collaborators

5 papers

cs.AR2025

A Digital SRAM-Based Compute-In-Memory Macro for Weight-Stationary Dynamic Matrix Multiplication in Transformer Attention Score Computation

Jianyi Yu, Tengxiao Wang, Yuxuan Wang +6

Compute-in-memory (CIM) techniques are widely employed in energy-efficient artificial intelligent (AI) processors. They alleviate power and latency bottlenecks caused by extensive…

cs.LG2025

Routing Mamba: Scaling State Space Models with Mixture-of-Experts Projection

Zheng Zhan, Liliang Ren, Shuohang Wang +5

Linear State Space Models (SSMs) offer remarkable performance gains in efficient sequence modeling, with constant inference-time computation and memory complexity. Recent advances,…

cs.LG2025

Optimal Embedding Learning Rate in LLMs: The Effect of Vocabulary Size

Soufiane Hayou, Liyuan Liu

Pretraining large language models is a costly process. To make this process more efficient, several methods have been proposed to optimize model architecture/parametrization and ha…

cs.LG2025

An Introduction to Discrete Variational Autoencoders

Alan Jeffares, Liyuan Liu

Variational Autoencoders (VAEs) are well-established as a principled approach to probabilistic unsupervised learning with neural networks. Typically, an encoder network defines the…

cs.LG2024

LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy

Rongzhi Zhang, Kuang Wang, Liyuan Liu +4

The Key-Value (KV) cache is a crucial component in serving transformer-based autoregressive large language models (LLMs), enabling faster inference by storing previously computed K…