Explore the intersection of language and vision in this 59-minute lecture by Andrei Barbu from MIT. Delve into topics such as communication, deep networks, and deep RT, while examining the integration of language into AI systems. Discover sampling-based planners, multi-tasking in AI, and the concept of theory of mind. Investigate joint distributions, paraphrasing techniques, and the importance of compositionality in language and vision tasks. Gain insights into both small-scale and large-scale questions in this field, and participate in a poster session to further discuss and explore these cutting-edge concepts.