Results 131 to 140 of about 30,335 (256)

Community-Invariant Graph Contrastive Learning

Graph augmentation has received great attention in recent years for graph contrastive learning (GCL) to learn well-generalized node/graph representations. However, mainstream GCL methods often favor randomly disrupting graphs for augmentation, which shows limited generalization and inevitably leads to the corruption of high-level graph information, i.e.
Tan, Shiyin, Li, Dongyuan, Jiang, Renhe, Zhang, Ying, Okumura, Manabu   +4 more
openaire   +2 more sources

Vision‐Augmented Wearable Interfaces: Bioinspired Approaches for Realistic AI‐Human‐Machine Interaction

Advanced Materials Technologies, EarlyView.
This review presents recent progress in vision‐augmented wearable interfaces that combine artificial vision, soft wearable sensors, and exoskeletal robots. Inspired by biological visual systems, these technologies enable multimodal perception and intelligent human–machine interaction.
Jihun Lee, Gwuidong Ryu, Kisoo Kim, Feng Xu, Won Gu Lee   +4 more
wiley   +1 more source

Model-Driven Graph Contrastive Learning

We propose $\textbf{MGCL}$, a model-driven graph contrastive learning (GCL) framework that leverages graphons (probabilistic generative models for graphs) to guide contrastive learning by accounting for the data's underlying generative process. GCL has emerged as a powerful self-supervised framework for learning expressive node or graph representations
Azizpour, Ali, Zilberstein, Nicolas, Segarra, Santiago   +2 more
openaire   +2 more sources

TopoGCL: Topological Graph Contrastive Learning

Proceedings of the AAAI Conference on Artificial Intelligence
Graph contrastive learning (GCL) has recently emerged as a new concept which allows for capitalizing on the strengths of graph neural networks (GNNs) to learn rich representations in a wide variety of applications which involve abundant unlabeled information. However, existing GCL approaches largely tend to overlook the important latent information on
Chen, Yuzhou, Frias, Jose, Gel, Yulia R.
openaire   +2 more sources

Hierarchical Multi‐Material Architectures With Gradient Design for Dynamic‐Range Flexible Tactile Sensing

Advanced Materials Technologies, EarlyView.
Hierarchical multi‐material TPMS lattices are engineered as flexible tactile sensors by combining soft and stiff elastomeric layers with a conformal conductive coating. The bilayer architecture delivers sensitivity at low pressures while maintaining a broad detectable range under large loads, enabling reliable pressure and vibration monitoring for ...
Reza Noroozi, Domenic Quiquero, Yan Yan Shery Huang, HaoTian Harvey Shi   +3 more
wiley   +1 more source

Optical Diversity and Nanostructural Organization in the Colored Scales of Sternotomis

Advanced Optical Materials, EarlyView.
Vivid colors in Sternotomis beetles originate from nanoscale photonic architectures embedded within individual scales. Here, we provide a comparative optical and structural analysis of 57 scale types that reveal how ordered, quasi‐ordered, and disordered 3D networks tune color, saturation, and angular response.
Viola Bauernfeind, Viola V. Vogler‐Neuling, Ilja Gunkel, Primož Pirih, Ullrich Steiner, Bodo D. Wilts   +5 more
wiley   +1 more source

Scalable Task Planning via Large Language Models and Structured World Representations

Advanced Robotics Research, EarlyView.
This work efficiently combines graph‐based world representations with the commonsense knowledge in Large Language Models to enhance planning techniques for the large‐scale environments that modern robots will need to face. Planning methods often struggle with computational intractability when solving task‐level problems in large‐scale environments ...
Rodrigo Pérez‐Dattari, Zhaoting Li, Robert Babuška, Jens Kober, Cosimo Della Santina   +4 more
wiley   +1 more source

AI‐Powered Framework for Evaluating Drug Efficacy for Three‐Dimensional In Vitro Cancer Models in Robot‐Assisted Production

Advanced Robotics Research, EarlyView.
An AI‐powered, robot‐assisted framework automatically produces, images, and analyzes 3D tumor spheroids to evaluate drug efficacy. Integrated modules handle spheroid formation, live/dead staining, brightfield imaging, and automated image analysis, including spheroid segmentation, viability and metrics to assess the drug treatment efficacy. The workflow
Dalia Mahdy, Jesus Nieves, Lukas Königer, Matthias Peindl, Fabio Erhard, Marc Möllmann, Anke Klingner, Markus Münig, Bibin Babu, Thomas Schwarz, Marco Metzger, Gudrun Dandekar, Maximiliane Wußmann, Jan Hansmann   +13 more
wiley   +1 more source

Grounding Large Language Models for Robot Task Planning Using Closed‐Loop State Feedback

Advanced Robotics Research, EarlyView.
BrainBody‐Large Language Model (LLM) introduces a hierarchical, feedback‐driven planning framework where two LLMs coordinate high‐level reasoning and low‐level control for robotic tasks. By grounding decisions in real‐time state feedback, it reduces hallucinations and improves task reliability.
Vineet Bhat, Ali Umut Kaypak, Prashanth Krishnamurthy, Ramesh Karri, Farshad Khorrami   +4 more
wiley   +1 more source

Dual-level graph contrastive collaborative filtering

Scientific Reports
The latest research positions graph-based collaborative filtering as an effective strategy in recommendation systems, enabling the analysis of user preferences via user-item interaction graphs.
Jiahao Wang, Qingshuai Wang, Kai Ma, Noor Farizah Ibrahim, Zurinahni Zainol   +4 more
doaj   +1 more source