arxiv:2603.01162
Kai Ye
Kyleyee
·
AI & ML interests
None yet
Recent Activity
authored a paper 16 days ago
Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic upvoted a paper 19 days ago
Learn-to-Distance: Distance Learning for Detecting LLM-Generated Text authored a paper about 1 month ago
Learn-to-Distance: Distance Learning for Detecting LLM-Generated TextOrganizations
models 144
Kyleyee/qwen2_5-0.5b-grpo-arithmetic
Text Generation • 0.5B • Updated • 1
Kyleyee/qwen2_5-0.5b-sft-arithmetic
Text Generation • 0.5B • Updated • 5
Kyleyee/stats_ai_final_model
2B • Updated • 62
Kyleyee/qwen2_5-1.5b-grpo-riaid_12k_v5_3
2B • Updated • 1
Kyleyee/qwen2_5-1.5b-grpo-riaid_12k_v5_2
2B • Updated
Kyleyee/qwen2_5-1.5b-grpo-riaid_70k_v4_3
2B • Updated • 4
Kyleyee/qwen2_5-1.5b-grpo-riaid_70k_v4_2
2B • Updated
Kyleyee/qwen2_5-1.5b-grpo-riaid_70k_v4_1
2B • Updated
Kyleyee/qwen2_5-1.5b-grpo-riaid_70k_v1
Text Generation • 2B • Updated • 1
Kyleyee/qwen2_5-1.5b-grpo-riaid_70k_v3
2B • Updated
datasets 202
Kyleyee/arithmetic-few-shot
Viewer • Updated • 500 • 9
Kyleyee/arithmetic-test
Viewer • Updated • 500 • 13
Kyleyee/arithmetic-grpo
Viewer • Updated • 25k • 11
Kyleyee/arithmetic-sft
Viewer • Updated • 5k • 8
Kyleyee/qwen05b-arith-oracle-v1
Viewer • Updated • 5k • 10
Kyleyee/black_box_test_updated_results_t0_token_calculated
Viewer • Updated • 6k • 10
Kyleyee/RIAID_sub_results
Viewer • Updated • 1.6k • 9
Kyleyee/sub_4s
Viewer • Updated • 4 • 13
Kyleyee/direct_grpo
Viewer • Updated • 92.2k • 13
Kyleyee/RIAID_sft_direct
Viewer • Updated • 20k • 14