11 citations · 21 across the 7 of their papers we have counts for
7 papers
Implicit In-context Learning
Zhuowei Li, Zihao Xu, Ligong Han +5
In-context Learning (ICL) empowers large language models (LLMs) to swiftly adapt to unseen tasks at inference-time by prefixing a few demonstration examples before queries. Despite…
DeFormer: Integrating Transformers with Deformable Models for 3D Shape Abstraction from a Single Image
Di Liu, Xiang Yu, Meng Ye +4
Accurate 3D shape abstraction from a single 2D image is a long-standing problem in computer vision and graphics. By leveraging a set of primitives to represent the target shape, re…
Training Like a Medical Resident: Context-Prior Learning Toward Universal Medical Image Segmentation
Yunhe Gao, Zhuowei Li, Di Liu +3
A major focus of clinical imaging workflow is disease diagnosis and management, leading to medical imaging datasets strongly tied to specific clinical objectives. This scenario has…
Steering Prototypes with Prompt-tuning for Rehearsal-free Continual Learning
Zhuowei Li, Long Zhao, Zizhao Zhang +4
In the context of continual learning, prototypes-as representative class embeddings-offer advantages in memory conservation and the mitigation of catastrophic forgetting. However,…
Towards Self-supervised and Weight-preserving Neural Architecture Search
Zhuowei Li, Yibo Gao, Zhenzhou Zha +4
Neural architecture search (NAS) algorithms save tremendous labor from human experts. Recent advancements further reduce the computational overhead to an affordable level. However,…
Contrastive and Selective Hidden Embeddings for Medical Image Segmentation
Zhuowei Li, Zihao Liu, Zhiqiang Hu +5
Medical image segmentation has been widely recognized as a pivot procedure for clinical diagnosis, analysis, and treatment planning. However, the laborious and expensive annotation…
Self-Ensembling Contrastive Learning for Semi-Supervised Medical Image Segmentation
Jinxi Xiang, Zhuowei Li, Wenji Wang +2
Deep learning has demonstrated significant improvements in medical image segmentation using a sufficiently large amount of training data with manual labels. Acquiring well-represen…