Google, IBM & Meta Certificates – 40% Off
One plan covers every Professional Certificate on Coursera.
Unlock All Certificates
This video explores a groundbreaking study by researchers from NVIDIA, Stanford University, and MIT on Visual Chain-of-Thought (CoT) reasoning. Learn how these researchers have developed a method to transpose linguistic chain-of-thought reasoning into the visual domain, enabling AI systems to generate sub-goal images for Vision-Language-Action (VLA) models. Discover the implications of this innovation for robotic AI models and complex visual reasoning tasks. The 22-minute presentation covers the collaborative work of researchers Qingqing Zhao, Yao Lu, Moo Jin Kim, Zipeng Fu, Zhuoyang Zhang, Yecheng Wu, Zhaoshuo Li, Qianli Ma, Song Han, Chelsea Finn, Ankur Handa, Ming-Yu Liu, Donglai Xiang, Gordon Wetzstein, and Tsung-Yi Lin from NVIDIA, Stanford University, and MIT on their paper "CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models."
