Publications (69)
Beyond the Class Subspace: Teacher-Guided Training for Reliable Out-of-Distribution Detection in Single-Domain Models
Hong Yang, Devroop Kar, Qi Yu +2
Out-of-distribution (OOD) detection methods perform well on multi-domain benchmarks, yet many practical systems are trained on single-domain data. We show that this regime induces…
A Dynamic Meta-Learning Model for Time-Sensitive Cold-Start Recommendations
Krishna Prasad Neupane, Ervine Zheng, Yu Kong +1
We present a novel dynamic recommendation model that focuses on users who have interactions in the past but turn relatively inactive recently. Making effective recommendations to t…
A -Machine Learning Approach for Force Fields, Illustrated by a CCSD(T) 4-body Correction to the MB-pol Water Potential
Chen Qu, Qi Yu, Riccardo Conte +3
-Machine Learning (-ML) has been shown to effectively and efficiently bring a low-level ML potential energy surface to CCSD(T) quality. Here we propose extending this appro…
Learn to Accumulate Evidence from All Training Samples: Theory and Practice
Deep Pandey, Qi Yu
Evidential deep learning, built upon belief theory and subjective logic, offers a principled and computationally efficient way to turn a deterministic neural network uncertainty-aw…
PLANETALIGN: A Comprehensive Python Library for Benchmarking Network Alignment
Qi Yu, Zhichen Zeng, Yuchen Yan +5
Network alignment (NA) aims to identify node correspondence across different networks and serves as a critical cornerstone behind various downstream multi-network learning tasks. D…
Evidential Conditional Neural Processes
Deep Shankar Pandey, Qi Yu
The Conditional Neural Process (CNP) family of models offer a promising direction to tackle few-shot problems by achieving better scalability and competitive predictive performance…
Uncertainty-Aware Multiple Instance Learning from Large-Scale Long Time Series Data
Yuansheng Zhu, Weishi Shi, Deep Shankar Pandey +4
We propose a novel framework to classify large-scale time series data with long duration. Long time seriesclassification (L-TSC) is a challenging problem because the dataoften cont…
Entitymetrics: Measuring the Impact of Entities
Ying Ding, Min Song, Jia Han +4
This paper proposes entitymetrics to measure the impact of knowledge units. Entitymetrics highlight the importance of entities embedded in scientific literature for further knowled…
MapSR: Prompt-Driven Land Cover Map Super-Resolution via Vision Foundation Models
Ruiqi Wang, Qi Yu, Jie Ma +1
High-resolution (HR) land-cover mapping is often constrained by the high cost of dense HR annotations. We revisit this problem from the perspective of map super-resolution, which e…
Model-free Quantum Gate Design and Calibration using Deep Reinforcement Learning
Omar Shindi, Qi Yu, Parth Girdhar +1
High-fidelity quantum gate design is important for various quantum technologies, such as quantum computation and quantum communication. Numerous control policies for quantum gate d…
MADAR: Efficient Continual Learning for Malware Analysis with Distribution-Aware Replay
Mohammad Saidur Rahman, Scott Coull, Qi Yu +1
Millions of new pieces of malicious software (i.e., malware) are introduced each year. This poses significant challenges for antivirus vendors, who use machine learning to detect a…
Scalable Optimal Transport Algorithm for Network Alignment
Elaheh Hassani, Durga Mandarapu, Qi Yu +2
Network alignment identifies node correspondences across different networks and is a fundamental primitive in many data science applications, including social network analysis, fra…
Harnessing Consistency for Robust Test-Time LLM Ensemble
Zhichen Zeng, Qi Yu, Xiao Lin +6
Different large language models (LLMs) exhibit diverse strengths and weaknesses, and LLM ensemble serves as a promising approach to integrate their complementary capabilities. Desp…
Dictionary Learning with BLOTLESS Update
Qi Yu, Wei Dai, Zoran Cvetkovic +1
Algorithms for learning a dictionary to sparsely represent a given dataset typically alternate between sparse coding and dictionary update stages. Methods for dictionary update aim…
