Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Dystruct: Dynamically Structured Diffusion Language Model Decoding via Bayesian Inference
Bian Sun, Kevin Zhai, Mubarak Shah +1
Diffusion language models (DLMs) have recently emerged as a promising alternative to autoregressive models, primarily due to their ability to enable parallel decoding. Despite this…
cs.LG2025
Layer-wise dynamic rank for compressing large language models
Zhendong Mi, Bian Sun, Grace Li Zhang +1
Large language models (LLMs) have rapidly scaled in size, bringing severe memory and computational challenges that hinder their deployment. Singular Value Decomposition (SVD)-based…