7 papers · ranked by Valyu relevance
Mohamed Selmy, A. Abdulnabi, A. A. Ali, E. M. Saied + 1 more
Nanogrids have emerged as a crucial solution for contemporary residential power systems, providing a robust framework for integrating distributed energy resources (DERs), comprising solar photovoltaics (PVs), wind turbines (WTs), energy storage systems (ESSs), and diesel generators (DGs). However, the uncertainty of…
Xiaoyue Hu, Yuhao Ma, Ruixing Ming, Heping Zhang + 1 more
Identifying essential biomarkers remains a core challenge in elucidating the pathogenic mechanisms and achieving precise diagnosis of complex diseases. Deep neural networks offer immense predictive power, yet their lack of interpretability severely limits downstream biological insight. Here, we introduce DeepVaris, an…
Odin Zhang, Jiaqi Wang, Tuscan Rock Thompson, Ziyi You + 3 more
Biomolecular interactions, including protein–protein interactions, protein–nucleic acid recognition, and protein–small molecule binding, underlie a wide range of biological processes and therapeutic mechanisms. Although recent de novo design methods can generate candidate binders for diverse molecular targets…
Fabio Cumbo, Kabir Dhillon, M. Hassan Najafi, Sercan Aygun + 1 more
The exponential growth of genomic databases necessitates alignment-free methods for comparing genomes. While MinHash-based tools have revolutionized this field by efficiently estimating the Average Nucleotide Identity based on k-mer sets, they inherently discard structural genomic information. We introduce HyperSketch…
Matteo Farina, Pietro Zamberlan, Arno Onken, Ulisse Ferrari
For datasets with thousands of neurons and images, vision transformers have proven successful at predicting neural responses to stimuli. However, they are expected to underperform in low-data regimes, where CNNs and Gaussian processes are considered more effective. We ask whether transformers can be made competitive…
Junjie Yao, Zhongxu Li, Cuiping Wang, Junyu Wu + 3 more
A motion control strategy based on multi-source heterogeneous motion information fusion and motion decoupling parallel washout algorithm (WA) is proposed for the control of a rehabilitation robot designed for stroke-related balance disorders. The robot features a serial-parallel hybrid structure and humanoid gait…
Hao Ding, Nannan Wu, Tianyi Qiu
DNA foundation models such as Evo2 7B adopt hybrid Hyena/attention architectures (Striped-Hyena2) whose single-stream autoregressive decoding is bounded by weight bandwidth at ∼45 tok/s. Speculative decoding on such hybrids faces a systems problem that prior SSM work solves only partially: after a draft is verified…