Yang Su
yang-su2000
AI & ML interests
Long-Horizon RL Agent Alignment
Recent Activity
new activity
28 days ago
Qwen/Qwen3-32B:The correct way of fine-tuning on multi-turn trajectories
new activity
about 1 month ago
Qwen/Qwen3-235B-A22B:Qwen3 not Using Tools in Complex Prompts Unlike QwQ-32B
liked
a model
about 1 month ago
Qwen/Qwen3-235B-A22B