Autonomous visual information seeking with large language models

There has been great progress towards adapting large language models (LLMs) to accommodate multimodal inputs for tasks including image captioningvisual question answering (VQA), and open vocabulary recognition. Despite such achievements, current state-of-the-art visual language models (VLMs) perform inadequately on visual information seeking datasets, such as Infoseek and OK-VQA, where external knowledge is required to answer the questions. — Read More

#frameworks

AI-powered drone beats human champion pilots

Having trounced humans at everything from chess and Go, to StarCraft and Gran Turismo, artificial intelligence (AI) has raised its game and defeated world champions at a real-world sport.

The latest mortals to feel the sting of AI-induced defeat are three expert drone racers who were beaten by an algorithm that learned to fly a drone around a 3D race course at breakneck speeds without crashing. Or at least not crashing too often. — Read More

#robotics

Baidu and SenseTime launch ChatGPT-style AI bots to the public


Chinese tech firms Baidu and SenseTime launched their ChatGPT-style AI bots to the public on Thursday, marking a new milestone in the global AI race.

Baidu has opened public access to its ERNIE Bot, allowing users to conduct AI-powered searches or carry out an array of tasks, from creating videos to providing summaries of complex documents. — Read More

#china-ai