Author

Xiaofeng Wang

h-index 10 View on Semantic Scholar

We have 2 of 18 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Training-Data Extraction from Genomic Language Models

Genomic language models generate long nucleotide continuations from short prefixes, exposing a direct route for studying training-sequence extraction through the generation interface. We present an output-only black-box attack on Evo 2 that selects convergent groups of repeated generations without gradients, token like...

Tian-Hao Mao, Zi-Hao Wang, Dongfang Zhao et al. · 0 citations

#artificial intelligence Preprint Sep 2026

When Safety Routing Breaks: Understanding Alignment Fragility under Benign Fine-Tuning

Overall, safety failure is best understood as a disruption of a low-rank output-routing mechanism, and it is shown that LoRA and ASAM mitigate early collapse by suppressing output-side sharpness, but their protection weakens at larger fine-tuning scales.

Yi-Tong Guo, Xiaoyi Chen, Si-Yuan Zhang et al. · 0 citations