Language Models and Real World Representation
Raphaël discusses how language models encode spatial relationships, reflecting real-world structures. Tim explores the deep implications of distributional semantics and human brain representations, highlighting the complexity of forming accurate representations. Language models' inferential and referential competencies are crucial for understanding word meanings and interactions with the physical world, as evidenced by Google AI's work integrating language models with robots.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#107 - Dr. RAPHAËL MILLIÈRE - Linguistics, Theory of Mind, Grounding
Related Questions