We present VizGenie, a self-improving, agentic framework that advances scientific visualization through large language model (LLM) by orchestrating of a collection of domain-specific and dynamically generated modules. Users initially access core functionalities-such as threshold-based filtering, slice extraction, and statistical analysis-through pre-existing tools. For tasks beyond this baseline, VizGenie autonomously employs LLMs to generate new visualization scripts (e.g., VTK Python code), expanding its capabilities on-demand. Each generated script undergoes automated backend validation and is seamlessly integrated upon successful testing, continuously enhancing the system's adaptability and robustness. A distinctive feature of VizGenie is its intuitive natural language interface, allowing users to issue high-level feature-based queries (e.g., "visualize the skull" or "highlight tissue boundaries"). The system leverages image-based analysis and visual question answering (VQA) via fine-tuned vision models to interpret these queries precisely, bridging domain expertise and technical implementation. Additionally, users can interactively query generated visualizations through VQA, facilitating deeper exploration. Reliability and reproducibility are further strengthened by Retrieval-Augmented Generation (RAG), providing context-driven responses while maintaining comprehensive provenance records. Evaluations on complex volumetric datasets demonstrate significant reductions in cognitive overhead for iterative visualization tasks. By integrating curated domain-specific tools with LLM-driven flexibility, VizGenie not only accelerates insight generation but also establishes a sustainable, continuously evolving visualization practice. The resulting platform dynamically learns from user interactions, consistently enhancing support for feature-centric exploration and reproducible research in scientific visualization.

An evaluation criterion for safe and trustworthy deep learning is how well the invariances captured by representations of deep neural networks (DNNs) are shared with humans. We identify challenges in measuring these invariances. Prior works used gradient-based methods to generate identically represented inputs (IRIs), ie, inputs which have identical representations (on a given layer) of a neural network, and thus capture invariances of a given network. One necessary criterion for a network's invariances to align with human perception is for its IRIs look 'similar' to humans. Prior works, however, have mixed takeaways; some argue that later layers of DNNs do not learn human-like invariances yet others seem to indicate otherwise. We argue that the loss function used to generate IRIs can heavily affect takeaways about invariances of the network and is the primary reason for these conflicting findings. We propose an adversarial regularizer on the IRI generation loss that finds IRIs that make any model appear to have very little shared invariance with humans. Based on this evidence, we argue that there is scope for improving models to have human-like invariances, and further, to have meaningful comparisons between models one should use IRIs generated using the regularizer-free loss. We then conduct an in-depth investigation of how different components (eg architectures, training losses, data augmentations) of the deep learning pipeline contribute to learning models that have good alignment with humans. We find that architectures with residual connections trained using a (self-supervised) contrastive loss with l_p ball adversarial data augmentation tend to learn invariances that are most aligned with humans. Code: github.com/nvedant07/Human-NN-Alignment

Aligning model representations to humans has been found to improve robustness and generalization. However, such methods often focus on standard observational data. Synthetic data is proliferating and powering many advances in machine learning; yet, it is not always clear whether synthetic labels are perceptually aligned to humans – rendering it likely model representations are not human aligned. We focus on the synthetic data used in mixup: a powerful regularizer shown to improve model robustness, generalization, and calibration. We design a comprehensive series of elicitation interfaces, which we release as HILL MixE Suite, and recruit 159 participants to provide perceptual judgments along with their uncertainties, over mixup examples. We find that human perceptions do not consistently align with the labels traditionally used for synthetic points, and begin to demonstrate the applicability of these findings to potentially increase the reliability of downstream models, particularly when incorporating human uncertainty. We release all elicited judgments in a new data hub we call H-Mix.

Despite their impressive performance in object recognition and other tasks under standard testing conditions, deep networks often fail to generalize to out-of-distribution (o.o.d.) samples. One cause for this shortcoming is that modern architectures tend to rely on ǣshortcutsǥ superficial features that correlate with categories without capturing deeper invariants that hold across contexts. Real-world concepts often possess a complex structure that can vary superficially across contexts, which can make the most intuitive and promising solutions in one context not generalize to others. One potential way to improve o.o.d. generalization is to assume simple solutions are unlikely to be valid across contexts and avoid them, which we refer to as the too-good-to-be-true prior. A low-capacity network (LCN) with a shallow architecture should only be able to learn surface relationships, including shortcuts. We find that LCNs can serve as shortcut detectors. Furthermore, an LCN’s predictions can be used in a two-stage approach to encourage a high-capacity network (HCN) to rely on deeper invariant features that should generalize broadly. In particular, items that the LCN can master are downweighted when training the HCN. Using a modified version of the CIFAR-10 dataset in which we introduced shortcuts, we found that the two-stage LCN-HCN approach reduced reliance on shortcuts and facilitated o.o.d. generalization.

