Call for Papers

Workshop Scope

Scale-to-See establishes a dedicated forum at the intersection of high-performance computing (HPC), artificial intelligence (AI), scientific imaging, and high-dimensional spatiotemporal data. While AI for science, large-scale simulation, and imaging are each active areas, there is currently no cohesive venue focused on AI methods and systems designed to operate at extreme HPC scale for imaging and spatiotemporal inference.

Scientific imaging and spatiotemporal data—arising in domains such as medical imaging, climate and weather, earth systems, materials science, manufacturing, bioengineering, and cosmology—are increasingly high-dimensional, multimodal, and time-evolving. Advancing these fields requires AI that is not only accurate, but also scalable, physics-aware, reproducible, and deployable on leadership-class HPC systems.

This workshop aims to answer this central question:
How do we design AI methods and systems that operate natively at HPC scale, respect physical constraints, and transform scientific imaging and spatiotemporal inference?

Topics

Topics include but are not limited to:

1. HPC-Aware AI Methods for Vision and Imaging Tasks
   AI models whose architectures, training strategies, and optimization methods are explicitly co-designed with HPC constraints, including extreme parallelism, memory hierarchies, communication costs, and heterogeneous accelerators.

2. Scalable AI Systems for Spatiotemporal Data
   End-to-end systems for training, inference, and deployment of AI models on massive spatiotemporal datasets, including data assimilation, surrogate modeling, and real-time or near-real-time workflows.

3. Scalable Algorithms for Neural Imaging
   Algorithms for inverse problems, reconstruction, enhancement, and multimodal fusion in scientific imaging that integrate physics, uncertainty quantification, and learning, while scaling efficiently across thousands to millions of cores.

4. Efficient Computing Techniques for Scientific Imaging and High-Dimensional Data
   Techniques such as mixed precision, model and data parallelism, communication-avoiding algorithms, adaptive resolution, and hardware-aware optimization that enable AI workloads to scale efficiently and sustainably on modern HPC platforms.

Submission Format:

In general, the format requirements are the same as SC'26 workshop requirement.

• The review process is double-blind, i.e. the names of the authors, reviewers, and area chairs are not revealed to each other. Papers must thus be properly anonymized before submission. 

• Domain conflicts: To avoid conflict of interest among the authors, reviewers and meta-reviewers, all co-author information and a complete and accurate list of domain conflicts must be entered in the submission form by the submission deadline. For the same reason (to avoid conflict of interest during the review process), the author list must be complete at submission time.

Paper Publication:

Accepted papers will be published by SC'26 proceedings. Among the accepted full papers, Scale-to-see will give one award to the best paper with certification.