5 papers
What Makes Recurrence Effective in Looped Language Models?
Xinlin Zhuang, Siyuan Wang, Imran Razzak +1
Looped language models (LoopLMs) increase computational depth through parameter sharing, offering a path to scale inference computation without adding parameters. However, it remai…
Denoise First, Orthogonalize Later: Understanding Momentum in Muon via Spectral Filtering
Xianliang Li, Zihan Zhang, Weiyang Liu +1
Muon has recently demonstrated strong empirical performance in large language model training, but the theoretical role of momentum in Muon remains unclear. Existing analyses of Muo…
AMO: Operator-level Adaptive Muon Orthogonalization
Xinlin Zhuang, Panyi Ouyang, Yichen Li +7
Muon has recently emerged as a competitive alternative to AdamW for large-scale pre-training, with orthogonalization via Newton-Schulz (NS) iteration as its core operation. Standar…
Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation
Yao Teng, Fuyun Wang, Xian Liu +7
As a new paradigm of visual content generation, autoregressive text-to-image models suffer from slow inference due to their sequential token-by-token decoding process, often requir…
SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator
Guoxuan Chen, Han Shi, Jiawei Li +7
Large Language Models (LLMs) have exhibited exceptional performance across a spectrum of natural language processing tasks. However, their substantial sizes pose considerable chall…