Publications (14)
Accelerating Prefilling for Long-Context LLMs via Sparse Pattern Sharing
Dan Peng, Zhihui Fu, Zewen Ye +2
Sparse attention methods exploit the inherent sparsity in attention to speed up the prefilling phase of long-context inference, mitigating the quadratic complexity of full attentio…
Punctuated equilibrium dynamics in human communications
Dan Peng, Xiao-Pu Han, Zong-Wen Wei +1
A minimal model based on individual interactions is proposed to study the non-Poisson statistical properties of human behavior: individuals in the system interact with their neighb…
Structure-Preserving Transformation: Generating Diverse and Transferable Adversarial Examples
Dan Peng, Zizhan Zheng, Xiaofeng Zhang
Adversarial examples are perturbed inputs designed to fool machine learning models. Most recent works on adversarial examples for image classification focus on directly modifying p…
Finite-size scaling of percolation on scale-free networks
Xuewei Zhao, Liwenying Yang, Dan Peng +2
Critical phenomena on scale-free networks with a degree distribution exhibit rich finite-size effects due to its structural heterogeneity. We systematically stud…
Structure Matters: Towards Generating Transferable Adversarial Images
Dan Peng, Zizhan Zheng, Linhao Luo +1
Recent works on adversarial examples for image classification focus on directly modifying pixels with minor perturbations. The small perturbation requirement is imposed to ensure t…
Focused State Recognition Using EEG with Eye Movement-Assisted Annotation
Tian-Hua Li, Tian-Fang Ma, Dan Peng +2
With the rapid advancement in machine learning, the recognition and analysis of brain activity based on EEG and eye movement signals have attained a high level of sophistication. U…