weiliu's picture

weiliu

thinkwee

·

https://thinkwee.top/about/

AI & ML interests

LLM reasoning, agents

Recent Activity

upvoted a paper 11 days ago

Analysing Chain of Thought Dynamics: Active Guidance or Unfaithful Post-hoc Rationalisation?

upvoted a paper 17 days ago

Agentic Reinforced Policy Optimization

updated a collection 17 days ago

View all activity

Organizations

None yet

thinkwee 's datasets 3

thinkwee/NOVEReason_full

Viewer • Updated Aug 6 • 1.7M • 226 • 1

thinkwee/NOVEReason_2k

Viewer • Updated Aug 6 • 24.3k • 132 • 1

thinkwee/NOVEReason_5k

Viewer • Updated Aug 6 • 36.3k • 206 • 1