Rose Yu
YOU?
Author Swipe
View article: CaTS-Bench: Can Language Models Describe Numeric Time Series?
CaTS-Bench: Can Language Models Describe Numeric Time Series? Open
Time series captioning, the task of describing numeric time series in natural language, requires numerical reasoning, trend interpretation, and contextual understanding. Existing benchmarks, however, often rely on synthetic data or overly …
View article: Physics-Guided Deep Learning for Dynamical Systems: A Survey
Physics-Guided Deep Learning for Dynamical Systems: A Survey Open
Modeling complex physical dynamics is a fundamental task in science and engineering. Traditional physics-based models are sample efficient, and interpretable but often rely on rigid assumptions. Furthermore, direct numerical approximation …
View article: TGLF-SINN: Deep Learning Surrogate Model for Accelerating Turbulent Transport Modeling in Fusion
TGLF-SINN: Deep Learning Surrogate Model for Accelerating Turbulent Transport Modeling in Fusion Open
The Trapped Gyro-Landau Fluid (TGLF) model provides fast, accurate predictions of turbulent transport in tokamaks, but whole device simulations requiring thousands of evaluations remain computationally expensive. Neural network (NN) surrog…
View article: Conformal Prediction for Time-series Forecasting with Change Points
Conformal Prediction for Time-series Forecasting with Change Points Open
Conformal prediction has been explored as a general and efficient way to provide uncertainty quantification for time series. However, current methods struggle to handle time series data with change points - sudden shifts in the underlying …
View article: Emergence of Hierarchical Emotion Organization in Large Language Models
Emergence of Hierarchical Emotion Organization in Large Language Models Open
As large language models (LLMs) increasingly power conversational agents, understanding how they model users' emotional states is critical for ethical deployment. Inspired by emotion wheels -- a psychological framework that argues emotions…
View article: Singularity image for ClimSim-Online
Singularity image for ClimSim-Online Open
This is a singularity image for climsim-online: https://github.com/leap-stc/climsim-online It can be used to launch E3SM-MMF climate simulations or the hybrid physics-machine-learning variants (by replacing the MMF cloud-resolving calculat…
View article: Elucidated Rolling Diffusion Models for Probabilistic Forecasting of Complex Dynamics
Elucidated Rolling Diffusion Models for Probabilistic Forecasting of Complex Dynamics Open
Diffusion models are a powerful tool for probabilistic forecasting, yet most applications in high-dimensional complex systems predict future states individually. This approach struggles to model complex temporal dependencies and fails to e…
View article: Symmetry in Neural Network Parameter Spaces
Symmetry in Neural Network Parameter Spaces Open
Modern deep learning models are highly overparameterized, resulting in large sets of parameter configurations that yield the same outputs. A significant portion of this redundancy is explained by symmetries in the parameter space--transfor…
View article: Understanding Mode Connectivity via Parameter Space Symmetry
Understanding Mode Connectivity via Parameter Space Symmetry Open
Neural network minima are often connected by curves along which train and test loss remain nearly constant, a phenomenon known as mode connectivity. While this property has enabled applications such as model merging and fine-tuning, its th…
View article: Discovering Symbolic Differential Equations with Symmetry Invariants
Discovering Symbolic Differential Equations with Symmetry Invariants Open
Discovering symbolic differential equations from data uncovers fundamental dynamical laws underlying complex systems. However, existing methods often struggle with the vast search space of equations and may produce equations that violate k…
View article: Improving Learning to Optimize Using Parameter Symmetries
Improving Learning to Optimize Using Parameter Symmetries Open
We analyze a learning-to-optimize (L2O) algorithm that exploits parameter space symmetry to enhance optimization efficiency. Prior work has shown that jointly learning symmetry transformations and local updates improves meta-optimizer perf…
View article: AtlasD: Automatic Local Symmetry Discovery
AtlasD: Automatic Local Symmetry Discovery Open
Existing symmetry discovery methods predominantly focus on global transformations across the entire system or space, but they fail to consider the symmetries in local neighborhoods. This may result in the reported symmetry group being a mi…
View article: Intelligent in-cell electrophysiology: Reconstructing intracellular action potentials using a physics-informed deep learning model trained on nanoelectrode array recordings
Intelligent in-cell electrophysiology: Reconstructing intracellular action potentials using a physics-informed deep learning model trained on nanoelectrode array recordings Open
View article: Multi-Modal Forecaster: Jointly Predicting Time Series and Textual Data
Multi-Modal Forecaster: Jointly Predicting Time Series and Textual Data Open
Current forecasting approaches are largely unimodal and ignore the rich textual data that often accompany the time series due to lack of well-curated multimodal benchmark dataset. In this work, we develop TimeText Corpus (TTC), a carefully…
View article: Back to Bayesics: Uncovering Human Mobility Distributions and Anomalies with an Integrated Statistical and Neural Framework
Back to Bayesics: Uncovering Human Mobility Distributions and Anomalies with an Integrated Statistical and Neural Framework Open
View article: ClimaQA: An Automated Evaluation Framework for Climate Question Answering Models
ClimaQA: An Automated Evaluation Framework for Climate Question Answering Models Open
The use of Large Language Models (LLMs) in climate science has recently gained significant attention. However, a critical issue remains: the lack of a comprehensive evaluation framework capable of assessing the quality and scientific valid…
View article: MF-LAL: Drug Compound Generation Using Multi-Fidelity Latent Space Active Learning
MF-LAL: Drug Compound Generation Using Multi-Fidelity Latent Space Active Learning Open
Current generative models for drug discovery primarily use molecular docking as an oracle to guide the generation of active compounds. However, such models are often not useful in practice because even compounds with high docking scores do…
View article: Can LLMs Understand Time Series Anomalies?
