PrismQuant achieves near rate-distortion optimality for Gaussian-mixture sources by losslessly transmitting the mixture component label at H(C)/n bits per dimension and applying component-matched KLT plus scalar quantization, with vanishing gap to the genie-aided bound.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Factual recall quality in LLMs follows a sigmoid scaling law in the log-linear combination of model parameter count and topic frequency in training data, explaining 60% of variance across models and up to 94% within families.
citing papers explorer
-
PrismQuant: Rate-Distortion-Optimal Vector Quantization for Gaussian-Mixture Sources
PrismQuant achieves near rate-distortion optimality for Gaussian-mixture sources by losslessly transmitting the mixture component label at H(C)/n bits per dimension and applying component-matched KLT plus scalar quantization, with vanishing gap to the genie-aided bound.
-
Predictable Confabulations: Factual Recall by LLMs Scales with Model Size and Topic Frequency
Factual recall quality in LLMs follows a sigmoid scaling law in the log-linear combination of model parameter count and topic frequency in training data, explaining 60% of variance across models and up to 94% within families.