Hanbin Wang's picture

19 5 4

Hanbin Wang

hanbin

·

https://wanghanbinpanda.github.io/

wanghanbinpanda

AI & ML interests

Code Intelligence and LLM Reasoning (Code, Math)

Recent Activity

authored a paper 2 days ago

Process Reinforcement through Implicit Rewards

updated a dataset 2 days ago

PRIME-RL/Eurus-2-RL-Data

updated a dataset 2 days ago

PRIME-RL/EurusPRM-Stage1-Data

View all activity

Organizations

Articles 1

Article

22

Process Reinforcement through Implicit Rewards

Papers 2

arxiv:2502.01456

arxiv:2404.02078

models 5

hanbin/o1_sft_all_abla_numina_oly_orca

Updated Nov 4, 2024 • 7

hanbin/MaMaL-Gen

Text2Text Generation • Updated Apr 18, 2023 • 110

hanbin/MaMaL-Sum

Text2Text Generation • Updated Apr 18, 2023 • 111

hanbin/MaMaL-Com

Text Generation • Updated Apr 18, 2023 • 112

hanbin/py-retriever

Feature Extraction • Updated Apr 17, 2023 • 109

datasets 2

hanbin/UltraInteract_sft_all_end_20240906

Viewer • Updated Nov 26, 2024 • 681k • 65

hanbin/UltraInteract_pair_all_20240911_v2_gt_v3

Preview • Updated Nov 4, 2024 • 42