🤝 Open to Collab

Kai Ye

Kyleyee

4 2

·

https://noncollapse.github.io/

AI & ML interests

None yet

Recent Activity

liked a model 20 days ago

Kyleyee/DrDPO_hh-seed3

authored a paper about 1 month ago

READER: Reasoning-Enhanced AI-Generated Text Detection

authored a paper about 1 month ago

BASIS: Batchwise Advantage Estimation from Single-Rollout Information Sharing for LLM Reasoning

View all activity

Organizations

Kyleyee 's datasets 213

Kyleyee/eval_data_imdb_with_subsft_reverse_preference

Viewer • Updated Mar 22, 2025 • 5k • 9

Kyleyee/train_data_imdb_base_model

Updated Mar 22, 2025 • 9

Kyleyee/eval_data_imdb_with_subsft_wrongp

Viewer • Updated Mar 21, 2025 • 5k • 18

Kyleyee/eval_data_imdb_with_subsft_wrong_preference

Viewer • Updated Mar 21, 2025 • 5k • 20

Kyleyee/train_data_imdb_subsft_reverse_preference

Viewer • Updated Mar 21, 2025 • 26k • 6

Kyleyee/train_data_imdb_reverse_preference

Viewer • Updated Mar 21, 2025 • 26k • 12

Kyleyee/eval_data_imdb_with_subsft

Viewer • Updated Mar 21, 2025 • 5k • 11

Kyleyee/train_data_imdb_sub_sft

Viewer • Updated Mar 21, 2025 • 26k • 18

Kyleyee/train_data_imdb_subsft_wrong_preference

Viewer • Updated Mar 21, 2025 • 26k • 13

Kyleyee/train_data_imdb_subsft

Viewer • Updated Mar 21, 2025 • 26k • 15

Kyleyee/eval_data_imdb_with_wrong_preference

Viewer • Updated Mar 21, 2025 • 5k • 16

Kyleyee/train_data_imdb_for_drdpo_wrong_preference

Viewer • Updated Mar 21, 2025 • 26k • 15

Kyleyee/eval_data_imdb_with_estimate_preference

Viewer • Updated Mar 21, 2025 • 5k • 10

Kyleyee/eval_data_imdb_muti_temp_with_estimate_preference

Viewer • Updated Mar 21, 2025 • 5k • 14

Kyleyee/train_data_imdb_for_drdpo_with_dpo_preference

Viewer • Updated Mar 21, 2025 • 26k • 15

Kyleyee/eval_data_imdb

Viewer • Updated Mar 20, 2025 • 5k • 23

Kyleyee/train_data_imdb_for_drdpo_preference

Viewer • Updated Mar 20, 2025 • 26k • 18

Kyleyee/train_data_imdb_for_drdpo

Viewer • Updated Mar 20, 2025 • 100 • 11

Kyleyee/evaluate-dataset-HH

Viewer • Updated Mar 19, 2025 • 11.8k • 19

Kyleyee/eval_data_hh_dpo_hinge_multi_temp_reformed

Viewer • Updated Mar 19, 2025 • 11.8k • 13

Kyleyee/eval_data_hh_dpo_hinge_multi_temp

Viewer • Updated Mar 19, 2025 • 11.8k • 9

Kyleyee/eval_dataset_hh_beta0.1_multi_temp_reformed

Viewer • Updated Mar 19, 2025 • 11.8k • 16

Kyleyee/eval_dataset_hh_beta0.1_multi_temp

Viewer • Updated Mar 18, 2025 • 11.8k • 8

Kyleyee/eval_data_hh_sft_dpo_drdpo_beta0.1_multi_temp

Viewer • Updated Mar 18, 2025 • 11.8k • 9

Kyleyee/train_data_Helpful_drdpo

Viewer • Updated Mar 16, 2025 • 46.2k • 19

Kyleyee/train_data_hh_stf

Viewer • Updated Mar 16, 2025 • 46.2k • 9

Kyleyee/eval_data_tldr_sft_dpo_drdpo_beta0.1_multi_temp

Viewer • Updated Mar 15, 2025 • 43k • 16

Kyleyee/train_data_SFT_Helpful

Viewer • Updated Mar 15, 2025 • 46.2k • 32

Kyleyee/train_data_Helpful_explicit_prompt

Viewer • Updated Mar 15, 2025 • 46.2k • 12

Kyleyee/train_data_Helpful_implicit_prompt

Viewer • Updated Mar 15, 2025 • 46.2k • 12