability. This review examines how auto‐generated high‐quality materials databases and domain‐specific language models accelerate research in photovoltaics, thermoelectrics, batteries and magnetic materials. Applications involve extraction of
Jacqueline M. Cole
wiley   +1 more source

Zero-Shot Visual Sentiment Prediction via Cross-Domain Knowledge Distillation

IEEE Open Journal of Signal Processing
There are various sentiment theories for categorizing human sentiments into several discrete sentiment categories, which means that the theory used for training sentiment prediction methods does not always match that used in the test phase. As a solution
Yuya Moroto, Yingrui Ye, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama   +4 more
doaj   +1 more source

On Zero-Shot Reinforcement Learning

CoRR
Modern reinforcement learning (RL) systems capture deep truths about general, human problem-solving. In domains where new data can be simulated cheaply, these systems uncover sequential decision-making policies that far exceed the ability of any human.
openaire   +2 more sources

S‐Nitrosothiols as Thiol‐Protecting Groups for Controlled Thiol‐Maleimide Crosslinking of Homogeneous Soft Hydrogels

Advanced Materials, EarlyView.
Rapid thiol‐maleimide addition frequently outpaces mixing, resulting in heterogeneous hydrogels. S‐nitrosothiols act as thiol‐protecting groups, allowing uniform mixing with maleimide‐functionalized polymers before gelation. Sodium thiosulfate or sodium ascorbate then regenerates thiols on demand, triggering controlled thiol‐maleimide crosslinking ...
Julian A. Serna, Michelle J. Iwohn, Maximilian Seifermann, Stefan Heißler, Maike Schliephake, Franziska Dopp, Claudia Muhle‐Goll, Pavel A. Levkin   +7 more
wiley   +1 more source