The incorporation of physical information in machine learning frameworks is opening and
transforming many application domains. Here the learning process is augmented through …

The goal of the growing discipline of neuro-symbolic artificial intelligence (AI) is to develop
AI systems with more human-like reasoning capabilities by combining symbolic reasoning …

Object-centric representations are a promising path toward more systematic generalization
by providing flexible abstractions upon which compositional world models can be built …

Reasoning in the real world is not divorced from situations. How to capture the present
knowledge from surrounding situations and perform reasoning accordingly is crucial and …

Understanding dynamics from visual observations is a challenging problem that requires
disentangling individual objects from the scene and learning their interactions. While recent …

Reasoning, a crucial ability for complex problem-solving, plays a pivotal role in various real-
world settings such as negotiation, medical diagnosis, and criminal investigation. It serves …

In this paper, we propose a novel task IntentQA, a special VideoQA task focusing on video
intent reasoning, which has become increasingly important for AI with its advantages in …

Video Question Answering (VideoQA) aims to answer natural language questions according
to the given videos. It has earned increasing attention with recent research trends in joint …

There is a growing trend to design hybrid neural networks (HNNs) by combining spiking
neural networks and artificial neural networks to leverage the strengths of both. Here, we …

While large language models (LLMs), such as GPT-3, appear to be robust and general, their
reasoning ability is not at a level to compete with the best models trained for specific natural …