Hugging Face's logo
Hanbin Wang's picture
19 5 4

Hanbin Wang

hanbin
Lynncc6's profile picture BryantMcGill's profile picture junwux's profile picture
·
https://wanghanbinpanda.github.io/

AI & ML interests

Code Intelligence and LLM Reasoning (Code, Math)

Recent Activity

authored a paper about 21 hours ago
Process Reinforcement through Implicit Rewards
updated a dataset about 24 hours ago
PRIME-RL/Eurus-2-RL-Data
updated a dataset about 24 hours ago
PRIME-RL/EurusPRM-Stage1-Data
View all activity

Articles

Organizations

OpenBMB's profile picture PRIME's profile picture

hanbin's activity

authored a paper about 21 hours ago
updated 3 datasets about 24 hours ago
updated 4 models about 24 hours ago
updated a Space about 24 hours ago
upvoted a paper 1 day ago
commented a paper 1 day ago
New activity in PRIME-RL/Eurus-2-RL-Data 8 days ago

some empty code ground truths (roughly 1k in train)

1
#3 opened 8 days ago by
rawsh
New activity in PRIME-RL/Eurus-2-7B-PRIME about 1 month ago

Evaluation

6
#1 opened about 1 month ago by
tugstugi

Add library_name and pipeline_tag
#2 opened about 1 month ago by
nielsr
upvoted an article about 1 month ago
view article
Article

Process Reinforcement through Implicit Rewards

By ganqu •
• 22
liked a model about 1 month ago
updated 2 datasets about 1 month ago
updated 2 models about 1 month ago