Multimodal Agents You Can Deploy Anywhere

David Cheng, Engineering Lead at Reka AI, discusses Reka's multimodal AI models designed for deployment across cloud, on-premises, and device environments. These models are capable of understanding text, images, video, and audio, addressing needs for applications like video analysis, speech-to-speech translation, and multimodal document understanding. The talk highlights how Reka models and their agentic framework can be used to build agents with advanced sensory and vocal capabilities.