Polo Chau

Georgia Institute of Technology | GT · School of Computational Science & Engineering

Differentiable rendering methods have emerged as a promising means for generating photo-realistic and physically plausible adversarial attacks by manipulating 3D objects and scenes that can deceive deep neural networks (DNNs). Recently, differentiable rendering capabilities have evolved significantly into a diverse landscape of libraries, such as M...

Text-to-image diffusion models have impactful applications in art, design, and entertainment, yet these technologies also pose significant risks by enabling the creation and dissemination of misinformation. Although recent advancements have produced AI-generated image detectors that claim robustness against various augmentations, their true effecti...

Dense Associative Memories are high storage capacity variants of the Hopfield networks that are capable of storing a large number of memory patterns in the weights of the network of a given size. Their common formulations typically require storing each pattern in a separate set of synaptic weights, which leads to the increase of the number of synap...

Modern deep learning models often make predictions by focusing on irrelevant areas, leading to biased performance and limited generalization. Existing methods aimed at rectifying model attention require explicit labels for irrelevant areas or complex pixel-wise ground truth attention maps. We present CRAYON (Correcting Reasoning with Annotations of...

The Mars Perseverance Rover represents a generational change in the scale of measurements that can be taken on Mars, however this increased resolution introduces new challenges for techniques in exploratory data analysis. The multiple different instruments on the rover each measures specific properties of interest to scientists, so analyzing how un...

Transformers have revolutionized machine learning, yet their inner workings remain opaque to many. We present Transformer Explainer, an interactive visualization tool designed for non-experts to learn about Transformers through the GPT-2 model. Our tool helps users understand complex Transformer concepts by integrating a model overview and enabling...

Collaborative planning for congenital heart diseases typically involves creating physical heart models through 3D printing, which are then examined by both surgeons and cardiologists. Recent developments in mobile augmented reality (AR) technologies have presented a viable alternative, known for their ease of use and portability. However, there is...

Diffusion-based generative models’ impressive ability to create convincing images has garnered global attention. However, their complex internal structures and operations often pose challenges for non-experts to grasp. We introduce Diffusion Explainer, the first interactive visualization tool designed to elucidate how Stable Diffusion transforms te...

Retrieval-augmented text generation (RAG) addresses the common limitations of large language models (LLMs), such as hallucination, by retrieving information from an updatable external knowledge base. However, existing approaches often require dedicated backend servers for data storage and retrieval, thereby limiting their applicability in use cases...

Safety alignment is the key to guiding the behaviors of large language models (LLMs) that are in line with human preferences and restrict harmful behaviors at inference time, but recent studies show that it can be easily compromised by finetuning with only a few adversarially designed training examples. We aim to measure the risks in finetuning LLM...

Human trafficking (HT) for forced sexual exploitation, often described as modern-day slavery, is a pervasive problem that affects millions of people worldwide. Perpetrators of this crime post advertisements (ads) on behalf of their victims on adult service websites (ASW). These websites typically contain hundreds of thousands of ads including those...

Manually grading D3 data visualizations is a challenging endeavor, and is especially difficult for large classes with hundreds of students. Grading an interactive visualization requires a combination of interactive, quantitative, and qualitative evaluation that are conventionally done manually and are difficult to scale up as the visualization comp...

Small-world networks are widely studied in many contexts due to their prevalence. For example, the collaboration network of movie actors is a small-world network, with short diameter and high clustering[8]. However, the availability of large-scale, crowd-sourced metrics of movie popularity and success allow us to gain deeper insight into how global...

Our research aims to unify existing works' diverging opinions on how architectural components affect the adversarial robustness of CNNs. To accomplish our goal, we synthesize a suite of three generalizable robust architectural design principles: (a) optimal range for depth and width configurations, (b) preferring convolutional over patchify stem st...

Large language models (LLMs) have skyrocketed in popularity in recent years due to their ability to generate high-quality text in response to human prompting. However, these models have been shown to have the potential to generate harmful content in response to user prompting (e.g., giving users instructions on how to commit crimes). There has been...

