PPL
Yang Xu
Papers (5)
GUITestScape: Towards Open-set Evaluation on Exploratory GUI TestingCore-Halo Decomposition: Decentralizing Large-Scale Fixed-Point ProblemsOnline Bayesian Calibration under Gradual and Abrupt System ChangesTowards Reliable LLM Evaluation: Correcting the Winner's Curse in Adaptive BenchmarkingAGPO: Asymmetric Group Policy Optimization for Verifiable Reasoning and Search Ads Relevance at JD