About the Workshop

The AI for Accelerated Materials Discovery (AI4Mat) Workshop at ICLR 2026 provides an inclusive and collaborative platform where AI researchers and material scientists converge to tackle the cutting-edge challenges in AI-driven materials discovery and development. Our goal is to foster a vibrant exchange of ideas, breaking down barriers between disciplines and encouraging insightful discussions among experts from diverse disciplines and curious newcomers to the field. The workshop embraces a broad definition of materials design encompassing matter in various forms, such as crystalline and amorphous solid-state materials, glasses, molecules, nanomaterials, and devices. By taking a comprehensive look at automated materials discovery spanning AI-guided design, synthesis and automated material characterization, we hope to create an opportunity for deep, thoughtful discussion among researchers working on these interdisciplinary topics, and highlight ongoing challenges in the field.

Covering materials such as :

AI4Mat was first held at NeurIPS 2022, bringing together materials scientists and AI researchers into a common forum with productive discussion on major research challenges at the intersection of AI and materials science. Since then, AI4Mat has established itself as a leading venue for the exchange of ideas on the latest developments in the field, bridging together international academic, industry and government institutions. AI4Mat-NeurIPS-2023 highlighted the growing interest and expanding research community of this emerging field. This momentum continued with two workshops held in 2024 (AI4Mat-BOKU-2024 in Vienna and AI4Mat-NeurIPS-2024 in Vancouver) designed to further accelerate research progress. The field of AI-enabled materials discovery is increasingly propelled by a global and interdisciplinary research community, whose collaborative efforts are driving materials innovation toward tangible real-world impact across diverse applications. AI4Mat-ICLR-2025 in Singapore, AI4Mat's first workshop in Asia, focused on the role of foundation models and representation learning for materials science while continuing to build a more global community of researchers for the emerging field. AI4Mat-NeurIPS-2025 focused discussion on latest frontiers and approaches to benchmarking while introducing a new format of live feedback for selected papers through AI4Mat-RLSF (Research Learning from Speaker Feedback. AI4Mat-ICLR-2026, AI4Mat's first workshop in South America, aims to continue building upon prior success while continuing to push the research frontier and grow the global community. The AI4Mat-ICLR-2026 program will focus on:

Reinforcement Learning & Beyond: The Role of Feedback in AI for Materials Science: Feedback-driven learning has demonstrated substantial promise across diverse AI applications, from robotics to large language models. Materials science, however, presents unique challenges: experimental data is sparse, expensive to generate, and time-intensive to collect. Feedback-based approaches offer a compelling solution by creating iterative learning loops that integrate experimental outcomes, computational predictions, and expert knowledge. By incorporating this multifaceted feedback, such approaches can accelerate discovery workflows and guide more efficient exploration of the vast materials space, enabling the development of novel compounds and systems.
Cross-Modal, Unified Materials Representations – From Structure to Properties to Performance: AI4Mat-ICLR-2025 initiated a broader technical conversation on effective materials representations through its session “What are Next-Generation Representations of Materials Data?”. While our previous session and related discussion focused primarily on developing specialized representations for specific problem settings, AI4Mat-ICLR-2026 expands the scope to address a more fundamental challenge: fusing and aligning multiple data modalities. Real-world materials systems generate diverse data types—structural characterization, property measurements, and performance metrics—each with distinct characteristics and requirements. Meaningful insights, however, emerge only through unified understanding across these modalities. This session examines cutting-edge methods for integrating heterogeneous materials data sources into comprehensive predictive models that capture the full complexity of materials behavior. We will explore current approaches and open challenges in creating such integrated representations, with the goal of enabling frameworks that can reliably predict and optimize materials performance in practical applications.

Submissions

Check our submissions page for instructions on how to submit through OpenReview.
Accepted peer-reviewed submissions will be invited to present a poster at the workshop and posted on the workshop website for non-archival records. Some peer-reviewed submissions will be invited to present a spotlight talk.