arxiv:2508.14904
sunlin
lincharliesun
LookLikeSquareButItRectangle's profile picture
21world's profile picture
zhaoguangxiang's profile picture
·
AI & ML interests
None yet
Recent Activity
authored
a paper
about 20 hours ago
Efficient Switchable Safety Control in LLMs via Magic-Token-Guided
Co-Training
upvoted
a
paper
3 days ago
Efficient Switchable Safety Control in LLMs via Magic-Token-Guided
Co-Training
commented on
a paper
3 months ago
Evaluation is All You Need: Strategic Overclaiming of LLM Reasoning
Capabilities Through Evaluation Design
Organizations
models
0
None public yet
datasets
0
None public yet