Scaling Up Dynamic Graph Representation Learning via Spiking Neural Networks
Jintang Li, Zhouxin Yu, Zulun Zhu +6
Recent years have seen a surge in research on dynamic graph representation learning, which aims to model temporal graphs that are dynamic and evolving constantly over time. However…
q-AQUA: a many-body CCSD(T) water potential, including 4-body interactions, demonstrates the quantum nature of water from clusters to the liquid phase
Qi Yu, Chen Qu, Paul L. Houston +3
Many model potential energy surfaces (PESs) have been reported for water; however, none are strictly from "first principles". Here we report such a potential, based on a many-body…
"Gold-Standard" -Machine Learned and Transferable Potential for Linear Alkanes
Chen Qu, Thomas C. Allison, Apurba Nandi +4
The conformational properties of linear alkanes, CH, have been of intense interest for many years. Experiments and corresponding electronic structure calculations were…
On the capability of a class of quantum sensors
Qi Yu, Yuanlong Wang, Daoyi Dong +1
Quantum sensors may provide extremely high sensitivity and precision to extract key information in a quantum or classical physical system. A fundamental question is whether a quant…
Can We Ignore Labels In Out of Distribution Detection?
Hong Yang, Qi Yu, Travis Desell
Out-of-distribution (OOD) detection methods have recently become more prominent, serving as a core element in safety-critical autonomous systems. One major purpose of OOD detection…
Monomeric machine learning potential for general covalent molecules: linear alkanes as an example
Xinze Li, Ruitao Ma, Chen Qu +2
Machine-learning potentials (MLPs) have become important tools for modern molecular simulations. However, developing models that simultaneously achieve high accuracy and high compu…
Quantum calculations on a new CCSD(T) machine-learned PES reveal the leaky nature of gas-phase and ethanol conformers
Apurba Nandi, Riccardo Conte, Chen Qu +3
Ethanol is a molecule of fundamental interest in combustion, astrochemistry, and condensed phase as a solvent. It is characterized by two methyl rotors and () and $ga…
Deep Reinforced Attention Regression for Partial Sketch Based Image Retrieval
Dingrong Wang, Hitesh Sapkota, Xumin Liu +1
Fine-Grained Sketch-Based Image Retrieval (FG-SBIR) aims at finding a specific image from a large gallery given a query sketch. Despite the widespread applicability of FG-SBIR in m…
DRIVE: Deep Reinforced Accident Anticipation with Visual Explanation
Wentao Bao, Qi Yu, Yu Kong
Traffic accident anticipation aims to accurately and promptly predict the occurrence of a future accident from dashcam videos, which is vital for a safety-guaranteed self-driving s…
Bayesian Nonparametric Submodular Video Partition for Robust Anomaly Detection
Hitesh Sapkota, Qi Yu
Multiple-instance learning (MIL) provides an effective way to tackle the video anomaly detection problem by modeling it as a weakly supervised problem as the labels are usually onl…
No Headache for PIPs: A PIP Potential for Aspirin Outperforms Other Machine-Learned Potentials
Paul L. Houston, Chen Qu, Qi Yu +4
Assessments of machine-learned (ML) potentials are an important aspect of the rapid development of this field. We recently reported an assessment of the linear-regression permutati…
Tracking Quantum Dynamics in an Optical Cavity for Recovering Purity and Squeezing via Quantum State Smoothing
Shota Yokoyama, Kiarn T. Laverick, David McManus +6
Tracking the dynamics of a quantum system is conventionally achieved by monitoring the system continuously in time and filtering the information contained in measurement records vi…
Multidimensional Belief Quantification for Label-Efficient Meta-Learning
Deep Pandey, Qi Yu
Optimization-based meta-learning offers a promising direction for few-shot learning that is essential for many real-world computer vision applications. However, learning from few s…
Rectangular SNAP microresonator fabricated with a femtosecond laser
Qi Yu, Sajid Zaki, Yong Yang +3
