Tuan Do

Tuan Do, Bernie Boscoe, Evan Jones et al.

We present a dataset built for machine learning applications consisting of galaxy photometry, images, spectroscopic redshifts, and structural properties. This dataset comprises 286,401 galaxy images and photometry from the Hyper-Suprime-Cam Survey PDR2 in five imaging filters ($g,r,i,z,y$) with spectroscopically confirmed redshifts as ground truth. Such a dataset is important for machine learning applications because it is uniform, consistent, and has minimal outliers but still contains a realistic range of signal-to-noise ratios. We make this dataset public to help spur development of machine learning methods for the next generation of surveys such as Euclid and LSST. The aim of GalaxiesML is to provide a robust dataset that can be used not only for astrophysics but also for machine learning, where image properties cannot be validated by the human eye and are instead governed by physical laws. We describe the challenges associated with putting together a dataset from publicly available archives, including outlier rejection, duplication, establishing ground truths, and sample selection. This is one of the largest public machine learning-ready training sets of its kind with redshifts ranging from 0.01 to 4. The redshift distribution of this sample peaks at redshift of 1.5 and falls off rapidly beyond redshift 2.5. We also include an example application of this dataset for redshift estimation, demonstrating that using images for redshift estimation produces more accurate results compared to using photometry alone. For example, the bias in redshift estimate is a factor of 10 lower when using images between redshift of 0.1 to 1.25 compared to photometry alone. Results from dataset such as this will help inform us on how to best make use of data from the next generation of galaxy surveys.

Bernie Boscoe, Tuan Do, Evan Jones et al.

In this work, we identify elements of effective machine learning datasets in astronomy and present suggestions for their design and creation. Machine learning has become an increasingly important tool for analyzing and understanding the large-scale flood of data in astronomy. To take advantage of these tools, datasets are required for training and testing. However, building machine learning datasets for astronomy can be challenging. Astronomical data is collected from instruments built to explore science questions in a traditional fashion rather than to conduct machine learning. Thus, it is often the case that raw data, or even downstream processed data is not in a form amenable to machine learning. We explore the construction of machine learning datasets and we ask: what elements define effective machine learning datasets? We define effective machine learning datasets in astronomy to be formed with well-defined data points, structure, and metadata. We discuss why these elements are important for astronomical applications and ways to put them in practice. We posit that these qualities not only make the data suitable for machine learning, they also help to foster usable, reusable, and replicable science practices.

Yun Qi Li, Tuan Do, Evan Jones et al.

Generative models producing images have enormous potential to advance discoveries across scientific fields and require metrics capable of quantifying the high dimensional output. We propose that astrophysics data, such as galaxy images, can test generative models with additional physics-motivated ground truths in addition to human judgment. For example, galaxies in the Universe form and change over billions of years, following physical laws and relationships that are both easy to characterize and difficult to encode in generative models. We build a conditional denoising diffusion probabilistic model (DDPM) and a conditional variational autoencoder (CVAE) and test their ability to generate realistic galaxies conditioned on their redshifts (galaxy ages). This is one of the first studies to probe these generative models using physically motivated metrics. We find that both models produce comparable realistic galaxies based on human evaluation, but our physics-based metrics are better able to discern the strengths and weaknesses of the generative models. Overall, the DDPM model performs better than the CVAE on the majority of the physics-based metrics. Ultimately, if we can show that generative models can learn the physics of galaxy evolution, they have the potential to unlock new astrophysical discoveries.

Rafael Cabral, Tuan Manh Do, Xuejun Yu et al.

Proof autoformalization, the task of translating natural language theorems and proofs into machine-verifiable code, is a critical step for integrating large language models into rigorous mathematical workflows. Current approaches focus on producing executable code, but they frequently fail to preserve the semantic meaning and logical structure of the original human-written argument. To address this, we introduce ProofFlow, a novel pipeline that treats structural fidelity as a primary objective. ProofFlow first constructs a directed acyclic graph (DAG) to map the logical dependencies between proof steps. Then, it employs a novel lemma-based approach to systematically formalize each step as an intermediate lemma, preserving the logical structure of the original argument. To facilitate evaluation, we present a new benchmark of 184 undergraduate-level problems, manually annotated with step-by-step solutions and logical dependency graphs, and introduce ProofScore, a new composite metric to evaluate syntactic correctness, semantic faithfulness, and structural fidelity. Experimental results show our pipeline sets a new state-of-the-art for autoformalization, achieving a ProofScore of 0.545, substantially exceeding baselines like full-proof formalization (0.123), which processes the entire proof at once, and step-proof formalization (0.072), which handles each step independently. Our pipeline, benchmark, and score metric are open-sourced to encourage further progress at https://github.com/Huawei-AI4Math/ProofFlow.

Tuan Do, Nikhil Krishnaswamy, James Pustejovsky

This paper introduces the Event Capture Annotation Tool (ECAT), a user-friendly, open-source interface tool for annotating events and their participants in video, capable of extracting the 3D positions and orientations of objects in video captured by Microsoft's Kinect(R) hardware. The modeling language VoxML (Pustejovsky and Krishnaswamy, 2016) underlies ECAT's object, program, and attribute representations, although ECAT uses its own spec for explicit labeling of motion instances. The demonstration will show the tool's workflow and the options available for capturing event-participant relations and browsing visual data. Mapping ECAT's output to VoxML will also be addressed.

Jonathan Soriano, Srinath Saikrishnan, Vikram Seenivasan et al.

