PPL
Yu Feng
Papers (5)
BLINK: Multimodal Large Language Models Can See but Not PerceiveNo Attack Required: Semantic Fuzzing for Specification Violations in Agent SkillsOptions, Not Clicks: Lattice Refinement for Consent-Driven MCP AuthorizationHEDP: A Hybrid Energy-Distance Prompt-based Framework for Domain Incremental LearningOn the (In-)Security of the Shuffling Defense in the Transformer Secure Inference