ZHIYI LYU's picture

1 2

ZHIYI LYU

ZHIYII

·

AI & ML interests

reinforment learning, LLM

Recent Activity

upvoted a paper about 2 months ago

SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning

updated a model 2 months ago

ZHIYII/19500_RRM

published a model 2 months ago

ZHIYII/19500_RRM

View all activity

Organizations

None yet

models 3

ZHIYII/19500_RRM

Text Classification • 7B • Updated Aug 26 • 16 • 1

ZHIYII/Revision-Reward-Model

ZHIYII/BT_Qwen2.5-7B_Base

datasets 27

ZHIYII/successful_finite_infinite_n_level_remove_duplicates

Viewer • Updated Apr 29 • 1.17M • 6

ZHIYII/same_tree_arbitrary_node

Viewer • Updated Apr 15 • 953k • 13

ZHIYII/successful_infinite_3_level_remove_duplicates

Viewer • Updated Apr 15 • 906k • 4

ZHIYII/average_path_length_list_taco_lcb_backup

Viewer • Updated Apr 15 • 703k • 7

ZHIYII/successful_infinite_3_level_subset

Viewer • Updated Apr 14 • 653k • 2

ZHIYII/successful_infinite_3_level

Viewer • Updated Apr 14 • 1.13M • 2

ZHIYII/successful_finite_inite_same_tree

Viewer • Updated Apr 13 • 1.62M • 3

ZHIYII/sampling_brother_same_father

Viewer • Updated Apr 12 • 1.19M • 6

ZHIYII/diff_list_taco_lcb

Viewer • Updated Apr 11 • 705k • 11

ZHIYII/successful_unsuccessful_500_only_TACO

Updated Apr 10 • 2

View 27 datasets