arxiv:2609.32722
Yuntai Bao
colored-dye
P(doom) 10%
ยท
AI & ML interests
on-policy distillation, reinforcement learning, mechanistic interpretability, training data attribution
Recent Activity
upvoted a collection 1 day ago
Ling 3.0 liked a model 1 day ago
Qwen/Qwen3.8-27B liked a model 1 day ago
Qwen/Qwen3.8-Flash-NextOrganizations
None yet