Shuming Liu PRO

sming256

·

https://sming256.github.io/

sming256

AI & ML interests

None yet

Recent Activity

authored a paper about 1 hour ago

The Thinking Leakage in Reinforcement Learning for LLMs

upvoted a paper about 16 hours ago

APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces

upvoted a paper about 18 hours ago

The Thinking Leakage in Reinforcement Learning for LLMs

View all activity

Organizations

sming256 's papers 11

arxiv:2610.14270

arxiv:2604.08120

arxiv:2604.06425

arxiv:2601.05175

arxiv:2511.12207

arxiv:2503.21483

arxiv:2502.20361

arxiv:2407.13036

arxiv:2311.17241

arxiv:2305.17066

arxiv:2211.14053