PPL
Rui Zhang
Papers (9)
A Policy-Driven Runtime Layer for Agentic LLM ServingNPSolver: Neural Poisson Solver with Iterative Physics SupervisionFrom Correctness to Preference: A Framework for Personalized Agentic Reinforcement LearningVeriCache: Turning Lossy KV Cache into Lossless LLM InferenceA Systematic Evaluation of Imbalance Handling Methods in Biomedical Binary ClassificationElastic Attention Cores for Scalable Vision TransformersWhen Relations Break: Analyzing Relation Hallucination in Vision-Language Model Under Rotation and NoiseGeometry-Aware Neural Optimizer for Shape Optimization and InversionPerFlow: Physics-Embedded Rectified Flow for Efficient Reconstruction and Uncertainty Quantification of Spatiotemporal Dynamics