Kai Ye's picture

Open to Collab

4 1

Kai Ye

Kyleyee

·

https://noncollapse.github.io/

AI & ML interests

None yet

Recent Activity

authored a paper 11 days ago

Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic

upvoted a paper 14 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 Text

View all activity

Organizations

Kyleyee 's datasets 202

Kyleyee/reward_distribuction_tldr

Viewer • Updated Jul 18, 2025 • 179k • 99

Kyleyee/reward_distribuction

Viewer • Updated Jul 15, 2025 • 46.2k • 82

Kyleyee/reward_distribuction_test

Viewer • Updated Jul 15, 2025 • 64 • 81

Kyleyee/eval_set_hh_7b_dpo_true_new

Viewer • Updated Jun 9, 2025 • 11.8k • 6

Kyleyee/train_data_Helpful_drdpo_preference_7b_sft_1e

Viewer • Updated Jun 8, 2025 • 46.2k • 5

Kyleyee/train_data_Helpful_drdpo_7b_sft_1e

Viewer • Updated Jun 8, 2025 • 46.2k • 5

Kyleyee/train_data_Helpful_drdpo_preference_7b_075

Viewer • Updated Jun 5, 2025 • 46.2k • 5

Kyleyee/train_data_Helpful_drdpo_7b_075

Viewer • Updated Jun 5, 2025 • 46.2k • 5

Kyleyee/eval_set_hh_7b_dpo_true

Viewer • Updated Jun 3, 2025 • 11.8k • 5

Kyleyee/train_data_Helpful_drdpo_preference

Viewer • Updated Jun 3, 2025 • 46.2k • 8

Kyleyee/train_data_Helpful_drdpo_7b

Viewer • Updated Jun 3, 2025 • 46.2k • 5

Kyleyee/eval_set_hh_7b

Viewer • Updated Jun 2, 2025 • 11.8k • 7

Kyleyee/eval_effect_hh_7b

Viewer • Updated Jun 2, 2025 • 11.8k • 5

Kyleyee/evaluate-dataset-HH-7b

Viewer • Updated Jun 2, 2025 • 11.8k • 5

Kyleyee/eval_effect_hh_drdpo_7b_merged

Viewer • Updated Jun 2, 2025 • 11.8k • 5

Kyleyee/evaluate-dataset-HH-Base

Viewer • Updated Jun 1, 2025 • 11.8k • 5

Kyleyee/evaluate-dataset-HH-Instruct

Viewer • Updated Jun 1, 2025 • 11.8k • 4

Kyleyee/eval_effect_hh_7b_500

Viewer • Updated Jun 1, 2025 • 500 • 5

Kyleyee/imdb_data_for_dr_test_8sample_PAD_FIX

Viewer • Updated May 10, 2025 • 10k • 10

Kyleyee/imdb_data_for_dr_test_8sample_gpt_neo

Viewer • Updated May 10, 2025 • 10k • 7

Kyleyee/imdb_data_for_true_preference_gpt-neoo

Viewer • Updated May 10, 2025 • 25k • 7

Kyleyee/train_data_imdb_for_target_policy_dpo

Viewer • Updated May 10, 2025 • 26k • 8

Kyleyee/imdb_data_for_dr_test_8sample

Viewer • Updated May 7, 2025 • 10k • 6

Kyleyee/imdb_data_for_dr_test_8samples

Viewer • Updated May 7, 2025 • 10k • 5

Kyleyee/imdb_data_for_dr_test_2sample

Viewer • Updated May 6, 2025 • 10k • 6

Kyleyee/imdb_data_for_true_preference

Viewer • Updated May 6, 2025 • 25k • 6

Kyleyee/imdb_data_for_dr_test

Viewer • Updated May 6, 2025 • 25k • 6

Kyleyee/trin_data_tldr_explicit_dataset

Viewer • Updated May 3, 2025 • 179k • 5

Kyleyee/eval_data_hh_sft_dpo_ppo

Viewer • Updated Apr 28, 2025 • 11.8k • 5

Kyleyee/eval_for_sft_quality_hh_old_new_end

Viewer • Updated Apr 23, 2025 • 500 • 5