Guangxiang Zhao's picture

8 3 1

Guangxiang Zhao

zhaoguangxiang

·

https://guangxiang.cc/

AI & ML interests

None yet

Recent Activity

upvoted a paper 4 days ago

Evaluation is All You Need: Strategic Overclaiming of LLM Reasoning Capabilities Through Evaluation Design

updated a model 19 days ago

zhaoguangxiang/Qwen2.5-1.5B-Open-R1-GRPO

published a model about 1 month ago

zhaoguangxiang/Qwen2.5-1.5B-Open-R1-GRPO

View all activity

Organizations

Papers 4

arxiv:2503.04872

arxiv:2502.20790

arxiv:2502.16860

arxiv:2502.12459

models 2

zhaoguangxiang/Qwen2.5-1.5B-Open-R1-GRPO

Text Generation • Updated 19 days ago • 9

zhaoguangxiang/DeepSeek-R1-Distill-Qwen-1.5B-GRPO

datasets 0

None public yet