Showing 2026Show all
2 papers · 1 filter
cs.LG2026
ScaleSweep: Accurate NVFP4 Post-Training Quantization of LLMs via Block Scale Initialization
Li Lin, Xiaojun Wan
NVFP4 is a recently introduced hardware-supported FP4 format that improves the fidelity of 4-bit quantization through fine-grained block scales. However, existing NVFP4 scale initi…
cs.CL2026
QuantileMark: A Message-Symmetric Multi-bit Watermark for LLMs
Junlin Zhu, Baizhou Huang, Xiaojun Wan
As large language models become standard backends for content generation, practical provenance increasingly requires multi-bit watermarking. In provider-internal deployments, a key…