arxiv:2602.10693
floyed shen
floyed
AI & ML interests
None yet
Recent Activity
submitted
a paper
about 5 hours ago
VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training upvoted a paper about 5 hours ago
DeepEyesV2: Toward Agentic Multimodal Model authored
a paper
6 days ago
Safety Instincts: LLMs Learn to Trust Their Internal Compass for Self-Defense Organizations
models 0
None public yet
datasets 0
None public yet