QIUSI ZHAN
qiusizhan
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 10 hours ago
Understanding and Enhancing Backdoor Persistency in LLM Agent Post-Training submitted a paper about 10 hours ago
Understanding and Enhancing Backdoor Persistency in LLM Agent Post-Training upvoted a paper 4 days ago
Sharpening Tax in Post-TrainingOrganizations
models 13
qiusizhan/swe-audit-7b-09
8B • Updated • 4
qiusizhan/swe-audit-7b-08
8B • Updated • 4
qiusizhan/swe-audit-7b-07
8B • Updated • 4
qiusizhan/swe-audit-7b-06
8B • Updated • 4
qiusizhan/swe-audit-7b-05
8B • Updated • 3
qiusizhan/swe-audit-7b-04
8B • Updated • 4
qiusizhan/swe-audit-7b-03
8B • Updated • 4
qiusizhan/swe-audit-7b-02
8B • Updated • 6
qiusizhan/swe-audit-7b-01
8B • Updated • 6
qiusizhan/swe-audit-3b-04
3B • Updated • 4
datasets 6
qiusizhan/benign_trajectories_5000_v2_select
Viewer • Updated • 842 • 8
qiusizhan/benign_trajectories_5000_v2_train
Viewer • Updated • 3.37k • 15
qiusizhan/benign_trajectories_5000
Viewer • Updated • 5k • 7
qiusizhan/test_comment_trigger_100
Viewer • Updated • 200 • 9
qiusizhan/backdoor_trajectories_5000
Viewer • Updated • 5k • 7
qiusizhan/benign_trajectories_5000_v2
Viewer • Updated • 4.21k • 12