13 papers
Towards the Connection between Activation Sparsity and Flat Minima
Ze Peng, Jian Zhang, Lei Qi +2
The observation that activation sparsity emerges in MLP blocks of standardly trained Transformers offers an opportunity to drastically reduce computation costs without sacrificing…
Understanding and Enforcing Weight Disentanglement in Task Arithmetic
Shangge Liu, Yuehan Yin, Lei Wang +5
Task arithmetic provides an efficient, training-free way to edit pre-trained models, yet lacks a fundamental theoretical explanation for its success. The existing concept of ``weig…
CLASP: Class-Adaptive Layer Fusion and Dual-Stage Pruning for Multimodal Large Language Models
Yunkai Dang, Yizhu Jiang, Yifan Jiang +4
Multimodal Large Language Models (MLLMs) suffer from substantial computational overhead due to the high redundancy in visual token sequences. Existing approaches typically address…
DeferredSeg: A Multi-Expert Deferral Framework for Trustworthy Medical Image Segmentation
Qiuyu Tian, Haoliang Sun, Yunshan Wang +2
Segmentation models based on deep neural networks demonstrate strong generalization for medical image segmentation. However, they often exhibit overconfidence or underconfidence, l…
Diffusion-Based Data Augmentation for Image Recognition: A Systematic Analysis and Evaluation
Zekun Li, Yinghuan Shi, Yang Gao +1
Diffusion-based data augmentation (DiffDA) has emerged as a promising approach to improving classification performance under data scarcity. However, existing works vary significant…
Leveraging Flatness to Improve Information-Theoretic Generalization Bounds for SGD
Ze Peng, Jian Zhang, Yisen Wang +3
Information-theoretic (IT) generalization bounds have been used to study the generalization of learning algorithms. These bounds are intrinsically data- and algorithm-dependent so…