activity
20242026
collaborators

13 papers

cs.LG2026

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…

cs.AI2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.LG2026

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…