← Search

Zhichang Guo

2 accepted papers

2025

Bohdi: Heterogeneous LLM Fusion with Automatic Data Exploration

NeurIPS 2025poster

Heterogeneous Large Language Model (LLM) fusion integrates the strengths of multiple source LLMs with different architectures into a target LLM with low computational overhead. While promising, existing methods suffer from two major limitations: 1) **reliance on real data from limited domain** for k…

Cited by 0SourceScholar
2023

Perturbation Towards Easy Samples Improves Targeted Adversarial Transferability

NeurIPS 2023poster

The transferability of adversarial perturbations provides an effective shortcut for black-box attacks. Targeted perturbations have greater practicality but are more difficult to transfer between models. In this paper, we experimentally and theoretically demonstrated that neural networks trained on t…