2 papers
cs.LG2026
KBBQ: A Predictive Noise Law and the Limits of Spectrum Flattening in FP4 Quantization
Lexington Whalen, Yuki Ito, Ryo Sakamoto
We develop a second-order theory of quantization noise in matrix multiplication in which the quantization format is characterized by the variance it assigns to each element. The co…
cs.CL2026
Teaching Diffusion to Speculate Left-to-Right
Lexington Whalen, Yuki Ito, Ryo Sakamoto
Large language models (LLMs) achieve remarkable performance across a wide range of tasks, but their autoregressive decoding process incurs substantial inference costs due to inhere…