NANOZK: Layerwise Zero-Knowledge Proofs for Verifiable Large Language Model Inference

ArXi:2603.18046v1 Announce Type: cross When users query Our approach exploits the fact that transformer inference naturally decomposes into independent layer computations, enabling a layerwise proof framework where each layer generates a constant-size proof regardless of model width. This decomposition sidesteps the scalability barrier facing monolithic approaches and enables parallel proving.