6 25 9

Bingxiang He

hbx

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

hbx_hbx
HBX-hbx

AI & ML interests

NLP

Recent Activity

updated a collection about 12 hours ago

JustRL

commentedon a paper 10 days ago

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

authored a paper 16 days ago

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

View all activity

Organizations

Collections 1

Papers 9

models 3

datasets 2

hbx/IN3

Viewer • Updated Feb 20, 2024 • 1.37k • 33 • 7

hbx/IN3-interaction

Viewer • Updated Feb 20, 2024 • 2.53k • 24 • 3

Bingxiang He

AI & ML interests

Recent Activity

Organizations

Collections 1

hbx/JustRL-DeepSeek-1.5B

hbx/JustRL-Nemotron-1.5B

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

hbx/JustRL-DeepSeek-1.5B

hbx/JustRL-Nemotron-1.5B

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

Papers 9

models 3

hbx/JustRL-Nemotron-1.5B

hbx/JustRL-DeepSeek-1.5B

hbx/Mistral-Interact

datasets 2

hbx/IN3

hbx/IN3-interaction

Bingxiang He

AI & ML interests

Recent Activity

Organizations

Collections 1

Papers 9

models 3 Sort: Recently updated

datasets 2 Sort: Recently updated

models 3

datasets 2