SNAP microresonators, which are fabricated by nanoscale effective radius variation (ERV) of the optical fiber with sub-angstrom precision, can be potentially used as miniature clas…
Reinforced Compressive Neural Architecture Search for Versatile Adversarial Robustness
Dingrong Wang, Hitesh Sapkota, Zhiqiang Tao +1
Prior neural architecture search (NAS) for adversarial robustness works have discovered that a lightweight and adversarially robust neural network architecture could exist in a non…
Hybrid filtering for a class of nonlinear quantum systems subject to classical stochastic disturbances
Qi Yu, Daoyi Dong, Ian R. Petersen
A hybrid quantum-classical filtering problem, where a qubit system is disturbed by a classical stochastic process, is investigated. The strategy is to model the classical disturban…
When Does Restricting a Coding Agent to execute_code Help? A Regime Agent-Design Ablation
Hong Yang, Qi Yu, Travis Desell
Modern coding agents expose multiple tool surfaces -- IDE primitives, bash, and Model Context Protocol (MCP) code-execution -- and the field has shipped three contradictory claims…
Towards Open Set Video Anomaly Detection
Yuansheng Zhu, Wentao Bao, Qi Yu
Open Set Video Anomaly Detection (OpenVAD) aims to identify abnormal events from video data where both known anomalies and novel ones exist in testing. Unsupervised models learned…
Comprehensive fabrication of SNAP microresonators by a femtosecond laser
Qi Yu, Zhen Zhang, Xuewen Shu
Surface nanoscale axial photonics (SNAP) microresonators with nanoscale effective radius variation (ERV) along optical fiber axis can be fabricated by inscribing axially oriented l…
The quantum nature of ubiquitous vibrational features revealed for ethylene glycol
Apurba Nandi, Riccardo Conte, Priyanka Pandey +4
Vibrational properties of molecules are of widespread interest and importance in chemistry and biochemistry. The reliability of widely employed approximate computational methods is…
Combined Dictionary Unfolding Network with Gradient-Adaptive Fidelity for Transferable Multi-Source Fusion
Ge Luo, Jun-Jie Huang, Qi Yu +6
Deep Unfolding Network-based methods have emerged as effective solutions for multi-source image fusion by combining model-driven iterative optimization with data-driven deep learni…
Presenting and Evaluating the Impact of Experiential Learning in Computing Accessibility Education
Weishi Shi, Samuel Malachowsky, Yasmine El-Glaly +2
Studies indicate that much of the software created today is not accessible to all users, indicating that developers don't see the need to devote sufficient resources to creating ac…
Spectral analyses of trans- and cis-DOCO transients via comb spectroscopy
Thinh Q. Bui, P. Bryan Changala, Bryce J. Bjork +5
We use time-resolved direct frequency comb spectroscopy in the mid-infrared to obtain high-resolution rovibrational spectra of products produced from the OD+CO reaction. In this wo…
Evidential Deep Learning for Open Set Action Recognition
Wentao Bao, Qi Yu, Yu Kong
In a real-world scenario, human actions are typically out of the distribution from training data, which requires a model to both recognize the known actions and reject the unknown.…
edge2vec: Representation learning using edge semantics for biomedical knowledge discovery
Zheng Gao, Gang Fu, Chunping Ouyang +8
Representation learning provides new and powerful graph analytical approaches and tools for the highly valued data science challenge of mining knowledge graphs. Since previous grap…
OpenTAL: Towards Open Set Temporal Action Localization
Wentao Bao, Qi Yu, Yu Kong
Temporal Action Localization (TAL) has experienced remarkable success under the supervised learning paradigm. However, existing TAL methods are rooted in the closed set assumption,…
Hybrid Filtering for a Class of Quantum Systems with Classical Disturbances
Qi Yu, Daoyi Dong, Ian R. Petersen +1
A filtering problem for a class of quantum systems disturbed by a classical stochastic process is investigated in this paper. The classical disturbance process, which is assumed to…
