Alex Bäuerle

Alex Bäuerle, Daniel Jönsson, Timo Ropinski

A key to deciphering the inner workings of neural networks is understanding what a model has learned. Promising methods for discovering learned features are based on analyzing activation values, whereby current techniques focus on analyzing high activation values to reveal interesting features on a neuron level. However, analyzing high activation values limits layer-level concept discovery. We present a method that instead takes into account the entire activation distribution. By extracting similar activation profiles within the high-dimensional activation space of a neural network layer, we find groups of inputs that are treated similarly. These input groups represent neural activation patterns (NAPs) and can be used to visualize and interpret learned layer concepts. We release a framework with which NAPs can be extracted from pre-trained models and provide a visual introspection tool that can be used to analyze NAPs. We tested our method with a variety of networks and show how it complements existing methods for analyzing neural network activation values.

Syeda Nahida Akter, Zichun Yu, Aashiq Muhamed et al. · cmu

The recently released Google Gemini class of models are the first to comprehensively report results that rival the OpenAI GPT series across a wide variety of tasks. In this paper, we do an in-depth exploration of Gemini's language abilities, making two contributions. First, we provide a third-party, objective comparison of the abilities of the OpenAI GPT and Google Gemini models with reproducible code and fully transparent results. Second, we take a closer look at the results, identifying areas where one of the two model classes excels. We perform this analysis over 10 datasets testing a variety of language abilities, including reasoning, answering knowledge-based questions, solving math problems, translating between languages, generating code, and acting as instruction-following agents. From this analysis, we find that Gemini Pro achieves accuracy that is close but slightly inferior to the corresponding GPT 3.5 Turbo on all tasks that we benchmarked. We further provide explanations for some of this under-performance, including failures in mathematical reasoning with many digits, sensitivity to multiple-choice answer ordering, aggressive content filtering, and others. We also identify areas where Gemini demonstrates comparably high performance, including generation into non-English languages, and handling longer and more complex reasoning chains. Code and data for reproduction can be found at https://github.com/neulab/gemini-benchmark

Alex Bäuerle, Adam Connors, Alexander Novikov et al.

Artificial intelligence offers powerful new tools for scientific discovery, but the interaction paradigms required to effectively harness these systems remain underexplored. In this paper, we present findings from a formative user study with 11 expert mathematicians who used AlphaEvolve, an evolutionary coding agent, to tackle advanced problems in their fields of expertise. We identify and characterize a distinct workflow we term intentmaking, the iterative process of discovering, defining, and refining one's experimental goals through active system interaction. We frame this as a natural extension to sensemaking, the cognitive process of building an understanding of complex or novel data. We suggest that users enter a cycle of intentmaking (defining and updating their experiment) and sensemaking (interpreting the results) which repeats many times during the course of an investigation. Our documentation of these themes suggests an approach to designing AI tools for scientific discovery that goes beyond the existing question/answer model of many current systems, treating them as collaborative instruments rather than opaque black-box assistants.

Alex Bäuerle, Aybuke Gul Turker, Ken Burke et al.

While the need for well-trained, fair ML systems is increasing ever more, measuring fairness for modern models and datasets is becoming increasingly difficult as they grow at an unprecedented pace. One key challenge in scaling common fairness metrics to such models and datasets is the requirement of exhaustive ground truth labeling, which cannot always be done. Indeed, this often rules out the application of traditional analysis metrics and systems. At the same time, ML-fairness assessments cannot be made algorithmically, as fairness is a highly subjective matter. Thus, domain experts need to be able to extract and reason about bias throughout models and datasets to make informed decisions. While visual analysis tools are of great help when investigating potential bias in DL models, none of the existing approaches have been designed for the specific tasks and challenges that arise in large label spaces. Addressing the lack of visualization work in this area, we propose guidelines for designing visualizations for such large label spaces, considering both technical and ethical issues. Our proposed visualization approach can be integrated into classical model and data pipelines, and we provide an implementation of our techniques open-sourced as a TensorBoard plug-in. With our approach, different models and datasets for large label spaces can be systematically and visually analyzed and compared to make informed fairness assessments tackling problematic bias.

Osman Aka, Ken Burke, Alex Bäuerle et al.

The measurement of bias in machine learning often focuses on model performance across identity subgroups (such as man and woman) with respect to groundtruth labels. However, these methods do not directly measure the associations that a model may have learned, for example between labels and identity subgroups. Further, measuring a model's bias requires a fully annotated evaluation dataset which may not be easily available in practice. We present an elegant mathematical solution that tackles both issues simultaneously, using image classification as a working example. By treating a classification model's predictions for a given image as a set of labels analogous to a bag of words, we rank the biases that a model has learned with respect to different identity labels. We use (man, woman) as a concrete example of an identity label set (although this set need not be binary), and present rankings for the labels that are most biased towards one identity or the other. We demonstrate how the statistical properties of different association metrics can lead to different rankings of the most "gender biased" labels, and conclude that normalized pointwise mutual information (nPMI) is most useful in practice. Finally, we announce an open-sourced nPMI visualization tool using TensorBoard.

Sebastian Hartwig, Dominik Engel, Leon Sick et al.

AI-based text-to-image models do not only excel at generating realistic images, they also give designers more and more fine-grained control over the image content. Consequently, these approaches have gathered increased attention within the computer graphics research community, which has been historically devoted towards traditional rendering techniques, that offer precise control over scene parameters (e.g., objects, materials, and lighting). While the quality of conventionally rendered images is assessed through well established image quality metrics, such as SSIM or PSNR, the unique challenges of text-to-image generation require other, dedicated quality metrics. These metrics must be able to not only measure overall image quality, but also how well images reflect given text prompts, whereby the control of scene and rendering parameters is interweaved. Within this survey, we provide a comprehensive overview of such text-to-image quality metrics, and propose a taxonomy to categorize these metrics. Our taxonomy is grounded in the assumption, that there are two main quality criteria, namely compositional quality and general quality, that contribute to the overall image quality. Besides the metrics, this survey covers dedicated text-to-image benchmark datasets, over which the metrics are frequently computed. Finally, we identify limitations and open challenges in the field of text-to-image generation, and derive guidelines for practitioners conducting text-to-image evaluation.

