Yang Su
yang-su2000
AI & ML interests
Long-Horizon RL Agent Alignment
Recent Activity
liked
a dataset
14 days ago
Agent-Ark/Toucan-1.5M
new activity
6 months ago
Qwen/Qwen3-32B:The correct way of fine-tuning on multi-turn trajectories
new activity
6 months ago
Qwen/Qwen3-235B-A22B:Qwen3 not Using Tools in Complex Prompts Unlike QwQ-32B
Organizations
models
0
None public yet
datasets
0
None public yet