Call for Papers

Artificial Intelligence (AI) and Machine Learning (ML) are transforming scientific discovery, driving breakthroughs in climate modeling, materials discovery, astrophysics, drug development, and many other domains. AI for Science (AI4S) focuses on developing and applying computational learning and machine intelligence to accelerate innovation in scientific research. Recent years have witnessed AI-driven advances that have reshaped the landscape of scientific research. AI methods have been successfully applied to predict extreme weather events with greater accuracy, identify exoplanets among trillions of sky pixels, accelerate numerical solvers for fluid dynamics and physics-based simulations, design novel materials and chemical processes, improve drug discovery pipelines, and help uncover fundamental insights into the universe. At the same time, generative AI is revolutionizing not only scientific computing but also broader societal applications. However, despite these advancements, several fundamental challenges remain in effectively integrating AI/ML into scientific workflows, particularly when leveraging high-performance computing (HPC) resources. One of the most pressing questions is how to systematically and automatically apply AI/ML techniques to complex scientific applications while ensuring reliability, interpretability, and efficiency. The integration of domain knowledge, such as conservation laws, invariants, causality, and symmetries, remains an open problem that requires deeper exploration. Additionally, enhancing the robustness of AI models for HPC environments and making them interpretable for scientific analysis is a crucial step toward broader adoption. Foundation models designed for scientific applications need further refinement to meet domain-specific requirements, and significant efforts are needed to reduce the energy cost of large-scale AI training. Ensuring that AI/ML frameworks are approachable and efficient for the broader HPC community is another important challenge, along with effectively utilizing extreme-scale HPC systems and emerging AI accelerators to unlock new scientific possibilities.

Topics will include but will not be limited to:

Advancing scientific discovery and development workflows through generative AI models;

Strategies for reducing the energy consumption of AI model training and inference;

Investigating the impact of quantization and reduced precision techniques on the accuracy and correctness of AI-driven scientific applications;

Novel AI/ML approaches for improving execution time, efficiency, and simulation accuracy;

Characterizing the impact, accuracy, and effectiveness of AI/ML for scientific workloads;

Leveraging HPC systems to accelerate training and inference of AI/ML models on large-scale scientific datasets;

Addressing scalability, optimization, and efficiency issues when deploying AI/ML on extreme-scale HPC platforms;

Methods for integrating domain knowledge, including physical laws and constraints, into AI-driven scientific modeling;

Replacing or augmenting traditional numerical methods with AI/ML models for computational efficiency;

Tools, frameworks, and infrastructure to enhance the usability and accessibility of AI in scientific applications;

Methods to improve interpretability, explainability, and robustness of AI models for critical scientific applications;

Performance evaluation and benchmarking of emerging AI accelerators (e.g., GPUs, TPUs, FPGAs, neuromorphic computing) for scientific workloads;

The AI4S workshop provides a platform for experts from academia, government, and industry to explore these challenges, share recent advances, and discuss emerging opportunities in AI-driven scientific discovery. The workshop aims to bridge the gap between AI research and scientific applications by bringing together computer scientists, domain experts, and HPC practitioners to exchange ideas and foster collaboration. By showcasing cutting-edge AI/ML advancements, identifying key challenges in deploying AI at scale, and facilitating discussions on the future of AI in science, this workshop will serve as a catalyst for accelerating AI adoption in scientific research.

Submission

Authors are invited to submit manuscripts in English structured as technical papers up to 8 pages 2-column pages, min 5 pages (U.S. letter – 8.5″x11″), excluding the bibliography, using the ACM proceedings template that is available at here. The manuscripts are single-blind. Word authors can use the “Interim Layout”. Submissions not conforming to these guidelines may be returned without review.

All manuscripts will be peer-reviewed and judged on correctness, originality, technical strength, and significance, quality of presentation, and interest and relevance to the workshop attendees. Submitted papers must represent original unpublished research that is not currently under review for any other conference or journal. Papers not following these guidelines will be rejected without review and further action may be taken, including (but not limited to) notifications sent to the heads of the institutions of the authors and sponsors of the conference. Submissions received after the due date, exceeding length limit, or not appropriately structured may also not be considered. At least one author of an accepted paper must register for and attend the workshop. Authors may contact the workshop organizers for more information.

Papers should be submitted electronically at: https://submissions.supercomputing.org, SC26 Workshop: AI4S'26: Workshop on Artificial Intelligence and Machine Learning for Scientific Applications".

The final papers will be published in the SC Workshops Proceedings.

Important Dates

TBD