Machine learning (ML), especially deep neural networks, has achieved great success, but
many of them often rely on a number of labeled samples for supervision. As sufficient …

It remains an open question whether incorporating external knowledge benefits
commonsense reasoning while maintaining the flexibility of pretrained sequence models. To …

Recent advances in the areas of multimodal machine learning and artificial intelligence (AI)
have led to the development of challenging tasks at the intersection of Computer Vision …

Pre-trained vision-language models, eg, CLIP, working with manually designed prompts
have demonstrated great effectiveness in transfer learning. Recently, learnable prompts …

Sources of commonsense knowledge support applications in natural language
understanding, computer vision, and knowledge graphs. Given their complementarity, their …

The success of language models has inspired the NLP community to attend to tasks that
require implicit and complex reasoning, relying on human-like commonsense mechanisms …

While vertical thinking relies on logical and commonsense reasoning, lateral thinking
requires systems to defy commonsense associations and overwrite them through …

Neural-symbolic computing (NeSy), which pursues the integration of the symbolic and
statistical paradigms of cognition, has been an active research area of Artificial Intelligence …

Commonsense knowledge is essential for many AI applications, including those in natural
language processing, visual processing, and planning. Consequently, many sources that …

Recently, large pretrained language models have achieved compelling performance on
commonsense benchmarks. Nevertheless, it is unclear what commonsense knowledge the …