Related papers: GIFT: A Framework Towards Global Interpretable Fai…

Diffusion models have recently shown strong potential in language modeling, offering faster generation compared to traditional autoregressive approaches. However, applying supervised fine-tuning (SFT) to diffusion models remains…

Video Large Language Models (VLMs) have achieved remarkable success in video understanding, but the significant computational cost from processing dense frames severely limits their practical application. Existing methods alleviate this by…

The growing realism of AI-generated images produced by recent GAN and diffusion models has intensified concerns over the reliability of visual media. Yet, despite notable progress in deepfake detection, current forensic systems degrade…

Nowadays, deep vision models are being widely deployed in safety-critical applications, e.g., autonomous driving, and explainability of such models is becoming a pressing concern. Among explanation methods, counterfactual explanations aim…

Counterfactual reasoning -- the practice of asking ``what if'' by varying inputs and observing changes in model behavior -- has become central to interpretable and fair AI. This thesis develops frameworks that use counterfactuals to…

Graph Neural Networks (GNNs) achieve strong performance on node classification tasks but remain difficult to interpret, particularly with respect to which input features drive their predictions. Existing global GNN explainers operate at the…

This paper presents a novel concept learning framework for enhancing model interpretability and performance in visual classification tasks. Our approach appends an unsupervised explanation generator to the primary classifier network and…

Visual counterfactual explanations are ideal hypothetical images that change the decision-making of the classifier with high confidence toward the desired class while remaining visually plausible and close to the initial image. In this…

A promising paradigm for adapting instruction-tuned language models is to learn task-specific updates on a pretrained base model and subsequently merge them into the instruction-tuned model. However, existing approaches typically treat the…

Tool use requires reasoning about the fit between an object's affordances and the demands of a task. Visual affordance learning can benefit from goal-directed interaction experience, but current techniques rely on human labels or expert…

Deep learning models in computer vision have made remarkable progress, but their lack of transparency and interpretability remains a challenge. The development of explainable AI can enhance the understanding and performance of these models.…

Deep models that are both effective and explainable are desirable in many settings; prior explainable models have been unimodal, offering either image-based visualization of attention weights or text-based generation of post-hoc…

Concept-based interpretability methods are a popular form of explanation for deep learning models which provide explanations in the form of high-level human interpretable concepts. These methods typically find concept activation vectors…

Image classification is an essential part of computer vision which assigns a given input image to a specific category based on the similarity evaluation within given criteria. While promising classifiers can be obtained through deep…

Clearly explaining a rationale for a classification decision to an end-user can be as important as the decision itself. Existing approaches for deep visual recognition are generally opaque and do not output any justification text;…

Despite their high accuracies, modern complex image classifiers cannot be trusted for sensitive tasks due to their unknown decision-making process and potential biases. Counterfactual explanations are very effective in providing…

Counterfactual explanations (CFE) for deep image classifiers aim to reveal how minimal input changes lead to different model decisions, providing critical insights for model interpretation and improvement. However, existing CFE methods…

Originally inspired by game-theory, path attribution framework stands out among the post-hoc model interpretation tools due to its axiomatic nature. However, recent developments show that this framework can still suffer from…

Finding local correspondences between images with different viewpoints requires local descriptors that are robust against geometric transformations. An approach for transformation invariance is to integrate out the transformations by…

Classifiers are important components in many computer vision tasks, serving as the foundational backbone of a wide variety of models employed across diverse applications. However, understanding the decision-making process of classifiers…