There has been an explosion in interest in machine learning (ML) in recent years due to its applications to science and engineering. However, as ML techniques have advanced, tools for explaining and visualizing novel ML algorithms have lagged behind. Animation has been shown to be a powerful tool for making engaging visualizations of systems that d...

Data in the real world is commonly imbalanced across classes. Training neural networks on imbalanced datasets often leads to poor performance on rare classes. Existing work in this area has primarily focused on Convolution Neural Networks (CNN), which are increasingly being replaced by Self-Attention-based Vision Transformers (ViT). Fundamentally,...

Given a million-scale dataset of who-calls-whom data containing imperfect labels, how can we detect existing and new fraud patterns? We propose TgrApp, which extracts carefully designed features and provides visualizations to assist analysts in spotting fraudsters and suspicious behavior. Our TgrApp method has the following properties: (a) Scalable...

Machine learning models often learn latent embedding representations that capture the domain semantics of their training data. These embedding representations are valuable for interpreting trained models, building new models, and analyzing new datasets. However, interpreting and using embeddings can be challenging due to their opaqueness, high dime...

Computational notebooks such as Jupyter Notebook have become data scientists' de facto programming environments. Many visualization researchers and practitioners have developed interactive visualization tools that support notebooks. However, little is known about the appropriate design of visual analytics (VA) tools in notebooks. To bridge this cri...

Diffusion-based generative models' impressive ability to create convincing images has captured global attention. However, their complex internal structures and operations often make them difficult for non-experts to understand. We present Diffusion Explainer, the first interactive visualization tool that explains how Stable Diffusion transforms tex...

As machine learning (ML) is increasingly integrated into our everyday Web experience, there is a call for transparent and explainable web-based ML. However, existing explainability techniques often require dedicated backend servers, which limit their usefulness as the Web community moves toward in-browser ML for lower latency and greater privacy. T...

Machine learning (ML) recourse techniques are increasingly used in high-stakes domains, providing end users with actions to alter ML predictions, but they assume ML developers understand what input variables can be changed. However, a recourse plan's actionability is subjective and unlikely to match developers' expectations completely. We present G...

Person tracking using computer vision techniques has wide ranging applications such as autonomous driving, home security and sports analytics. However, the growing threat of adversarial attacks raises serious concerns regarding the security and reliability of such techniques. In this work, we study the impact of multi-task learning (MTL) on the adv...

Transformers have become the de facto models of choice in machine learning, typically leading to impressive performance on many applications. At the same time, the architectural development in the transformer world is mostly driven by empirical findings, and the theoretical understanding of their architectural building blocks is rather limited. In...

While anomaly detection stands among the most important and valuable problems across many scientific domains, anomaly detection research often focuses on AI methods that can lack the nuance and interpretability so critical to conducting scientific inquiry. In this application paper we present the results of utilizing an alternative approach that si...

Adversarial Training is the most effective approach for improving the robustness of Deep Neural Networks (DNNs). However, compared to the large body of research in optimizing the adversarial training process, there are few investigations into how architecture components affect robustness, and they rarely constrain model capacity. Thus, it is unclea...

With recent advancements in diffusion models, users can generate high-quality images by writing text prompts in natural language. However, generating images with desired details requires proper prompts, and it is often unclear how a model reacts to different prompts and what the best prompts are. To help researchers tackle these critical challenges...

Discovering and making sense of relevant literature is fundamental in any scientific field. Node-link diagram-based visualization tools can aid this process; however, existing tools have been evaluated only on small scales. This paper evaluates Argo Scholar, an open-source visualization tool designed for interactive exploration of literature and ea...

We present our ongoing work NeuroMapper, an in-browser visualization tool that helps machine learning (ML) developers interpret the evolution of a model during training, providing a new way to monitor the training process and visually discover reasons for suboptimal training. While most existing deep neural networks (DNNs) interpretation tools are...

Law enforcement and domain experts can detect human trafficking (HT) in online escort websites by analyzing suspicious clusters of connected ads. How can we explain clustering results intuitively and interactively, visualizing potential evidence for experts to analyze? We present T raffic V is , the first interface for cluster-level HT detection...

