Shiba AI Members Present their paper at ICML 2026 in Seoul

ArticleRidhi Mahajan

Representing Shiba AI on a Global Stage

Shiba AI is pleased to share that several members of our research team attended the International Conference on Machine Learning (ICML) 2026 in Seoul, one of the most prominent venues in the field of machine learning. Over the course of the week, our members presented their research, exchanged ideas with leading researchers, and strengthened the lab's connections across the international AI community. Representing Shiba AI were Ujwal K, Alice Saito, Hershraj Niranjani, and Rayan Yessou.

Presenting "Evolving Interpretable Constitutions for Multi-Agent Coordination"

At the conference, the team presented their paper, "Evolving Interpretable Constitutions for Multi-Agent Coordination," which examines how multi-agent systems can autonomously discover their own behavioural norms while keeping those norms transparent and human-readable. The work reflects the lab's broader commitment to building AI systems that are not only capable, but also interpretable and amenable to meaningful human oversight. The full paper is available here.

Shiba AI members at ICML 2026 in Seoul Ujwal and Alice presenting the team's research

Scenes from ICML 2026 in Seoul: presenting the team's research and connecting with the global community.

Building Connections Across the Research Community

Beyond the presentation itself, the week offered valuable opportunities to engage with researchers from around the world, sharing perspectives, discussing emerging directions in AI safety and alignment, and forming collaborations that we look forward to continuing. We are grateful to the ICML community, and to everyone who stopped by, for a productive and inspiring week in Seoul.

To follow our lab's ongoing contributions to international AI safety initiatives or explore our collaborative research tracks, visit Shiba AI Research or get in touch through our Contact Page.