Zhenwen Liang's picture

2 16

Zhenwen Liang

invokerliang

·

http://zhenwen-nlp.github.io/

LZhenwen

AI & ML interests

Mathematical Reasoning.

Recent Activity

authored a paper 7 days ago

Can LLMs Guide Their Own Exploration? Gradient-Guided Reinforcement Learning for LLM Reasoning

upvoted a paper 7 days ago

Can LLMs Guide Their Own Exploration? Gradient-Guided Reinforcement Learning for LLM Reasoning

updated a dataset about 1 month ago

invokerliang/math_aime_grpo

View all activity

Organizations

Papers 12

arxiv:2512.15687

arxiv:2510.01591

arxiv:2509.15194

arxiv:2508.19652

models 2

invokerliang/MWP-BERT-zh

Fill-Mask • Updated Aug 19, 2022 • 20 • 1

invokerliang/MWP-BERT-en

Fill-Mask • Updated Aug 19, 2022 • 12

datasets 1

invokerliang/math_aime_grpo

Viewer • Updated Nov 19 • 9.04k • 8