Helen Qu
YOU?
Author Swipe
View article: T-FIX: Text-Based Explanations with Features Interpretable to eXperts
T-FIX: Text-Based Explanations with Features Interpretable to eXperts Open
As LLMs are deployed in knowledge-intensive settings (e.g., surgery, astronomy, therapy), users expect not just answers, but also meaningful explanations for those answers. In these settings, users are often domain experts (e.g., doctors, …
View article: Universal Spectral Tokenization via Self-Supervised Panchromatic Representation Learning
Universal Spectral Tokenization via Self-Supervised Panchromatic Representation Learning Open
Sequential scientific data span many resolutions and domains, and unifying them into a common representation is a key step toward developing foundation models for the sciences. Astronomical spectra exemplify this challenge: massive surveys…
View article: AION-1: Omnimodal Foundation Model for Astronomical Sciences
AION-1: Omnimodal Foundation Model for Astronomical Sciences Open
While foundation models have shown promise across a variety of fields, astronomy still lacks a unified framework for joint modeling across its highly diverse data modalities. In this paper, we present AION-1, a family of large-scale multim…
View article: The Hourglass Simulation: A Catalog for the Roman High-latitude Time-domain Core Community Survey
The Hourglass Simulation: A Catalog for the Roman High-latitude Time-domain Core Community Survey Open
We present a simulation of the time-domain catalog for the Nancy Grace Roman Space Telescope’s High-Latitude Time-Domain Core Community Survey. This simulation, called the Hourglass simulation, uses the most up-to-date spectral energy dist…
View article: Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models
Impact of Pretraining Word Co-occurrence on Compositional Generalization in Multimodal Models Open
CLIP and large multimodal models (LMMs) have better accuracy on examples involving concepts that are highly represented in the training data. However, the role of concept combinations in the training data on compositional generalization is…
View article: The Hourglass Simulation: A Catalog for the Roman High-Latitude Time-Domain Core Community Survey
The Hourglass Simulation: A Catalog for the Roman High-Latitude Time-Domain Core Community Survey Open
We present a simulation of the time-domain catalog for the Nancy Grace Roman Space Telescope's High-Latitude Time-Domain Core Community Survey. This simulation, called the Hourglass simulation, uses the most up-to-date spectral energy dist…
View article: Dark Energy Survey: implications for cosmological expansion models from the final DES Baryon Acoustic Oscillation and Supernova data
Dark Energy Survey: implications for cosmological expansion models from the final DES Baryon Acoustic Oscillation and Supernova data Open
The Dark Energy Survey (DES) recently released the final results of its two principal probes of the expansion history: Type Ia Supernovae (SNe) and Baryonic Acoustic Oscillations (BAO). In this paper, we explore the cosmological implicatio…
View article: The Multimodal Universe: 100 TB of Machine Learning Ready Astronomical Data
The Multimodal Universe: 100 TB of Machine Learning Ready Astronomical Data Open
We present the Multimodal Universe , a new framework collating over 100 TB of multimodal astronomical data for its first release, spanning images, spectra, time series, tabular and hyper-spectral data. This unified collection enables a wid…
View article: Evaluating cosmological biases using photometric redshifts for Type Ia Supernova cosmology with the Dark Energy Survey Supernova Program
Evaluating cosmological biases using photometric redshifts for Type Ia Supernova cosmology with the Dark Energy Survey Supernova Program Open
Cosmological analyses with Type Ia Supernovae (SNe Ia) have traditionally been reliant on spectroscopy for both classifying the type of supernova and obtaining reliable redshifts to measure the distance–redshift relation. While obtaining a…
View article: The Multimodal Universe: Enabling Large-Scale Machine Learning with 100TB of Astronomical Scientific Data
The Multimodal Universe: Enabling Large-Scale Machine Learning with 100TB of Astronomical Scientific Data Open
We present the MULTIMODAL UNIVERSE, a large-scale multimodal dataset of scientific astronomical data, compiled specifically to facilitate machine learning research. Overall, the MULTIMODAL UNIVERSE contains hundreds of millions of astronom…
