Bingxiang He

hbx

·

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

AI & ML interests

NLP

Recent Activity

new activity 3 days ago

hbx/JustRL-DeepSeek-1.5B:疑问：没有使用拒绝采样或者动态采样，用GRPO哪里来的梯度呀

liked a dataset 3 days ago

openbmb/UltraFeedback

upvoted a paper 7 days ago

StudyBench: Can Self-Evolution Squeeze Textbooks for Olympiad Capability?

View all activity

Organizations

hbx 's models 3

hbx/JustRL-Nemotron-1.5B

Text Generation • 2B • Updated Dec 29, 2025 • 438 • 3

hbx/JustRL-DeepSeek-1.5B

Text Generation • 2B • Updated Dec 29, 2025 • 1.84k • 12

hbx/Mistral-Interact

Text Generation • Updated Feb 20, 2024 • 12 • 3