Explaining deep learning models is essential for clinical integration of medical image analysis systems. A good explanation highlights if a model depends on spurious features that undermines generalization and harms a subset of patients or, conversely, may present novel biological insights. Although techniques like GradCAM can identify influential features, they are measurement tools that do not themselves form an explanation. We propose a human-machine-VLM interaction system tailored to explaining classifiers in computational pathology, including multi-instance learning for whole-slide images. Our proof of concept comprises (1) an AI-integrated slide viewer to run sliding-window experiments to test claims of an explanation, and (2) quantification of an explanation's predictiveness using general-purpose vision-language models. The results demonstrate that this allows us to qualitatively test claims of explanations and can quantifiably distinguish competing explanations. This offers a practical path from explainable AI to explained AI in digital pathology and beyond. Code and prompts are available at https://github.com/nki-ai/x2x.

While eXplainable AI (XAI) has advanced significantly, few methods address interpretabil-ity in embedded vector spaces where dimensions represent complex abstractions. We introduce Distance Explainer, a novel method for generating local, post-hoc explanations of embedded spaces in machine learning models. Our approach adapts saliency-based techniques from RISE to explain the distance between two embedded data points by assigning attribution values through selective masking and distance-ranked mask filtering. We evaluate Distance Explainer on cross-modal embeddings (image-image and image-caption pairs) using established XAI metrics including Faithfulness, Sensitivity/Robustness, and Randomization. Experiments with ImageNet and CLIP models demonstrate that our method effectively identifies features contributing to similarity or dissimilarity between embedded data points while maintaining high robustness and consistency. We also explore how parameter tuning, particularly mask quantity and selection strategy, affects explanation quality. This work addresses a critical gap in XAI research and enhances transparency and trustworthiness in deep learning applications utilizing embedded spaces.

Infections in Diabetic Foot Ulcers (DFUs) can cause severe complications, including tissue death and limb amputation, highlighting the need for accurate, timely diagnosis. Previous machine learning methods have focused on identifying infections by analyzing wound images alone, without utilizing additional metadata such as medical notes. In this study, we aim to improve infection detection by introducing Synthetic Caption Augmented Retrieval for Wound Infection Detection (SCARWID), a novel deep learning framework that leverages synthetic textual descriptions to augment DFU images. SCARWID consists of two components: (1) Wound-BLIP, a Vision-Language Model (VLM) fine-tuned on GPT-4o-generated descriptions to synthesize consistent captions from images; and (2) an Image-Text Fusion module that uses cross-attention to extract cross-modal embeddings from an image and its corresponding Wound-BLIP caption. Infection status is determined by retrieving the top-k similar items from a labeled support set. To enhance the diversity of training data, we utilized a latent diffusion model to generate additional wound images. As a result, SCARWID outperformed state-of-the-art models, achieving average sensitivity, specificity, and accuracy of 0.85, 0.78, and 0.81, respectively, for wound infection classification. Displaying the generated captions alongside the wound images and infection detection results enhances interpretability and trust, enabling nurses to align SCARWID outputs with their medical knowledge. This is particularly valuable when wound notes are unavailable or when assisting novice nurses who may find it difficult to identify visual attributes of wound infection.

Summary and Contributions: Reconstruction of a low-rank matrix from its linear measurements is a canonical problem in machine learning and signal processing. There has been an intense effort to establish theoretical guarantees and design efficient algorithms for solving these problems. Of these, the most prominent two methods are: 1- Convex optimization approach - Nuclear-norm regularization. In particular, the non-convex factorization approach has received increasing attention due to the reduced arithmetic and storage costs. Recently, Gunasekar et al. (2017) reported a surprising observation, that the non-convex factorization approach (when solved with gradient descent) generalizes (i.e., recovers the low-rank matrix of interest) even when the factors U and V are full dimensional (i.e., not tall, hence UV' does not impose an explicit low-rank structure).

A strand of research that has emerged recently in theoretically understanding the success of deep learning suggests that implicit regularization due to the choice of optimization algorithms and other heuristics may play an important role. Authors also suggest that implicit regularization via minimization of rank may be more useful in terms of explaining generalization in deep learning. One of the concerns that reviewers expressed was that the theoretical results focused primarily on matrix factorization and learning linear networks. While the authors provide empirical evidence that their results may extend to nonlinear neural networks, the reviewers suggested that the paper's positioning (and the title) would be more accurate if it were to focus on matrix problems rather than deep learning. The paper reads very well, and the results and insights in the paper are very compelling.

