PPL
Yi Liu
Papers (11)
SNARE: Adaptive Scenario Synthesis for Eliciting Overeager Behavior in Coding AgentsMIRAGE: Context-Aware Prompt Injection against Mobile GUI Agents via User-Generated ContentA Unified Framework for the Evaluation of LLM Agentic CapabilitiesTowards end-to-end LLM-based censoring-aware survival analysisRADAR: Defending RAG Dynamically against Retrieval CorruptionDisentangling Generation and Regression in Stochastic Interpolants for Controllable Image RestorationSemi-MedRef: Semi-Supervised Medical Referring Image Segmentation with Cross-Modal AlignmentCAMPA: Efficient and Aligned Multimodal Graph Learning via Decoupled Propagation and AggregationEnvSimBench: A Benchmark for Evaluating and Improving LLM-Based Environment SimulationWhen Can Voting Help, Hurt, or Change Course? Exact Structure of Binary Test-Time AggregationTwo Calls, Two Moments, and the Vote-Accuracy Curve of Repeated LLM Inference