Xinfeng Li
~Xinfeng_Li1
5
论文总数
5.0
年均投稿
平均评分
接收情况4/5
会议分布
NeurIPS
4
ICLR
1
发表论文 (5 篇)
20255 篇
4
AgentAuditor: Human-level Safety and Security Evaluation for LLM Agents
NeurIPS 2025Poster
4
Prompt-Independent Safe Decoding to Restrain Unsafe Image Generation for Text-to-Image Models against White-Box Adversary
ICLR 2025Rejected
4
SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG
NeurIPS 2025Poster
4
Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
NeurIPS 2025Poster
4
GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning
NeurIPS 2025Poster