Related papers: Causal Reasoning Meets Visual Representation Learn…

Recently, deep learning has been advancing the state of the art in artificial intelligence to a new level, and humans rely on artificial intelligence techniques more than ever. However, even with such unprecedented advancements, the lack of…

Modern deep learning models excel at pattern recognition but remain fundamentally limited by their reliance on spurious correlations, leading to poor generalization and a demand for massive datasets. We argue that a key ingredient for…

Medical multimodal representation learning aims to integrate heterogeneous data into unified patient representations to support clinical outcome prediction. However, real-world medical datasets commonly contain systematic biases from…

While visual imitation learning offers one of the most effective ways of learning from visual demonstrations, generalizing from them requires either hundreds of diverse demonstrations, task specific priors, or large, hard-to-train…

Visual reasoning is dominated by end-to-end neural networks scaled to billions of model parameters and training examples. However, even the largest models struggle with compositional reasoning, generalization, fine-grained spatial and…

Rapid progress in video models has largely focused on visual quality, leaving their reasoning capabilities underexplored. Video reasoning grounds intelligence in spatiotemporally consistent visual environments that go beyond what text can…

Understanding how individuals interpret charts is a crucial concern for visual data communication. This imperative has motivated a number of studies, including past work demonstrating that causal priors -- a priori beliefs about causal…

While Reinforcement Learning (RL) achieves tremendous success in sequential decision-making problems of many domains, it still faces key challenges of data inefficiency and the lack of interpretability. Interestingly, many researchers have…

Causality knowledge is crucial for many artificial intelligence systems. Conventional textual-based causality knowledge acquisition methods typically require laborious and expensive human annotations. As a result, their scale is often…

Causal reasoning is a cornerstone of human intelligence and a critical capability for artificial systems aiming to achieve advanced understanding and decision-making. This thesis delves into various dimensions of causal reasoning and…

Reasoning about temporal causality, particularly irreversible transformations of objects governed by real-world knowledge (e.g., fruit decay and human aging), is a fundamental aspect of human visual understanding. Unlike temporal perception…

Recent advances in vision-language models (VLMs) have enabled impressive multi-modal reasoning and understanding. Yet, whether these models truly grasp visual persuasion-how visual cues shape human attitudes and decisions-remains unclear.…

Effectiveness and interpretability are two essential properties for trustworthy AI systems. Most recent studies in visual reasoning are dedicated to improving the accuracy of predicted answers, and less attention is paid to explaining the…

Causal reasoning capability is critical in advancing large language models (LLMs) toward strong artificial intelligence. While versatile LLMs appear to have demonstrated capabilities in understanding contextual causality and providing…

Visual Commonsense Reasoning (VCR) refers to answering questions and providing explanations based on images. While existing methods achieve high prediction accuracy, they often overlook bias in datasets and lack debiasing strategies. In…

Causal structure learning refers to a process of identifying causal structures from observational data, and it can have multiple applications in biomedicine and health care. This paper provides a practical review and tutorial on scalable…

Despite the rapid progress of multimodal large language models (MLLMs), they have largely overlooked the importance of visual processing. In a simple yet revealing experiment, we interestingly find that language-only models, when provided…

Causal reasoning is the main learning and explanation tool used by humans. AI systems should possess causal reasoning capabilities to be deployed in the real world with trust and reliability. Introducing the ideas of causality to machine…

Causal discovery aims to automatically uncover causal relationships from data, a capability with significant potential across many scientific disciplines. However, its real-world applications remain limited. Current methods often rely on…

Learning meaningful causal representations from observations has emerged as a crucial task for facilitating machine learning applications and driving scientific discoveries in fields such as climate science, biology, and physics. This…