arxiv:2509.12521
Yifan Lan
yflantmy
·
AI & ML interests
None yet
Recent Activity
submitted a paper about 5 hours ago
The Illusion of Reasoning: Exposing Evasive Data Contamination in LLMs via Zero-CoT Truncation upvoted a paper 5 months ago
Phi: Preference Hijacking in Multi-modal Large Language Models at
Inference Time commentedon a paper 8 months ago
Phi: Preference Hijacking in Multi-modal Large Language Models at
Inference TimeOrganizations
