Hanbin Wang's picture

20 5 4

Hanbin Wang

hanbin

·

https://wanghanbinpanda.github.io/

wanghanbinpanda

AI & ML interests

Code Intelligence and LLM Reasoning (Code, Math)

Recent Activity

updated a model about 17 hours ago

hanbin/Llama-3.1-8B-pretrain-1

published a model about 18 hours ago

hanbin/Llama-3.1-8B-pretrain-1

updated a model 4 months ago

PRIME-RL/Eurus-2-7B-PRIME-Zero

View all activity

Organizations

Articles 1

Article

29

Process Reinforcement through Implicit Rewards

Papers 2

arxiv:2502.01456

arxiv:2404.02078

models 6

hanbin/Llama-3.1-8B-pretrain-1

Text Generation • 8B • Updated about 17 hours ago • 3

hanbin/o1_sft_all_abla_numina_oly_orca

8B • Updated Nov 4, 2024 • 3

hanbin/MaMaL-Gen

Text Generation • Updated Apr 18, 2023 • 16

hanbin/MaMaL-Sum

Text Generation • Updated Apr 18, 2023 • 21

hanbin/MaMaL-Com

Text Generation • Updated Apr 18, 2023 • 9

hanbin/py-retriever

Feature Extraction • Updated Apr 17, 2023 • 10

datasets 2

hanbin/UltraInteract_sft_all_end_20240906

Viewer • Updated Nov 26, 2024 • 681k • 25

hanbin/UltraInteract_pair_all_20240911_v2_gt_v3

Preview • Updated Nov 4, 2024 • 13