|
| |||||||||||||||
PAISE 2026 : 8th Workshop on Parallel AI and Systems for the Edge | |||||||||||||||
| Link: https://paise.org | |||||||||||||||
| |||||||||||||||
Call For Papers | |||||||||||||||
|
PAISE 2026: 8th Workshop on Parallel AI and Systems for the Edge
Co-located with IPDPS 2026, 26th May 2026, New Orleans, USA. Edge computing is revolutionizing the computing landscape, from applications to hardware platforms. Building on the success of previous years and incorporating valuable feedback from in-person attendees at the 2023, 2024 and 2025 workshops, PAISE 2026 will feature a carefully balanced mix of interactive sessions and traditional technical talks. The goal is to foster organic discussions that complement traditional paper presentations, offering a much-needed platform to explore current trends, share visions, exchange feedback, and discuss solutions in the following key areas of edge computing: • applications — computer vision, machine learning, analytics, IoT; • data flows — processing pipeline of data from ingestion to archival, pipeline of AI from learning to inference; • control flows — parallel and distributed programming models and runtimes for managing constrained resources, cybersecurity; and • infrastructure — storage, compute, and connectivity conducive to resource-constrained and harsh edge environments. Call for Papers All submitted papers must be original and will undergo a rigorous peer review process, evaluated by three independent reviewers. The following paper categories are welcome: • Full Papers: Full research papers should present original work that has not been submitted simultaneously to another journal or conference. Submissions must be limited to 8 pages, including all figures, tables and references. Accepted papers will be allocated 20 minutes for presentation, followed by 5 min for discussions. • Short Papers: Submissions may include research papers, position papers, vision papers, conceptual ideas, demo descriptions, or practice reports. These should be limited to 4 pages, including all figures, tables and references, and must provide sufficient detail for the program committee to assess their potential to spark discussions at the workshop. Accepted papers will be allocated 15 minutes for presentation, followed by 5 min for discussions. Accepted full and short papers will be published in the IPDPS workshop proceedings. For detailed paper submission instructions, please visit the workshop webpage at https://paise.org. Topics The following research topics are welcome: 1. Edge AI Models, Learning, and Inference • Collaborative, distributed, and decentralized learning at the edge • Communication-efficient distributed learning • Hybrid distributed/decentralized learning models • Multi-agent reinforcement learning at the edge • Early-exit and resource-aware inference mechanisms • Learning-based resource management at the edge 2. Edge Applications and Emerging Workloads • AI and IoT applications at the edge • Digital twins and other edge-driven applications • Emerging edge workloads and novel systems support 3. Systems, Architecture, and Programming Models for Edge Computing • Serverless and other programming models for edge environments • DevOps practices across edge and cloud • Multitenancy and resource sharing at the edge • Edge-driven HPC and HPC-steered edge computing • Energy-efficient, low-power, and sustainable hardware/software architectures • Green and sustainable Edge AI 4. Data, Security, and Lifecycle Management • Cyber-security and privacy in edge computing • Security and privacy for distributed learning and inference • Data and AI lifecycle management across edge and cloud • Submission Instructions For the most current submission information, please refer to the PAISE workshop page: https://paise.org/cfp. Important Dates • January 31st 2026: Submission deadline. • February 21st 2026: Notification of acceptance. • March 6th 2026: Camera ready papers due. • May 26th 2026: Workshop. Workshop Organizers • Laurent Lefèvre, Inria, Lyon, France • Rajesh Sankaran, Argonne National Laboratory • Hulya Seferoglu, University of Illinois Chicago • Omesh Tickoo, Intel Advanced Technology Group |
|