arxiv:2603.01162
🤝 Open to Collab
Kai Ye
Kyleyee
AI & ML interests
None yet
Organizations
models 181
Kyleyee/DrDPO_hh-seed3
Text Generation • 2B • Updated • 18
Kyleyee/DrDPO_hh-seed4
Text Generation • 2B • Updated • 19
Kyleyee/DrDPO_hh-seed5
Text Generation • 2B • Updated • 18
Kyleyee/DrDPO_hh-seed2
Text Generation • 2B • Updated • 17
Kyleyee/cDPO_hh-seed3
Text Generation • 2B • Updated • 16
Kyleyee/CPO_hh-seed3
Text Generation • 2B • Updated • 17
Kyleyee/CPO_hh-seed5
Text Generation • 2B • Updated • 16
Kyleyee/CPO_hh-seed2
Text Generation • 2B • Updated • 15
Kyleyee/ORPO_hh-seed3
Text Generation • 2B • Updated • 16
Kyleyee/CPO_hh-seed4
Text Generation • 2B • Updated • 16
datasets 210
Kyleyee/eval-hh-clean
Viewer • Updated • 11.8k • 227
Kyleyee/eval-hh-seed
Viewer • Updated • 11.8k • 321
Kyleyee/eval-hh-all
Viewer • Updated • 11.8k • 150
Kyleyee/detect_CN_by_scenari_result
Viewer • Updated • 7k • 124
Kyleyee/detect_CN
Viewer • Updated • 7k • 68
Kyleyee/test_with_label_ood_format
Viewer • Updated • 7k • 7
Kyleyee/grpo_v7_2_correct_wrong_400
Viewer • Updated • 400 • 10
Kyleyee/OOD_data
Viewer • Updated • 1.2k • 22
Kyleyee/arithmetic-few-shot
Viewer • Updated • 500 • 7 • 1
Kyleyee/arithmetic-test
Viewer • Updated • 500 • 7 • 1