Xinfeng Li
- Adversarial Attacks against Closed-Source MLLMs via Feature Optimal Alignment
- AgentAuditor: Human-level Safety and Security Evaluation for LLM Agents
- GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning
- LIFEBENCH: Evaluating Length Instruction Following in Large Language Models
- MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix
- MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios
- SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG