2 papers
cs.AR2025
SCRec: A Scalable Computational Storage System with Statistical Sharding and Tensor-train Decomposition for Recommendation Models
Jinho Yang, Ji-Hoon Kim, Joo-Young Kim
Deep Learning Recommendation Models (DLRMs) play a crucial role in delivering personalized content across web applications such as social networking and video streaming. However, w…
cs.AR2025
EXION: Exploiting Inter- and Intra-Iteration Output Sparsity for Diffusion Models
Jaehoon Heo, Adiwena Putra, Jieon Yoon +4
Over the past few years, diffusion models have emerged as novel AI solutions, generating diverse multi-modal outputs from text prompts. Despite their capabilities, they face challe…