Yukang's picture

1 2 3

Yukang

yyk19

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 23 days ago

Exploration v.s. Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward

upvoted a paper 7 months ago

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

updated a model about 1 year ago

PDMR/GGDMOptim

View all activity

Organizations

upvoted a paper 23 days ago

Exploration v.s. Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward

Paper • 2512.16912 • Published 23 days ago • 10

upvoted a paper 7 months ago

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Paper • 2506.01939 • Published Jun 2, 2025 • 187