5 papers · 1 filter
Energy-Structured Low-Rank Adaptation for Continual Learning
Longhua Li, Lei Qi, Qi Tian +1
While orthogonal subspace methods try to mitigate task interference in Continual Learning (CL), they often suffer from energy diffusion across the basis, hindering knowledge compac…
Essential Subspace Merging for Multi-Task Learning
Longhua Li, Lei Qi, Xin Geng +1
Model merging aims to enable multi-task learning by integrating the capabilities of multiple models fine-tuned from the same pre-trained checkpoint into a single model. Its core ch…
Model Merging in the Essential Subspace
Longhua Li, Lei Qi, Qi Tian +1
Model merging aims to integrate multiple task-specific fine-tuned models derived from a shared pre-trained checkpoint into a single multi-task model without additional training. De…
Stratified Knowledge-Density Super-Network for Scalable Vision Transformers
Longhua Li, Lei Qi, Xin Geng
Training and deploying multiple vision transformer (ViT) models for different resource constraints is costly and inefficient. To address this, we propose transforming a pre-trained…
Scalable Label Distribution Learning for Multi-Label Classification
Xingyu Zhao, Yuexuan An, Lei Qi +1
Multi-label classification (MLC) refers to the problem of tagging a given instance with a set of relevant labels. Most existing MLC methods are based on the assumption that the cor…