Search Results for author:
Found 5 papers, 4 papers with code
Every FLOP Counts: Scaling a 300B Mixture-of-Experts LING LLM without Premium GPUs
Ultimately, our experimental findings demonstrate that a 300B MoE LLM can be effectively trained on lower-performance devices while achieving comparable performance to models of a similar scale, including dense and MoE models.
FedLPPA: Learning Personalized Prompt and Aggregation for Federated Weakly-supervised Medical Image Segmentation
In such context, we propose a novel personalized FL framework with learnable prompt and aggregation (FedLPPA) to uniformly leverage heterogeneous weak supervision for medical image segmentation.
Unifying and Personalizing Weakly-supervised Federated Medical Image Segmentation via Adaptive Representation and Aggregation
The statistical heterogeneity (e. g., non-IID data and domain shifts) is a primary obstacle in FL, impairing the generalization performance of the global model.
YoloCurvSeg: You Only Label One Noisy Skeleton for Vessel-style Curvilinear Structure Segmentation
With only one noisy skeleton annotation (respectively 0. 14\%, 0. 03\%, 1. 40\%, and 0. 65\% of the full annotation), YoloCurvSeg achieves more than 97\% of the fully-supervised performance on each dataset.
BSDA-Net: A Boundary Shape and Distance Aware Joint Learning Framework for Segmenting and Classifying OCTA Images
Moreover, both low-level and high-level features from the aforementioned three branches, including shape, size, boundary, and signed directional distance map of FAZ, are fused hierarchically with features from the diagnostic classifier.
