PPL
Yu Liu
Papers (6)
What Does the Server See? Understanding Privacy Leakage from Large Language Models in Split InferencePROVE: A Perceptual RemOVal cohErence Benchmark for Visual MediaFrom Token to Token Pair: Efficient Prompt Compression for Large Language Models in Clinical PredictionLASSA Architecture-Based Autonomous Fault-Tolerant Control of Unmanned Underwater VehiclesLLM-Guided Open Hypothesis Learning from Autonomous Scanning Probe Microscopy ExperimentsTowards Generation-Efficient Uncertainty Estimation in Large Language Models