Quantum speed-up in solving the maximal clique problem
Weng-Long Chang, Qi Yu, Zhaokai Li +3
The maximal clique problem, to find the maximally sized clique in a given graph, is classically an NP-complete computational problem, which has potential applications ranging from…
Generation of accessible sets in the dynamical modelling of quantum network systems
Qi Yu, Yuanlong Wang, Daoyi Dong +2
In this paper, we consider the dynamical modeling of a class of quantum network systems consisting of qubits. Qubit probes are employed to measure a set of selected nodes of the qu…
On Model Explanations with Transferable Neural Pathways
Xinmiao Lin, Wentao Bao, Qi Yu +1
Neural pathways as model explanations consist of a sparse set of neurons that provide the same level of prediction performance as the whole model. Existing methods primarily focus…
Quantum mechanical deconstruction of vibrational energy transfer rate and pathways modified by collective vibrational strong coupling
Qi Yu, Dong H. Zhang, Joel M. Bowman
Recent experiments have demonstrated that vibrational strong coupling (VSC) between molecular vibrations and the optical cavity field can modify vibrational energy transfer (VET) p…
ProDisc-VAD: An Efficient System for Weakly-Supervised Anomaly Detection in Video Surveillance Applications
Tao Zhu, Qi Yu, Xinru Dong +4
Weakly-supervised video anomaly detection (WS-VAD) using Multiple Instance Learning (MIL) suffers from label ambiguity, hindering discriminative feature learning. We propose ProDis…
Generalized Regularized Evidential Deep Learning Models: Theory and Comprehensive Evaluation
Deep Shankar Pandey, Hyomin Choi, Qi Yu
Evidential deep learning (EDL) models, based on Subjective Logic, introduce a principled and computationally efficient way to make deterministic neural networks uncertainty-aware.…
Object-Aware Centroid Voting for Monocular 3D Object Detection
Wentao Bao, Qi Yu, Yu Kong
Monocular 3D object detection aims to detect objects in a 3D physical world from a single camera. However, recent approaches either rely on expensive LiDAR devices, or resort to de…
AvAtar: Learning to Align via Active Optimal Transport
Qi Yu, Ruizhong Qiu, Zhichen Zeng +3
The paper introduces AvAtar, an active learning framework that selects informative supervision points to improve optimal transport‑based alignment by measuring each candidate's gra…
Permutationally invariant polynomial regression for energies and gradients, using reverse differentiation, achieves orders of magnitude speed-up with high precision compared to other machine learning methods
Paul L. Houston, Chen Qu, Apurba Nandi +3
Permutationally invariant polynomial (PIP) regression has been used to obtain machine-learned (ML) potential energy surfaces, including analytical gradients, for many molecules and…
Latent Space Energy-based Model for Fine-grained Open Set Recognition
Wentao Bao, Qi Yu, Yu Kong
Fine-grained open-set recognition (FineOSR) aims to recognize images belonging to classes with subtle appearance differences while rejecting images of unknown classes. A recent tre…
Multidimensional quantum calculation of the infrared spectra under polaritonic vibrational strong and ultrastrong coupling
Qi Yu
Recent experiments and theory demonstrate that the the ground state properties and chemical reactivity of molecules can be modified inside an optical cavity. The vibrational strong…
Joint Optimal Transport and Embedding for Network Alignment
Qi Yu, Zhichen Zeng, Yuchen Yan +3
Network alignment, which aims to find node correspondence across different networks, is the cornerstone of various downstream multi-network and Web mining tasks. Most of the embedd…
Extending the atomic decomposition and many-body representation, a chemistry-motivated monomer-centered approach for machine learning potentials
Qi Yu, Ruitao Ma, Chen Qu +6
Most widely used machine learned (ML) potentials for condensed phase applications rely on many-body permutationally invariant polynomial (PIP) or atom-centered neural networks (NN)…
