Zhihan Liu

ZHLiu627

AI & ML interests

LLMs

Recent Activity

upvoted a paper about 1 month ago

Self-rewarding correction for mathematical reasoning

updated a dataset about 1 month ago

ZHLiu627/updated_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212__self_correction_iter1_v1

updated a dataset about 1 month ago

ZHLiu627/dataset_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212_2_global_step_70filtered_v1_v1

View all activity

Organizations

None yet

ZHLiu627's activity

upvoted a paper about 1 month ago

Self-rewarding correction for mathematical reasoning

Paper • 2502.19613 • Published Feb 26 • 82

updated 2 datasets about 1 month ago

ZHLiu627/updated_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212__self_correction_iter1_v1

Viewer • Updated Feb 27 • 29.3k • 59

ZHLiu627/dataset_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212_2_global_step_70filtered_v1_v1

Viewer • Updated Feb 27 • 29.3k • 67

published a dataset about 1 month ago

ZHLiu627/dataset_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212_2_global_step_70filtered_v1_v1

Viewer • Updated Feb 27 • 29.3k • 67

upvoted a paper about 1 month ago

Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer

Paper • 2405.16436 • Published May 26, 2024 • 1

updated 2 models about 1 month ago

ZHLiu627/zephyr-7b-gemma-rpo-avg

Updated Feb 25 • 11

ZHLiu627/beta_ultra_rdpo_full_eta0.005_beta0.01_no_decay_new

Updated Feb 24 • 5

published 2 models about 1 month ago

ZHLiu627/beta_ultra_rdpo_full_eta0.005_beta0.01_no_decay_new

Updated Feb 24 • 5

ZHLiu627/zephyr-7b-gemma-rpo-avg

Updated Feb 25 • 11

updated a dataset about 1 month ago

ZHLiu627/dataset_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212_2_global_step_70filtered_v1

Viewer • Updated Feb 22 • 29.3k • 86

published a dataset about 1 month ago

ZHLiu627/dataset_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212_2_global_step_70filtered_v1

Viewer • Updated Feb 22 • 29.3k • 86

updated a dataset about 1 month ago

ZHLiu627/updated-code-qwen7-edufiltered

Viewer • Updated Feb 21 • 43k • 69

published a dataset about 1 month ago

ZHLiu627/updated-code-qwen7-edufiltered

Viewer • Updated Feb 21 • 43k • 69

updated a dataset about 1 month ago

ZHLiu627/updated-code-qwen7-edu

Viewer • Updated Feb 21 • 75.6k • 68

published a dataset about 1 month ago

ZHLiu627/updated-code-qwen7-edu

Viewer • Updated Feb 21 • 75.6k • 68

updated a dataset about 1 month ago

ZHLiu627/updated_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212__self_correction_iter1_v2filtered

Viewer • Updated Feb 19 • 28.9k • 74

published a dataset about 1 month ago

ZHLiu627/updated_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212__self_correction_iter1_v2filtered

Viewer • Updated Feb 19 • 28.9k • 74

updated a dataset about 1 month ago

ZHLiu627/updated_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212__self_correction_iter1_v2

Viewer • Updated Feb 19 • 29.3k • 50

published a dataset about 1 month ago

ZHLiu627/updated_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212__self_correction_iter1_v2

Viewer • Updated Feb 19 • 29.3k • 50

updated a dataset about 1 month ago

ZHLiu627/dataset_qwen2.5_code_1.5b_grpo_iter0_full_data_miao_0212_2_global_step_70filteredd

Viewer • Updated Feb 19 • 29.3k • 59