Zehua Cheng

Curvature Graph Mergeability: Predicting Model Compatibility from Per-Layer Hessian Geometry

Merging independently trained neural networks --- via weight averaging, model soups, or task-vector arithmetic --- is increasingly central to large-scale model reuse, yet the success of any merge hinges on whether two parameter vectors occupy the same loss basin, a property currently certified only by expensive multi-p...

Imbuing Large Language Models with Bidirectional Logic for Robust Chain Repair

Invariant Gradient Alignment for Robust Reasoning Distillation