AI researchers ’embodied’ an LLM into a robot – and it started channeling Robin Williams

AI researchers at Andon Labs embedded various LLMs in a vacuum robot to test how ready they were to be embodied. And hilarity ensued.
IEEE

Enhancing Visual Aligning and Grounding for Aerial Vision-and-Dialog Navigation

Abstract: Vision-and-Language Navigation tasks require an agent to navigate to a destination following natural language instructions. We focus on a challenging VLN dataset, Aerial Vision-and-Dialog ...
IEEE

Improving Cross-Modal Understanding in Visual Dialog Via Contrastive Learning

Abstract: Visual Dialog is a challenging vision-language task since the visual dialog agent needs to answer a series of questions after reasoning over both the image content and dialog history. Though ...