Can LLMs Understand Time Series Anomalies? Open
Large Language Models (LLMs) have gained popularity in time series forecasting, but their potential for anomaly detection remains largely unexplored. Our study investigates whether LLMs can understand and detect anomalies in time series da…
View article: Back to Bayesics: Uncovering Human Mobility Distributions and Anomalies with an Integrated Statistical and Neural Framework
Back to Bayesics: Uncovering Human Mobility Distributions and Anomalies with an Integrated Statistical and Neural Framework Open
Existing methods for anomaly detection often fall short due to their inability to handle the complexity, heterogeneity, and high dimensionality inherent in real-world mobility data. In this paper, we propose DeepBayesic, a novel framework …
View article: Pushing the frontiers in climate modelling and analysis with machine learning
Pushing the frontiers in climate modelling and analysis with machine learning Open
View article: Ligand-Based Compound Activity Prediction via Few-Shot Learning
Ligand-Based Compound Activity Prediction via Few-Shot Learning Open
Predicting the activities of new compounds against biophysical or phenotypic assays based on the known activities of one or a few existing compounds is a common goal in early stage drug discovery. This problem can be cast as a "few-shot le…
View article: Diffusion-BBO: Diffusion-Based Inverse Modeling for Online Black-Box Optimization
Diffusion-BBO: Diffusion-Based Inverse Modeling for Online Black-Box Optimization Open
Online black-box optimization (BBO) aims to optimize an objective function by iteratively querying a black-box oracle in a sample-efficient way. While prior studies focus on forward approaches such as Gaussian Processes (GPs) to learn a su…
View article: Learning dynamical systems from data: An introduction to physics-guided deep learning
Learning dynamical systems from data: An introduction to physics-guided deep learning Open
Modeling complex physical dynamics is a fundamental task in science and engineering. Traditional physics-based models are first-principled, explainable, and sample-efficient. However, they often rely on strong modeling assumptions and expe…
View article: Probabilistic Emulation of a Global Climate Model with Spherical DYffusion
Probabilistic Emulation of a Global Climate Model with Spherical DYffusion Open
Data-driven deep learning models are transforming global weather forecasting. It is an open question if this success can extend to climate modeling, where the complexity of the data and long inference rollouts pose significant challenges. …
View article: Data-Driven Simulator for Mechanical Circulatory Support with Domain Adversarial Neural Process
Data-Driven Simulator for Mechanical Circulatory Support with Domain Adversarial Neural Process Open
Mechanical Circulatory Support (MCS) devices, implemented as a probabilistic deep sequence model. Existing mechanical simulators for MCS rely on oversimplifying assumptions and are insensitive to patient-specific behavior, limiting their a…
View article: Symmetry-Informed Governing Equation Discovery
Symmetry-Informed Governing Equation Discovery Open
Despite the advancements in learning governing differential equations from observations of dynamical systems, data-driven methods are often unaware of fundamental physical laws, such as frame invariance. As a result, these algorithms may s…
View article: Preliminary Validity and Acceptability of Motion Tape for Measuring Low Back Movement: Mixed Methods Study
Preliminary Validity and Acceptability of Motion Tape for Measuring Low Back Movement: Mixed Methods Study Open
Background Low back pain (LBP) is a significant public health problem that can result in physical disability and financial burden for the individual and society. Physical therapy is effective for managing LBP and includes evaluation of pos…
View article: Understanding the Difficulty of Solving Cauchy Problems with PINNs
Understanding the Difficulty of Solving Cauchy Problems with PINNs Open
Physics-Informed Neural Networks (PINNs) have gained popularity in scientific computing in recent years. However, they often fail to achieve the same level of accuracy as classical methods in solving differential equations. In this paper, …
View article: Intelligent In-Cell Electrophysiology: Reconstructing Action Potentials from Nanoelectrode Data Using Physics-Informed Deep Learning.
Intelligent In-Cell Electrophysiology: Reconstructing Action Potentials from Nanoelectrode Data Using Physics-Informed Deep Learning. Open
Intracellular electrophysiology is utilized across different scientific and medical disciplines, including neuroscience, cardiology, and pharmacology, due to its pivotal role in exploring and comprehending the electrical properties of cell…
View article: On the Theoretical Expressive Power and the Design Space of Higher-Order Graph Transformers
On the Theoretical Expressive Power and the Design Space of Higher-Order Graph Transformers Open
Graph transformers have recently received significant attention in graph learning, partly due to their ability to capture more global interaction via self-attention. Nevertheless, while higher-order graph neural networks have been reasonab…