Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Unlocking Lossless Speedups in LLMs via Discrete Diffusion
Subham Sekhar Sahoo, Lingjie Chen, Khiem Pham +14
Large Language Models (LLMs) owe much of their success to next-token prediction (NTP), but their autoregressive (AR) structure requires slow, sequential token generation. To overco…
cs.LG2025
any4: Learned 4-bit Numeric Representation for LLMs
Mostafa Elhoushi, Jeff Johnson
We present any4, a learned 4-bit weight quantization solution for large language models (LLMs) providing arbitrary numeric representations without requiring pre-processing of weigh…