← Search

Dongwei Xu

2 accepted papers

2026

Improving the Convergence Rate of Ray Search Optimization for Query-Efficient Hard-Label Attacks

AAAI 2026technical

In hard-label black-box adversarial attacks, where only the top-1 predicted label is accessible, the prohibitive query complexity poses a major obstacle to practical deployment. In this paper, we focus on optimizing a representative class of attacks that search for the optimal ray direction yielding

Cited by 0SourcePDFScholar
2026

Reassessing Layer Pruning in LLMs: New Insights and Methods

ICLR 2026poster

Although large language models (LLMs) have achieved remarkable success across various domains, their considerable scale necessitates substantial computational resources, posing significant challenges for deployment in resource-constrained environments. Layer pruning, as a simple yet effective compre…

Cited by 0SourcecodeScholar