arxiv:2609.32722
Yuntai Bao
colored-dye
P(doom) 10%
·
AI & ML interests
on-policy distillation, reinforcement learning, mechanistic interpretability, training data attribution
Recent Activity
liked a model about 2 hours ago
Qwen/Qwen3.8-27B liked a model about 2 hours ago
Qwen/Qwen3.8-Flash-Next liked a model about 2 hours ago
deepseek-ai/DeepSeek-V4.1-FlashOrganizations
None yet