2 papers
cs.DB2026
Contextual Utility of Quantization Moves in Extreme Low-Bit LLMs
Wenxuan Xiao, Xu Cao
Accurate measurements of isolated weight replacements need not predict their joint effect on a quantized model. We study this gap for legal replacements at a fixed bitrate, separat…
cs.DB2026
When Does Low-Bit Quantization Preserve the Decisions of Vector Search?
Wenxuan Xiao, Xu Cao
Low-bit quantization can achieve high recall on some vector representations and fail sharply on others, while average distortion and global rank correlation do not explain the diff…