Bingxiang He's picture

Bingxiang He

hbx

·

https://hbx-hbx.github.io/

AI & ML interests

NLP

Recent Activity

commented on a paper 2 days ago

How Far Can Unsupervised RLVR Scale LLM Training?

upvoted a paper 2 days ago

How Far Can Unsupervised RLVR Scale LLM Training?

submitted a paper 2 days ago

How Far Can Unsupervised RLVR Scale LLM Training?

View all activity

Organizations

Collections 1

Papers 8

arxiv:2509.18154

arxiv:2509.08827

arxiv:2506.07900

arxiv:2504.03612

models 3

hbx/JustRL-Nemotron-1.5B

Text Generation • 2B • Updated Dec 29, 2025 • 277 • 3

hbx/JustRL-DeepSeek-1.5B

Text Generation • 2B • Updated Dec 29, 2025 • 249 • 10

hbx/Mistral-Interact

Text Generation • Updated Feb 20, 2024 • 21 • 3

datasets 2

hbx/IN3

Viewer • Updated Feb 20, 2024 • 1.37k • 26 • 7

hbx/IN3-interaction

Viewer • Updated Feb 20, 2024 • 2.53k • 15 • 3