CodeMasters Talks: The Future of Multi-Modal GenAI

​Where Research Meets Reality in the Next Wave of AI

​Generative AI is rapidly evolving beyond text, enabling systems to understand and generate across multiple modalities—language, vision, audio, and even 3D environments. The first edition of CodeMasters Talks explores this frontier, bringing together researchers and practitioners working at the edge of what's next.

​🔍 Inside the Talks
Two expert keynotes will dive into the architecture and training of multi-modal generative models—how disparate data points are fused across modalities, the challenges of aligning inputs like text, image, and sound, and what it takes to push models toward embodied AI that can interpret and operate in 3D environments.

​🤝 90 Minutes of Curated Peer Networking
Over 70% of the evening is dedicated to meaningful exchange among peers. Expect high-level discussions with AI PhDs, ML engineers, researchers, and CTOs tackling real-world challenges: model deployment, infrastructure scaling, and the future of foundation models.

​Who Should Join:
– PhDs in AI and Computer Vision
– Senior ML and Software Engineers
– Technical Architects and CTOs
– Researchers in foundation models, robotics, and 3D AI