arxiv:2608.16647
DeyangKong
DeyangKong
AI & ML interests
Natural Language Processing
Recent Activity
liked a model 7 days ago
IQuestLab/IQuest-Q1 upvoted a paper 26 days ago
SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research? authored a paper about 1 month ago
Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models