arxiv:2603.01162
Kai Ye
Kyleyee
AI & ML interests
None yet
Recent Activity
updated a dataset about 18 hours ago
Kyleyee/eval-hh-all updated a model 1 day ago
Kyleyee/VRPO_hh-seed5 updated a model 1 day ago
Kyleyee/VRPO_hh-seed4Organizations
models 153
Kyleyee/VRPO_hh-seed5
Text Generation • 2B • Updated • 190
Kyleyee/VRPO_hh-seed4
Text Generation • 2B • Updated • 195
Kyleyee/VRPO_hh-seed3
Text Generation • 2B • Updated • 201
Kyleyee/DPO_hh-seed5
Text Generation • 2B • Updated • 209
Kyleyee/VRPO_hh-seed2
Text Generation • 2B • Updated • 219
Kyleyee/DPO_hh-seed4
Text Generation • 2B • Updated • 215
Kyleyee/DPO_hh-seed3
Text Generation • 2B • Updated • 241
Kyleyee/DPO_hh-seed2
Text Generation • 2B • Updated • 263
Kyleyee/VRPO_hh-seed1
Text Generation • 2B • Updated • 242
Kyleyee/DPO_hh-seed1
Text Generation • 2B • Updated • 251
datasets 208
Kyleyee/eval-hh-all
Viewer • Updated • 11.8k • 50
Kyleyee/detect_CN_by_scenari_result
Viewer • Updated • 7k • 38
Kyleyee/detect_CN
Viewer • Updated • 7k • 34
Kyleyee/test_with_label_ood_format
Viewer • Updated • 7k • 33
Kyleyee/grpo_v7_2_correct_wrong_400
Viewer • Updated • 400 • 33
Kyleyee/OOD_data
Viewer • Updated • 1.2k • 36
Kyleyee/arithmetic-few-shot
Viewer • Updated • 500 • 8
Kyleyee/arithmetic-test
Viewer • Updated • 500 • 10
Kyleyee/arithmetic-grpo
Viewer • Updated • 25k • 10
Kyleyee/arithmetic-sft
Viewer • Updated • 5k • 7