Bingxiang He's picture

Bingxiang He

hbx

·

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

AI & ML interests

NLP

Recent Activity

upvoted a paper 3 days ago

Advancing Creative Physical Intelligence in Large Multimodal Models

liked a model 6 days ago

openbmb/MiniCPM5-1B

upvoted a paper 13 days ago

Post-Trained MoE Can Skip Half Experts via Self-Distillation

View all activity

Organizations

commented a paper about 1 month ago

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Paper • 2604.13016 • Published Apr 14 • 109 •

commented a paper about 2 months ago

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Paper • 2604.13016 • Published Apr 14 • 109 •

commented a paper 3 months ago

How Far Can Unsupervised RLVR Scale LLM Training?

Paper • 2603.08660 • Published Mar 9 • 59 •

New activity in hbx/JustRL-Nemotron-1.5B 5 months ago

Add Hugging Face paper link badge to model card

#1 opened 5 months ago by

New activity in hbx/JustRL-DeepSeek-1.5B 5 months ago

Improve model card: Update title, add paper link, correct license and citation

#1 opened 5 months ago by

commented a paper 5 months ago

JustRL: Scaling a 1.5B LLM with a Simple RL Recipe

Paper • 2512.16649 • Published Dec 18, 2025 • 29 •