In this work, we explore methods to improve galaxy redshift predictions by combining different ground truths. Traditional machine learning models rely on training sets with known spectroscopic redshifts, which are precise but only represent a limited sample of galaxies. To make redshift models more generalizable to the broader galaxy population, we investigate transfer learning and directly combining ground truth redshifts derived from photometry and spectroscopy. We use the COSMOS2020 survey to create a dataset, TransferZ, which includes photometric redshift estimates derived from up to 35 imaging filters using template fitting. This dataset spans a wider range of galaxy types and colors compared to spectroscopic samples, though its redshift estimates are less accurate. We first train a base neural network on TransferZ and then refine it using transfer learning on a dataset of galaxies with more precise spectroscopic redshifts (GalaxiesML). In addition, we train a neural network on a combined dataset of TransferZ and GalaxiesML. Both methods reduce bias by $\sim$ 5x, RMS error by $\sim$ 1.5x, and catastrophic outlier rates by 1.3x on GalaxiesML, compared to a baseline trained only on TransferZ. However, we also find a reduction in performance for RMS and bias when evaluated on TransferZ data. Overall, our results demonstrate these approaches can meet cosmological requirements.

Andrew Lizarraga, Eric Hanchen Jiang, Jacob Nowack et al.

Redshift measures the distance to galaxies and underlies our understanding of the origin of the Universe and galaxy evolution. Spectroscopic redshift is the gold-standard method for measuring redshift, but it requires about $1000$ times more telescope time than broad-band imaging. That extra cost limits sky coverage and sample size and puts large spectroscopic surveys out of reach. Photometric redshift methods rely on imaging in multiple color filters and template fitting, yet they ignore the wealth of information carried by galaxy shape and structure. We demonstrate that a diffusion model conditioned on continuous redshift learns this missing joint structure, reproduces known morphology-$z$ correlations. We verify on the HyperSuprime-Cam survey, that the model captures redshift-dependent trends in ellipticity, semi-major axis, Sérsic index, and isophotal area that these generated images correlate closely with true redshifts on test data. To our knowledge this is the first study to establish a direct link between galaxy morphology and redshift. Our approach offers a simple and effective path to redshift estimation from imaging data and will help unlock the full potential of upcoming wide-field surveys.

Chandler Campbell, Bernie Boscoe, Tuan Do

Research groups face persistent challenges in capturing, storing, and retrieving knowledge that is distributed across team members. Although structured data intended for analysis and publication is often well managed, much of a group's collective knowledge remains informal, fragmented, or undocumented--often passed down orally through meetings, mentoring, and day-to-day collaboration. This includes private resources such as emails, meeting notes, training materials, and ad hoc documentation. Together, these reflect the group's tacit knowledge--the informal, experience-based expertise that underlies much of their work. Accessing this knowledge can be difficult, requiring significant time and insider understanding. Retrieval-augmented generation (RAG) systems offer promising solutions by enabling users to query and generate responses grounded in relevant source material. However, most current RAG-LLM systems are oriented toward public documents and overlook the privacy concerns of internal research materials. We introduce AquiLLM (pronounced ah-quill-em), a lightweight, modular RAG system designed to meet the needs of research groups. AquiLLM supports varied document types and configurable privacy settings, enabling more effective access to both formal and informal knowledge within scholarly groups.

Tuan Do, Nikhil Krishnaswamy, Kyeongmin Rim et al.

We describe an ongoing project in learning to perform primitive actions from demonstrations using an interactive interface. In our previous work, we have used demonstrations captured from humans performing actions as training samples for a neural network-based trajectory model of actions to be performed by a computational agent in novel setups. We found that our original framework had some limitations that we hope to overcome by incorporating communication between the human and the computational agent, using the interaction between them to fine-tune the model learned by the machine. We propose a framework that uses multimodal human-computer interaction to teach action concepts to machines, making use of both live demonstration and communication through natural language, as two distinct teaching modalities, while requiring few training samples.

Tuan Do, James Pustejovsky

Selecting an optimal event representation is essential for event classification in real world contexts. In this paper, we investigate the application of qualitative spatial reasoning (QSR) frameworks for classification of human-object interaction in three dimensional space, in comparison with the use of quantitative feature extraction approaches for the same purpose. In particular, we modify QSRLib, a library that allows computation of Qualitative Spatial Relations and Calculi, and employ it for feature extraction, before inputting features into our neural network models. Using an experimental setup involving motion captures of human-object interaction as three dimensional inputs, we observe that the use of qualitative spatial features significantly improves the performance of our machine learning algorithm against our baseline, while quantitative features of similar kinds fail to deliver similar improvement. We also observe that sequential representations of QSR features yield the best classification performance. A result of our learning method is a simple approach to the qualitative representation of 3D activities as compositions of 2D actions that can be visualized and learned using 2-dimensional QSR.

Tuan Do, James Pustejovsky

Event learning is one of the most important problems in AI. However, notwithstanding significant research efforts, it is still a very complex task, especially when the events involve the interaction of humans or agents with other objects, as it requires modeling human kinematics and object movements. This study proposes a methodology for learning complex human-object interaction (HOI) events, involving the recording, annotation and classification of event interactions. For annotation, we allow multiple interpretations of a motion capture by slicing over its temporal span, for classification, we use Long-Short Term Memory (LSTM) sequential models with Conditional Randon Field (CRF) for constraints of outputs. Using a setup involving captures of human-object interaction as three dimensional inputs, we argue that this approach could be used for event types involving complex spatio-temporal dynamics.