Visual knowledge is a new form of knowledge representation that can encapsulate visual
concepts and their relations in a succinct, comprehensive, and interpretable manner, with a …

An important task for intelligent systems is affordance grounding where the goal is to locate
regions on an object where an action can be performed. Past weakly supervised …

Affordance grounding aims to localize the interaction regions for the manipulated objects in
the scene image according to given instructions, which is essential for Embodied AI and …

As a prominent research area, visual reasoning plays a crucial role in AI by facilitating
concept formation and interaction with the world. However, current works are usually carried …

Embodied AI represents a crucial step towards achieving Artificial General Intelligence
(AGI). The next paradigm of Embodied AI involves physical embodiment, enhanced …

Intelligent robots need to interact with diverse objects across various environments. The
appearance and state of objects frequently undergo complex transformations depending on …

Recent years in natural language processing (NLP) research have seen a paradigm shift
toward foundational language models (LMs), which are self-supervised, transformer-based …