arxiv:2510.27623
QIUSI ZHAN
qiusizhan
ยท
AI & ML interests
None yet
Recent Activity
authored
a paper
about 1 month ago
Removing RLHF Protections in GPT-4 via Fine-Tuning
authored
a paper
about 1 month ago
LLM Agents can Autonomously Hack Websites
authored
a paper
about 1 month ago
ConFiguRe: Exploring Discourse-level Chinese Figures of Speech
Organizations
models
0
None public yet
datasets
0
None public yet