MAGE combines two key mechanisms: a novel multi-timescale attention mechanism, capable of learning representations across multiple temporal scales and a trainable aggregation module, that dynamically identifies and adapts to the most informative timescale of the input signal.
T. Doan, Van-Chien Nguyen, Trung-Hieu Tran et al.· 0 citations
This paper introduces COUPLED FLOW, a new neural operator learning framework for multi-physics PDE systems that captures the co-evolution of multiple physical processes by modeling their cross-process interactions. Unlike existing neural operator methods that primarily target single-physics settings, COUPLED FLOW emplo...
Trong Khiem Tran, Minh Long Bui, Phi Le Nguyen et al.· 0 citations
Histological whole-slide images (WSIs) are central to computational pathology but pose severe computational challenges due to their extremely high resolution, often spanning several gigabytes per slide. To enable scalable learning, existing methods apply self-supervised data condensation to reduce computational cost, b...
Duong M. Nguyen, T. Hoang, H. Nguyen et al.· 1 citation
A diffusion-inspired reconfiguration of transformers in which each feature transformation block is modeled as a probabilistic mapping that mimics the structure of a diffusion process, transporting data mass from the input distribution to the pre-trained feature distribution.
M. Dao, Quang Pham, Phi Le Nguyen et al.· arXiv.org· 0 citations
This paper formulates uplink MPQUIC scheduling as a multi-objective optimization problem that jointly considers maximum upload completion time and total LTE usage and proposes a Bayesian Optimization-based framework that treats the MPQUIC system as a black box and systematically explores probabilistic path selection co...
T. Nguyen, T. Lê, Phi Le Nguyen et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.