weiliu's picture

In a Training Loop 🔄

weiliu

thinkwee

·

https://thinkwee.top/about/

AI & ML interests

LLM reasoning, agents

Recent Activity

submitted a paper about 8 hours ago

Large Language Models Hack Rewards, and Society

upvoted a paper about 8 hours ago

Large Language Models Hack Rewards, and Society

upvoted a paper 4 days ago

Linear Ensembles Wash Away Watermarks: On the Fragility of Distributional Perturbations in LLMs

View all activity

Organizations

None yet

thinkwee 's papers 13

arxiv:2602.02039

arxiv:2511.09586

arxiv:2505.16022

arxiv:2505.06904

arxiv:2406.14928

arxiv:2406.08979

arxiv:2406.07155

arxiv:2405.04219

arxiv:2312.17025

arxiv:2112.01147

arxiv:2106.10084

arxiv:2106.04847

arxiv:1909.10852