Class imbalance is a ubiquitous phenomenon occurring in real world data distributions. To overcome its detrimental effect on training accurate classifiers, existing work follows three major directions: class re-balancing, information transfer, and representation learning. In this paper, we propose a new and complementary direction for improving per...

As the information on the Internet continues growing exponentially, understanding and assessing the reliability of a website is becoming increasingly important. Misinformation has far-ranging repercussions, from sowing mistrust in media to undermining democratic elections. While some research investigates how to alert people to misinformation on th...

Given thousands of equally accurate machine learning (ML) models, how can users choose among them? A recent ML technique enables domain experts and data scientists to generate a complete Rashomon set for sparse decision trees--a huge set of almost-optimal interpretable ML models. To help ML practitioners identify models with desirable properties fr...

Advanced surgical procedures for congenital heart diseases (CHDs) require precise planning before the surgeries. The conventional approach utilizes 3D-printing and cutting physical heart models, which is a time and resource intensive process. While rapid advances in augmented reality (AR) technologies have the potential to streamline surgical plann...

Machine learning (ML) interpretability techniques can reveal undesirable patterns in data that models exploit to make predictions--potentially causing harms once deployed. However, how to take action to address these patterns is not always clear. In a collaboration between ML and human-computer interaction researchers, physicians, and data scientis...

Keeping track of scientific challenges, advances and emerging directions is a fundamental part of research. However, researchers face a flood of papers that hinders discovery of important knowledge. In biomedicine, this directly impacts human lives. To address this problem, we present a novel task of extraction and search of scientific challenges a...

As machine learning (ML) systems become increasingly widespread, it is necessary to audit these systems for biases prior to their deployment. Recent research has developed algorithms for effectively identifying intersectional bias in the form of interpretable, underperforming subsets (or slices) of the data. However, these solutions and their insig...

How can we develop visual analytics (VA) tools that can be easily adopted? Visualization researchers have developed a large number of web-based VA tools to help data scientists in a wide range of tasks. However, adopting these standalone systems can be challenging, as they require data scientists to create new workflows to streamline the VA process...

CNN image classifiers are widely used, thanks to their efficiency and accuracy. However, they can suffer from biases that impede their practical applications. Most existing bias investigation techniques are either inapplicable to general image classification tasks or require significant user efforts in perusing all data subgroups to manually specif...

As automatic speech recognition (ASR) systems are now being widely deployed in the wild, the increasing threat of adversarial attacks raises serious questions about the security and reliability of using such systems. On the other hand, multi-task learning (MTL) has shown success in training models that can resist adversarial attacks in the computer...

Deep neural networks (DNNs) have been widely used for decision making, prompting a surge of interest in interpreting how these complex models work. Recent literature on DNN interpretation has revolved around already-trained models; however, much less research focuses on interpreting how the models evolve as they are trained. Interpreting model evol...

Few-shot learning (FSL) aims at learning to generalize from only a small number of labeled examples for a given target task. Most current state-of-the-art FSL methods typically have two limitations. First, they usually require access to a source dataset (in a similar domain) with abundant labeled examples, which may not always be possible due to pr...

The study of network robustness is a critical tool in the characterization and sense making of complex interconnected systems such as infrastructure, communication and social networks. While significant research has been conducted in these areas, gaps in the surveying literature still exist. Answers to key questions are currently scattered across m...

Recent strides in interpretable machine learning (ML) research reveal that models exploit undesirable patterns in the data to make predictions, which potentially causes harms in deployment. However, it is unclear how we can fix these models. We present our ongoing work, GAM Changer, an open-source interactive system to help data scientists and doma...

Discovering and making sense of relevant research literature is fundamental to becoming knowledgeable in any scientific discipline. Visualization can aid this process; however, existing tools' adoption and impact have often been constrained, such as by their reliance on small curated paper datasets that quickly become outdated or a lack of support...

Manually grading D3 data visualizations is a challenging endeavor, and is especially difficult for large classes with hundreds of students. Grading an interactive visualization requires a combination of interactive, quantitative, and qualitative evaluation that are conventionally done manually and are difficult to scale up as the visualization comp...

