卷某
liushiyang
AI & ML interests
Reinforcement Learning
Recent Activity
new activity about 13 hours ago
Kwaipilot/KAT-Coder-V2.5-Dev:No difference with base model (for me)... new activity 1 day ago
Kwaipilot/KAT-Coder-V2.5-Dev:did you train it for 90 rl steps new activity 2 days ago
Kwaipilot/KAT-Coder-V2.5-Dev:Wrong Qwen3.6-35B-A3B BenchmarkOrganizations
