Kun Wan

timecuriosity

5

AI & ML interests

None yet

Recent Activity

authored a paper about 13 hours ago

From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement

upvoted a paper about 15 hours ago

From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement

upvoted a paper 2 months ago

When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs

View all activity

Organizations

None yet

timecuriosity 's papers 8

arxiv:2607.23802

arxiv:2509.25541

arxiv:2509.22576

arxiv:2506.09501

arxiv:2504.09710

arxiv:2412.10292

arxiv:2410.06169

arxiv:2312.16256