Mathematically characterizing the implicit regularization induced by gradient-based optimization is a longstanding pursuit in the theory of deep learning. A widespread hope is that a characterization based on minimization of norms may apply, and a standard test-bed for studying this prospect is matrix factorization (matrix completion via linear neural networks). It is an open question whether norms can explain the implicit regularization in matrix factorization. The current paper resolves this open question in the negative, by proving that there exist natural matrix factorization problems on which the implicit regularization drives all norms (and quasi-norms) towards infinity. Our results suggest that, rather than perceiving the implicit regularization via norms, a potentially more useful interpretation is minimization of rank.

Dehumanization, characterized as a subtle yet harmful manifestation of hate speech, involves denying individuals of their human qualities and often results in violence against marginalized groups. Despite significant progress in Natural Language Processing across various domains, its application in detecting dehumanizing language is limited, largely due to the scarcity of publicly available annotated data for this domain. This paper evaluates the performance of cutting-edge NLP models, including GPT-4, GPT-3.5, and LLAMA-2, in identifying dehumanizing language. Our findings reveal that while these models demonstrate potential, achieving a 70\% accuracy rate in distinguishing dehumanizing language from broader hate speech, they also display biases. They are over-sensitive in classifying other forms of hate speech as dehumanization for a specific subset of target groups, while more frequently failing to identify clear cases of dehumanization for other target groups. Moreover, leveraging one of the best-performing models, we automatically annotated a larger dataset for training more accessible models. However, our findings indicate that these models currently do not meet the high-quality data generation threshold necessary for this task.

Earlier this week, Senate majority leader Chuck Schumer unveiled his SAFE Innovation Framework for artificial intelligence (AI), calling on Congress to take swift, decisive action. Leaders in the AI industry have been calling out for regulation. But Schumer's proposal reveals how difficult it could be in practice for policymakers to regulate a technology that even experts struggle to fully understand. The SAFE Innovation Framework has a number of policy goals: make sure AI systems are secure against cyber attacks, protect jobs, ensure accountability for those deploying AI systems, and defend U.S. democratic values, all without stifling innovation. The part of Schumer's framework which comes closest to making a concrete policy proposal, rather than setting a policy goal, is his call for explainability.

Machine learning (ML) and Artificial Intelligence (AI) are increasingly used in energy and engineering systems, but these models must be fair, unbiased, and explainable. It is critical to have confidence in AI's trustworthiness. ML techniques have been useful in predicting important parameters and improving model performance. However, for these AI techniques to be useful for making decisions, they need to be audited, accounted for, and easy to understand. Therefore, the use of Explainable AI (XAI) and interpretable machine learning (IML) is crucial for the accurate prediction of prognostics, such as remaining useful life (RUL) in a digital twin system to make it intelligent while ensuring that the AI model is transparent in its decision-making processes and that the predictions it generates can be understood and trusted by users. By using AI that is explainable, interpretable, and trustworthy, intelligent digital twin systems can make more accurate predictions of RUL, leading to better maintenance and repair planning and, ultimately, improved system performance. The objective of this paper is to understand the idea of XAI and IML and justify the important role of ML/AI in the Digital Twin framework and components, which requires XAI to understand the prediction better. This paper explains the importance of XAI and IML in both local and global aspects to ensure the use of trustworthy ML/AI applications for RUL prediction. This paper used the RUL prediction for the XAI and IML studies and leveraged the integrated python toolbox for interpretable machine learning (PiML).

Is Real AI Superintelligence the Fundamental Solution of Human Problems? RAIS is like a scientific modelling makes a particular part or feature of the world to automatically understand, define, quantify, visualize, or simulate by referencing to its encoded/programmed world's data/information/knowledge base. The RAIS is to run the Master Algorithm of Reality and Mentality as Descriptive, Deductive, Intuitive, Inductive, Exploratory, Explainable, Predictive and Prescriptive (DDIIEEPP) Platform. In all, the RAI program implies radically innovative approaches and paradigmatic shifts in fundamental knowledge fields and advanced technology domains, as reality and mentality, causality, science, technology and statistics, AI and ML, data and intelligence, information and knowledge, AI software and hardware, cyberspace and intelligent robotics. The RAIS Platform could compute the real world as a whole and in parts [e.g., the causal nexus of various human domains, such as fire technology and human civilizations; globalization and political power; climate change and consumption; economic growth and ecological destruction; future economy, unemployment and global pandemic; wealth and corruption, perspectives on the world's future, etc.].