6 papers
Exploring the Impact of Parameter Update Magnitude on Forgetting and Generalization of Continual Learning
JinLi He, Liang Bai, Xian Yang
The magnitude of parameter updates are considered a key factor in continual learning. However, most existing studies focus on designing diverse update strategies, while a theoretic…
Understanding the Role of Rehearsal Scale in Continual Learning under Varying Model Capacities
JinLi He, Liang Bai, Xian Yang
Rehearsal is one of the key techniques for mitigating catastrophic forgetting and has been widely adopted in continual learning algorithms due to its simplicity and practicality. H…
LLM-Guided Diagnostic Evidence Alignment for Medical Vision-Language Pretraining under Limited Pairing
Huimin Yan, Liang Bai, Xian Yang +1
Most existing CLIP-style medical vision--language pretraining methods rely on global or local alignment with substantial paired data. However, global alignment is easily dominated…
Bipartite Graph Attention-based Clustering for Large-scale scRNA-seq Data
Zhuomin Liang, Liang Bai, Xian Yang
scRNA-seq clustering is a critical task for analyzing single-cell RNA sequencing (scRNA-seq) data, as it groups cells with similar gene expression profiles. Transformers, as powerf…
Progressive Local Alignment for Medical Multimodal Pre-training
Huimin Yan, Xian Yang, Liang Bai +1
Local alignment between medical images and text is essential for accurate diagnosis, though it remains challenging due to the absence of natural local pairings and the limitations…
C-LoRA: Continual Low-Rank Adaptation for Pre-trained Models
Xin Zhang, Liang Bai, Xian Yang +1
Low-Rank Adaptation (LoRA) is an efficient fine-tuning method that has been extensively applied in areas such as natural language processing and computer vision. Existing LoRA fine…