The remarkable success of deep learning has prompted interest in its application to medical
imaging diagnosis. Even though state-of-the-art deep learning models have achieved …

Visual representation learning is ubiquitous in various real-world applications, including
visual comprehension, video understanding, multi-modal analysis, human-computer …

Existing visual question answering methods often suffer from cross-modal spurious
correlations and oversimplified event-level reasoning processes that fail to capture event …

The integration of Computer-Aided Diagnosis (CAD) with Large Language Models (LLMs)
presents a promising frontier in clinical applications, notably in automating diagnostic …

Existing methods for video question answering (VideoQA) often suffer from spurious
correlations between different modalities, leading to a failure in identifying the dominant …

Existing mainstream approaches follow the encoder-decoder paradigm for generating
radiology reports. They focus on improving the network structure of encoders and decoders …

Deep learning relies on learning from extensive data to generate prediction results. This
approach may inadvertently capture spurious correlations within the data, leading to models …

Existing visual question reasoning methods usually fail to explicitly discover the inherent
causal mechanism and ignore the complex event-level understanding that requires jointly …

We present CausalVLR (Causal Visual-Linguistic Reasoning), an open-source toolbox
containing a rich set of state-of-the-art causal relation discovery and causal inference …

With the surge in the development of large language models, embodied intelligence has
attracted increasing attention. Nevertheless, prior works on embodied intelligence typically …