The ability to keep track of scientific challenges, advances and emerging directions is a fundamental part of research. However, researchers face a flood of papers that hinders discovery of important knowledge. In biomedicine, this directly impacts human lives. To address this problem, we present a novel task of extraction and search of scientific...

Existing research on making sense of deep neural networks often focuses on neuron-level interpretation, which may not adequately capture the bigger picture of how concepts are collectively encoded by multiple neurons. We present NeuroCartography, an interactive system that scalably summarizes and visualizes concepts learned by neural networks. It a...

Visual analytics systems integrate interactive visualizations and machine learning to enable expert users to solve complex analysis tasks. Applications combine techniques from various fields of research and are consequently not trivial to evaluate. The result is a lack of structure and comparability between evaluations. In this survey, we provide a...

As job markets worldwide have become more competitive and applicant selection criteria have become more opaque, and different (and sometimes contradictory) information and advice is available for job seekers wishing to progress in their careers, it has never been more difficult to determine which factors in a r\'esum\'e most effectively help career...

Skeleton-based human action recognition technologies are increasingly used in video-based applications, such as home robotics, healthcare on the aging population, and surveillance. However, such models are vulnerable to adversarial attacks, raising serious concerns for their use in safety-critical applications. To develop an effective defense again...

The study of network robustness is a critical tool in the characterization and sense making of complex interconnected systems such as infrastructure, communication and social networks. While significant research has been conducted in all of these areas, gaps in the surveying literature still exist. Answers to key questions are currently scattered a...

Substances involved in overdose deaths have shifted over time and continue to undergo transition. Early detection of emerging drugs involved in overdose is a major challenge for traditional public health data systems. While novel social media data have shown promise, there is a continued need for robust natural language processing approaches that c...

The advent of larger machine learning (ML) models have improved state-of-the-art (SOTA) performance in various modeling tasks, ranging from computer vision to natural language. As ML models continue increasing in size, so does their respective energy consumption and computational requirements. However, the methods for tracking, reporting, and compa...

Why do large pre-trained transformer-based models perform so well across a wide variety of NLP tasks? Recent research suggests the key may lie in multi-headed attention mechanism's ability to learn and represent linguistic information. Understanding how these models represent both syntactic and semantic knowledge is vital to investigate why they su...

Training deep neural networks for automatic speech recognition (ASR) requires large amounts of transcribed speech. This becomes a bottleneck for training robust models for accented speech which typically contains high variability in pronunciation and other semantics, since obtaining large amounts of annotated accented data is both tedious and costl...

With the widespread use of toxic language online, platforms are increasingly using automated systems that leverage advances in natural language processing to automatically flag and remove toxic comments. However, most automated systems---when detecting and moderating toxic language---do not provide feedback to their users, let alone provide an aven...

Computer vision is playing an increasingly important role in automated malware detection with to the rise of the image-based binary representation. These binary images are fast to generate, require no feature engineering, and are resilient to popular obfuscation methods. Significant research has been conducted in this area, however, it has been res...

Skeleton-based human action recognition technologies are increasingly used in video based applications, such as home robotics, healthcare on aging population, and surveillance. However, such models are vulnerable to adversarial attacks, raising serious concerns for their use in safety-critical applications. To develop an effective defense against a...

Mixed-initiative visual analytics systems incorporate well-established design principles that improve users' abilities to solve problems. As these systems consider whether to take initiative towards achieving user goals, many current systems address the potential for cognitive bias in human initiatives statically, relying on fixed initiatives they...

With the rapid emergence of graph representation learning, the construction of new large-scale datasets are necessary to distinguish model capabilities and accurately assess the strengths and weaknesses of each technique. By carefully analyzing existing graph databases, we identify 3 critical components important for advancing the field of graph re...

With the recent release of AI interaction guidelines from Apple, Google, and Microsoft, there is clearly interest in understanding the best practices in human-AI interaction. However, industry standards are not determined by a single company, but rather by the synthesis of knowledge from the whole community. We have surveyed all of the design guide...