@article{hscalehessianguidedscalerefinementfornvf, title = {H-Scale: Hessian-Guided Scale Refinement for NVFP4 Sub-Byte LLM Inference}, author = {Hao Yu and Zheng Li and Dayiheng Liu and Jianwei Zhang}, year = {2026}, eprint = {2608.28113}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2608.28113}, }