View article: The Dark Energy Survey Supernova Program: Cosmological Analysis and Systematic Uncertainties
The Dark Energy Survey Supernova Program: Cosmological Analysis and Systematic Uncertainties Open
We present the full Hubble diagram of photometrically classified Type Ia supernovae (SNe Ia) from the Dark Energy Survey supernova program (DES-SN). DES-SN discovered more than 20,000 SN candidates and obtained spectroscopic redshifts of 7…
View article: The Dark Energy Survey Supernova Program: Light Curves and 5 Yr Data Release
The Dark Energy Survey Supernova Program: Light Curves and 5 Yr Data Release Open
We present griz photometric light curves for the full 5 yr of the Dark Energy Survey Supernova (DES-SN) program, obtained with both forced point-spread function photometry on difference images ( DiffImg ) performed during survey operations…
View article: The FIX Benchmark: Extracting Features Interpretable to eXperts
The FIX Benchmark: Extracting Features Interpretable to eXperts Open
Feature-based methods are commonly used to explain model predictions, but these methods often implicitly assume that interpretable features are readily available. However, this is often not the case for high-dimensional data, and it can be…
View article: The dark energy survey supernova program: investigating beyond-ΛCDM
The dark energy survey supernova program: investigating beyond-ΛCDM Open
We report constraints on a variety of non-standard cosmological models using the full 5-yr photometrically classified type Ia supernova sample from the Dark Energy Survey (DES-SN5YR). Both Akaike Information Criterion (AIC) and Suspiciousn…
View article: The Dark Energy Survey Supernova Program: Investigating\n Beyond-$\\Lambda$CDM
The Dark Energy Survey Supernova Program: Investigating\n Beyond-$\\Lambda$CDM Open
We report constraints on a variety of non-standard cosmological models using\nthe full 5-year photometrically-classified type Ia supernova sample from the\nDark Energy Survey (DES-SN5YR). Both Akaike Information Criterion (AIC) and\nSuspic…
View article: Towards Precision Photometric Type Ia Supernova Cosmology with Machine Learning
Towards Precision Photometric Type Ia Supernova Cosmology with Machine Learning Open
The revolutionary discovery of dark energy and accelerating cosmic expansion was made with just 42 type Ia supernovae (SNe Ia) in 1999. Since then, large synoptic surveys, e.g., Dark Energy Survey (DES), have observed thousands more SNe Ia…
View article: The Dark Energy Survey Supernova Program: Cosmological Biases from Host Galaxy Mismatch of Type Ia Supernovae
The Dark Energy Survey Supernova Program: Cosmological Biases from Host Galaxy Mismatch of Type Ia Supernovae Open
Redshift measurements, primarily obtained from host galaxies, are essential for inferring cosmological parameters from type Ia supernovae (SNe Ia). Matching SNe to host galaxies using images is nontrivial, resulting in a subset of SNe with…
View article: Connect Later: Improving Fine-tuning for Robustness with Targeted Augmentations
Connect Later: Improving Fine-tuning for Robustness with Targeted Augmentations Open
Models trained on a labeled source domain (e.g., labeled images from wildlife camera traps) often generalize poorly when deployed on an out-of-distribution (OOD) target domain (e.g., images from new camera trap locations). In the domain ad…
View article: The Dark Energy Survey Supernova Program: Cosmological Analysis and Systematic Uncertainties
The Dark Energy Survey Supernova Program: Cosmological Analysis and Systematic Uncertainties Open
We present the full Hubble diagram of photometrically-classified Type Ia supernovae (SNe Ia) from the Dark Energy Survey supernova program (DES-SN). DES-SN discovered more than 20,000 SN candidates and obtained spectroscopic redshifts of 7…
View article: Sum-of-Parts: Self-Attributing Neural Networks with End-to-End Learning of Feature Groups
Sum-of-Parts: Self-Attributing Neural Networks with End-to-End Learning of Feature Groups Open
Self-attributing neural networks (SANNs) present a potential path towards interpretable models for high-dimensional problems, but often face significant trade-offs in performance. In this work, we formally prove a lower bound on errors of …
View article: Transformers for scientific data: a pedagogical review for astronomers
