arxiv:2509.25534
Ye Zhiling
yzlnew
·
AI & ML interests
Data → Pre-train → Post-train
Recent Activity
upvoted a paper 1 day ago
1% of Tokens Can Be Enough: On Gradient Estimation in On-Policy Distillation upvoted a paper about 1 month ago
Stealing Reasoning Traces from Proprietary LLM APIs liked a model 2 months ago
extraltodeus/Qwen3.5-9B-Nikusui-v1Organizations
