Stanford CS25: Transformers United V6 I From Representation Learning to World Modeling

Stanford Online

Stanford's CS25 introductory lecture traces the evolution from hand-engineered features to Transformer architectures, explaining how self-attention mechanisms enable parallel processing and long-context modeling, while exploring how billion-parameter language models develop emergent reasoning capabilities through next-token prediction on internet-scale data.

Stanford Online

This seminar introduces 'missile-scale' robotics (~1kg) as a critical gap between micro and macro robots, demonstrating that mechanical redundancy (morphological intelligence) enables reliable locomotion in unpredictable terrain without sensors by applying Shannon's information theory to legged locomotion, while biological gait-switching strategies can overcome inherent speed limitations.

Stanford Online

This seminar presents a paradigm shift in robot learning by replacing teleoperation with direct capture of human egocentric experience using wearable sensors, demonstrating that scaling human data—combined with alignment techniques like optimal transport—enables dramatic performance gains and zero-shot task transfer to robots.

Stanford Online

This lecture introduces GPU architecture for language model training, explaining the shift from serial CPU execution to parallel GPU throughput, the critical importance of memory hierarchies, and the SIMT programming model essential for efficient deep learning systems.