Daniel Wolf, Heiko Hillenhagen, Billurvan Taskin et al.

Clinical decision-making relies heavily on understanding relative positions of anatomical structures and anomalies. Therefore, for Vision-Language Models (VLMs) to be applicable in clinical practice, the ability to accurately determine relative positions on medical images is a fundamental prerequisite. Despite its importance, this capability remains highly underexplored. To address this gap, we evaluate the ability of state-of-the-art VLMs, GPT-4o, Llama3.2, Pixtral, and JanusPro, and find that all models fail at this fundamental task. Inspired by successful approaches in computer vision, we investigate whether visual prompts, such as alphanumeric or colored markers placed on anatomical structures, can enhance performance. While these markers provide moderate improvements, results remain significantly lower on medical images compared to observations made on natural images. Our evaluations suggest that, in medical imaging, VLMs rely more on prior anatomical knowledge than on actual image content for answering relative position questions, often leading to incorrect conclusions. To facilitate further research in this area, we introduce the MIRP , Medical Imaging Relative Positioning, benchmark dataset, designed to systematically evaluate the capability to identify relative positions in medical images.

Alex Bäuerle, Ángel Alexander Cabrera, Fred Hohman et al.

Interfaces for machine learning (ML), information and visualizations about models or data, can help practitioners build robust and responsible ML systems. Despite their benefits, recent studies of ML teams and our interviews with practitioners (n=9) showed that ML interfaces have limited adoption in practice. While existing ML interfaces are effective for specific tasks, they are not designed to be reused, explored, and shared by multiple stakeholders in cross-functional teams. To enable analysis and communication between different ML practitioners, we designed and implemented Symphony, a framework for composing interactive ML interfaces with task-specific, data-driven components that can be used across platforms such as computational notebooks and web dashboards. We developed Symphony through participatory design sessions with 10 teams (n=31), and discuss our findings from deploying Symphony to 3 production ML projects at Apple. Symphony helped ML practitioners discover previously unknown issues like data duplicates and blind spots in models while enabling them to share insights with other stakeholders.

Alex Bäuerle, Patrick Albus, Raphael Störk et al.

Due to the success of deep learning (DL) and its growing job market, students and researchers from many areas are interested in learning about DL technologies. Visualization has proven to be of great help during this learning process. While most current educational visualizations are targeted towards one specific architecture or use case, recurrent neural networks (RNNs), which are capable of processing sequential data, are not covered yet. This is despite the fact that tasks on sequential data, such as text and function analysis, are at the forefront of DL research. Therefore, we propose exploRNN, the first interactively explorable educational visualization for RNNs. On the basis of making learning easier and more fun, we define educational objectives targeted towards understanding RNNs. We use these objectives to form guidelines for the visual design process. By means of exploRNN, which is accessible online, we provide an overview of the training process of RNNs at a coarse level, while also allowing a detailed inspection of the data flow within LSTM cells. In an empirical study, we assessed 37 subjects in a between-subjects design to investigate the learning outcomes and cognitive load of exploRNN compared to a classic text-based learning environment. While learners in the text group are ahead in superficial knowledge acquisition, exploRNN is particularly helpful for deeper understanding of the learning content. In addition, the complex content in exploRNN is perceived as significantly easier and causes less extraneous load than in the text group. The study shows that for difficult learning material such as recurrent networks, where deep understanding is important, interactive visualizations such as exploRNN can be helpful.

Alex Bäuerle, Christian van Onzenoodt, Timo Ropinski

To convey neural network architectures in publications, appropriate visualizations are of great importance. While most current deep learning papers contain such visualizations, these are usually handcrafted just before publication, which results in a lack of a common visual grammar, significant time investment, errors, and ambiguities. Current automatic network visualization tools focus on debugging the network itself and are not ideal for generating publication visualizations. Therefore, we present an approach to automate this process by translating network architectures specified in Keras into visualizations that can directly be embedded into any publication. To do so, we propose a visual grammar for convolutional neural networks (CNNs), which has been derived from an analysis of such figures extracted from all ICCV and CVPR papers published between 2013 and 2019. The proposed grammar incorporates visual encoding, network layout, layer aggregation, and legend generation. We have further realized our approach in an online system available to the community, which we have evaluated through expert feedback, and a quantitative study. It not only reduces the time needed to generate network visualizations for publications, but also enables a unified and unambiguous visualization design.

Alex Bäuerle, Heiko Neumann, Timo Ropinski

Training data plays an essential role in modern applications of machine learning. However, gathering labeled training data is time-consuming. Therefore, labeling is often outsourced to less experienced users, or completely automated. This can introduce errors, which compromise valuable training data, and lead to suboptimal training results. We thus propose a novel approach that uses the power of pretrained classifiers to visually guide users to noisy labels, and let them interactively check error candidates, to iteratively improve the training data set. To systematically investigate training data, we propose a categorization of labeling errors into three different types, based on an analysis of potential pitfalls in label acquisition processes. For each of these types, we present approaches to detect, reason about, and resolve error candidates, as we propose measures and visual guidance techniques to support machine learning users. Our approach has been used to spot errors in well-known machine learning benchmark data sets, and we tested its usability during a user evaluation. While initially developed for images, the techniques presented in this paper are independent of the classification algorithm, and can also be extended to many other types of training data.