Ziquan/cohortworld-qwen3.6-27b-csgrpo-psi
Reinforcement Learning • 27B • Updated • 19
👋 Open to Work
Wei
Ziquan
AI & ML interests
None yet
Recent Activity
liked a dataset about 24 hours ago
Ziquan/cohort-world updated a Space about 24 hours ago
Ziquan/cohort-world upvoted a paper 5 days ago
Grounded Skill Synthesis from Code at Scale for Agentic IntelligenceOrganizations
Ziquan/cohortworld-qwen3.6-27b-csgrpo
Reinforcement Learning • 27B • Updated • 11
Ziquan/cohortworld-qwen3.6-27b-sft
Reinforcement Learning • 27B • Updated • 10
Ziquan/cohortworld-qwen3.5-9b-csgrpo-psi
Reinforcement Learning • 9B • Updated • 5
Ziquan/cohortworld-qwen3.5-9b-csgrpo
Reinforcement Learning • 9B • Updated • 7
Ziquan/cohortworld-qwen3.5-9b-sft
Reinforcement Learning • 9B • Updated • 7
Ziquan/qwen3-icd10-ntp
0.1B • Updated • 4