Early December, 2026, Singapore
In the rapidly advancing era of artificial intelligence, large models have become the cornerstone of transformative technologies, reshaping how machines perceive, reason, and interact with the world. Beyond standalone models, the emergence of large-model-powered applications, AI agents, and embodied AI systems has unlocked unprecedented capabilities across diverse domains. However, alongside these breakthroughs come growing concerns regarding safety, reliability, robustness, and ethical responsibility, making large model safety a critical priority for the AI community.
To address these pressing challenges, we are proud to introduce the Large Model Safety Workshop 2026, a dedicated forum for researchers, practitioners, and industry leaders to explore the evolving safety landscape of large models and their real-world deployments. This workshop aims to foster in-depth discussions on emerging threats, novel attack paradigms, system-level vulnerabilities, and comprehensive risk mitigation strategies across models, agents, and embodied intelligence.
This engaging workshop will feature a series of expert talks, technical presentations, and interactive discussions covering the full spectrum of large model safety. Topics will range from foundational safety mechanisms and adversarial robustness to secure agent design, alignment in embodied environments, and responsible deployment practices. Whether you are a seasoned AI researcher or new to the field, this workshop offers a unique opportunity to gain insights into the multifaceted challenges of ensuring trustworthy, ethical, and secure AI systems in the age of large-scale intelligent technologies.
We welcome organizations and companies to partner with us and support this workshop.
If you are interested in becoming a Workshop Partner, please contact: AIDX TECH PTE. LTD. (aidxtech0426@gmail.com).
Detailed sponsorship packages and benefits will be announced soon.