Transformers for scientific data: a pedagogical review for astronomers Open
The deep learning architecture associated with ChatGPT and related generative AI products is known as transformers. Initially applied to Natural Language Processing, transformers and the self-attention mechanism they exploit have gained wi…
View article: Photo-zSNthesis: Converting Type Ia Supernova Lightcurves to Redshift Estimates via Deep Learning
Photo-zSNthesis: Converting Type Ia Supernova Lightcurves to Redshift Estimates via Deep Learning Open
Upcoming photometric surveys will discover tens of thousands of Type Ia supernovae (SNe Ia), vastly outpacing the capacity of our spectroscopic resources. In order to maximize the scientific return of these observations in the absence of s…
View article: What’s the Difference? The Potential for Convolutional Neural Networks for Transient Detection without Template Subtraction
What’s the Difference? The Potential for Convolutional Neural Networks for Transient Detection without Template Subtraction Open
We present a study of the potential for convolutional neural networks (CNNs) to enable separation of astrophysical transients from image artifacts, a task known as “real–bogus” classification, without requiring a template-subtracted (or di…
View article: Photo-zSNthesis: Converting Type Ia Supernova Lightcurves to Redshift Estimates via Deep Learning
Photo-zSNthesis: Converting Type Ia Supernova Lightcurves to Redshift Estimates via Deep Learning Open
Upcoming photometric surveys will discover tens of thousands of Type Ia supernovae (SNe Ia), vastly outpacing the capacity of our spectroscopic resources. In order to maximize the science return of these observations in the absence of spec…
View article: The Dark Energy Survey Supernova Program: Corrections on Photometry Due to Wavelength-dependent Atmospheric Effects
The Dark Energy Survey Supernova Program: Corrections on Photometry Due to Wavelength-dependent Atmospheric Effects Open
Wavelength-dependent atmospheric effects impact photometric supernova flux measurements for ground-based observations. We present corrections on supernova flux measurements from the Dark Energy Survey Supernova Program’s 5YR sample (DES-SN…
View article: Probing the consistency of cosmological contours for supernova cosmology
Probing the consistency of cosmological contours for supernova cosmology Open
As the scale of cosmological surveys increases, so does the complexity in the analyses. This complexity can often make it difficult to derive the underlying principles, necessitating statistically rigorous testing to ensure the results of …
View article: The Pantheon+ Analysis: SuperCal-fragilistic Cross Calibration, Retrained SALT2 Light-curve Model, and Calibration Systematic Uncertainty
The Pantheon+ Analysis: SuperCal-fragilistic Cross Calibration, Retrained SALT2 Light-curve Model, and Calibration Systematic Uncertainty Open
We present a recalibration of the photometric systems in the Pantheon+ sample of Type Ia supernovae (SNe Ia) including those in the SH0ES distance-ladder measurement of H 0 . We utilize the large and uniform sky coverage of the public Pan-…
View article: The Pantheon+ Analysis: Cosmological Constraints
The Pantheon+ Analysis: Cosmological Constraints Open
We present constraints on cosmological parameters from the Pantheon+ analysis of 1701 light curves of 1550 distinct Type Ia supernovae (SNe Ia) ranging in redshift from z = 0.001 to 2.26. This work features an increased sample size from th…
View article: A Convolutional Neural Network Approach to Supernova Time-Series Classification
A Convolutional Neural Network Approach to Supernova Time-Series Classification Open
One of the brightest objects in the universe, supernovae (SNe) are powerful explosions marking the end of a star's lifetime. Supernova (SN) type is defined by spectroscopic emission lines, but obtaining spectroscopy is often logistically u…
View article: What's the Difference? The potential for Convolutional Neural Networks for transient detection without template subtraction
What's the Difference? The potential for Convolutional Neural Networks for transient detection without template subtraction Open
We present a study of the potential for Convolutional Neural Networks (CNNs) to enable separation of astrophysical transients from image artifacts, a task known as "real-bogus" classification without requiring a template subtracted (or dif…