Advances in supervised learning approaches to object recognition flourished in part because of the availability of high-quality datasets and associated benchmarks. However, these benchmarks—such as ILSVRC—are relatively task-specific, focusing predominately on predicting class labels. We introduce a publicly-available dataset that embodies the task-general capabilities of human perception and reasoning. The Human Similarity Judgments extension to ImageNet (ImageNet-HSJ) is composed of a large set of human similarity judgments that supplements the existing ILSVRC validation set. The new dataset supports a range of task and performance metrics, including evaluation of unsupervised algorithms. We demonstrate two methods of assessment: using the similarity judgments directly and using a psychological embedding trained on the similarity judgments. This embedding space contains an order of magnitude more points (i.e., images) than previous efforts based on human judgments. We were able to scale to the full 50,000 image ILSVRC validation set through a selective sampling process that used variational Bayesian inference and model ensembles to sample aspects of the embedding space that were most uncertain. To demonstrate the utility of ImageNet-HSJ, we used the similarity ratings and the embedding space to evaluate how well several popular models conform to human similarity judgments. One finding is that the more complex models that perform better on task-specific benchmarks do not better conform to human semantic judgments. In addition to the human similarity judgments, pre-trained psychological embeddings and code for inferring variational embeddings are made publicly available. ImageNet-HSJ supports the appraisal of internal representations and the development of more humanlike models.

We discuss the problem of assessing and aiding user performance in dynamic tasks that require rapid selection among multiple information sources. Motivated by research in human sequential learning, we develop a system that learns by observation to predict the information a user desires in different contexts. The model decides when the display should be updated, which is akin to the problem of scene segmentation, and then selects the situationally relevant information display. The model reduces the cognitive burden of selecting situation-relevant displays. We evaluate the system in a tank video game environment and find that the system boosts user performance. The fit of the model to user data provides a quantitative assessment of user behavior, which is useful in assessing individual differences and the progression from novice- to expert-level proficiency. We discuss the relative benefits of adopting a learning approach to predicting information preferences and possible avenues to reduce the negative consequences of automation.

SUSTAIN (Supervised and Unsupervised STratified Adaptive Incremental Network) is a network model of human category learning. SUSTAIN initially assumes a simple category structure. If simple solutions prove inadequate and SUSTAIN is confronted with a surprising event (e.g. it is told that a bat is a mammal instead of a bird), SUSTAIN recruits an additional cluster to represent the surprising event. Newly recruited clusters are available to explain future events and can themselves evolve into prototypes/attractors/rules. SUSTAIN has expanded the scope of findings that models of human category learning can address. This paper extends SUSTAIN to account for both supervised and unsupervised learning data through a common mechanism. The modified model, uSUSTAIN (unified SUSTAIN), is successfully applied to human learning data that compares unsupervised and supervised learning performances.18

(Supervised and Unsupervised STratified Adaptive IncrementalNetwork) is a network model of human category learning. SUSTAIN initially assumes a simple category structure. If simple solutions prove inadequate and SUSTAIN is confronted with a surprising event (e.g. it is told that a bat is a mammal instead of a bird), SUSTAIN recruits an additional cluster to represent the surprising event. Newly recruited clusters are available to explain future events and can themselves evolve into prototypes/attractors/rules. SUSTAIN has expanded the scope of findings that models of human category learning can address. This paper extends SUSTAIN so that it can be used to account for both supervised and unsupervised learning data through a common mechanism. A modified recruitment rule is introduced that creates new conceptual clusters in response to surprising events during learning. The new formulation of the model is called uSUSTAIN for ‘unified SUSTAIN.’ The implications of using a unified recruitment method for both supervised and unsupervised learning are discussed.