Work

DyPARS: Dynamic-Shape DNN Optimization via Pareto-Aware MCTS for Graph Variants

Year: 2025

Type: conference-paper

Abstract: This is the artifact for the CGO'26 paper titled "DyPARS: Dynamic-Shape DNN Optimization via Pareto-Aware MCTS for Graph Variants". It includes a Docker image, source code, and a README file.

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.16758226

Authors: Qian, Hao, Li, Guangli, Yu, Qiuchu, Wang, Xueying, Xue, Jingling

Language: English

Topic: Parallel Computing and Optimization Techniques

Subfield: Hardware and Architecture

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7076529322

FWCI:

Cites:

Cited by:

Related to: