activity
20242026
collaborators
Showing cs.ARShow all

7 papers · 1 filter

cs.AR2026

Characterizing State Space Model and Hybrid Language Model Performance with Long Context

Saptarshi Mitra, Rachid Karami, Haocheng Xu +2

Emerging applications such as AR are driving demands for machine intelligence capable of processing continuous and/or long-context inputs on local devices. However, currently domin…

cs.AR2025

D-com: Accelerating Iterative Processing to Enable Low-rank Decomposition of Activations

Faraz Tahmasebi, Michael Pelluer, Hyoukjun Kwon

The computation and memory costs of large language models kept increasing over last decade, which reached over the scale of 1T parameters. To address the challenges from the large…

cs.AR2025

FlexiBit: Fully Flexible Precision Bit-parallel Accelerator Architecture for Arbitrary Mixed Precision AI

Faraz Tahmasebi, Yian Wang, Benji Y. H. Huang +1

Recent research has shown that large language models (LLMs) can utilize low-precision floating point (FP) quantization to deliver high efficiency while maintaining original model a…

cs.AR2025

Understanding the Performance Horizon of the Latest ML Workloads with NonGEMM Workloads

Rachid Karami, Sheng-Chun Kao, Hyoukjun Kwon

Among ML operators today, GEneralMatrix Multiplication (GEMM)-based operators are known to be key operators that build the main backbone of ML models. As their computational overhe…

cs.AR2024

Performance Implications of Multi-Chiplet Neural Processing Units on Autonomous Driving Perception

Mohanad Odema, Luke Chen, Hyoukjun Kwon +1

We study the application of emerging chiplet-based Neural Processing Units to accelerate vehicular AI perception workloads in constrained automotive settings. The motivation stems…

cs.AR2024

Optimized Spatial Architecture Mapping Flow for Transformer Accelerators

Haocheng Xu, Faraz Tahmasebi, Ye Qiao +3

Recent innovations in Transformer-based large language models have significantly advanced the field of general-purpose neural language understanding and generation. With billions o…