Yuhang Zhou

zyh-ralph

·

AI & ML interests

None yet

Recent Activity

published a model 4 days ago

zyh-ralph/qwen3.5-4b-sft

published a model 9 days ago

zyh-ralph/qwen3.5-4b-rl-ckpt85

upvoted a paper 12 days ago

Demystifying On-Policy Distillation: Roles, Pathologies, and Regulations

View all activity

Organizations

Papers 3

arxiv:2607.05804

arxiv:2601.18467

arxiv:2505.23885

models 3

zyh-ralph/qwen3.5-4b-rl-ckpt85

5B • Updated Jun 17 • 19

zyh-ralph/qwen3.5-4b-rl-ckpt45

5B • Updated Jun 17 • 8

zyh-ralph/qwen3.5-4b-sft

5B • Updated Jun 17 • 10

datasets 0

None public yet