PPL
Jun Zhang
Papers (4)
Training-Free Long-Context Scaling of Large Language ModelsCode-QA-Bench: Separating Code Reasoning from Documentation Memorization in Repository-Level QAGeoGS-CE: Learning Delay--Beam Channel Priors with 3D Gaussians for High-Mobility ScenariosEfficient Verification of Neural Control Barrier Functions with Smooth Nonlinear Activations