Simultaneous estimation of parameters and the state of an optical parametric oscillator system
Qi Yu, Shota Yokoyama, Daoyi Dong +2
In this paper, we consider the filtering problem of an optical parametric oscillator (OPO). The OPO pump power may fluctuate due to environmental disturbances, resulting in uncerta…
Balancing Bias and Variance for Active Weakly Supervised Learning
Hitesh Sapkota, Qi Yu
As a widely used weakly supervised learning scheme, modern multiple instance learning (MIL) models achieve competitive performance at the bag level. However, instance-level predict…
DLAU: A Scalable Deep Learning Accelerator Unit on FPGA
Chao Wang, Qi Yu, Lei Gong +3
As the emerging field of machine learning, deep learning shows excellent ability in solving complex learning problems. However, the size of the networks becomes increasingly large…
Control-centric quantum noise spectroscopy of time-ordered polyspectra
Kaiah Steven, Elliot Coupe, Qi Yu +1
Precise environmental-noise characterisation in open quantum systems is a key step toward high-fidelity quantum control and targeted decoherence suppression in computing and sensin…
Time-In-Range Analyses of Functional Data Subject to Missing with Applications to Inpatient Continuous Glucose Monitoring
Qi Yu, Guillermo E. Umpierrez, Limin Peng
Continuous glucose monitoring (CGM) has been increasingly used in US hospitals for the care of patients with diabetes. Time in range (TIR), which measures the percent of time over…
Fidelity of Machine Learned Potentials: Quantitative Assessment for Protonated Oxalate
Chen Qu, Paul L. Houston, Qi Yu +5
There has been a veritable explosion of methods and software to perform machine-learned regression on datasets of electronic energies and forces to develop high-dimensional machine…
FuXi-Air: Urban Air Quality Forecasting Based on Emission-Meteorology-Pollutant multimodal Machine Learning
Zhixin Geng, Xu Fan, Xiqiao Lu +9
Air pollution has emerged as a major public health challenge in megacities. Numerical simulations and single-site machine learning approaches have been widely applied in air qualit…
Spiking Graph Convolutional Networks
Zulun Zhu, Jiaying Peng, Jintang Li +3
Graph Convolutional Networks (GCNs) achieve an impressive performance due to the remarkable representation ability in learning the graph information. However, GCNs, when implemente…
Can We Learn the Energy of Sublimation of Ice from Water Clusters?
Joe Bowman, Qi Yu, Chen Qu +2
This short paper reports a study of the electronic dissociation energies, De, of water clusters from direct ab initio (mostly CCSD(T)) calculations and the q-AQUA and MB-pol potent…
The MD17 Datasets from the Perspective of Datasets for Gas-Phase "Small" Molecule Potentials
Joel M. Bowman, Chen Qu Riccardo Conte, Apurba Nandi +2
There has been great progress in developing methods for machine-learned potential energy surfaces. There have also been important assessments of these methods by comparing so-calle…
-Machine Learning to Elevate DFT-based Potentials and a Force Field to the CCSD(T) Level Illustrated for Ethanol
Apurba Nandi, Priyanka Pandey, Paul L. Houston +5
Progress in machine learning has facilitated the development of potentials that offer both the accuracy of first-principles techniques and vast increases in the speed of evaluation…
Workflows Community Summit 2024: Future Trends and Challenges in Scientific Workflows
Rafael Ferreira da Silva, Deborah Bard, Kyle Chard +108
The Workflows Community Summit gathered 111 participants from 18 countries to discuss emerging trends and challenges in scientific workflows, focusing on six key areas: time-sensit…
Improving the Decision-Making Process of Self-Adaptive Systems by Accounting for Tactic Volatility
Jeffrey Palmerino, Qi Yu, Travis Desell +1
When self-adaptive systems encounter changes within their surrounding environments, they enact tactics to perform necessary adaptations. For example, a self-adaptive cloud-based sy…
Domain Feature Collapse: Implications for Out-of-Distribution Detection and Solutions
Hong Yang, Devroop Kar, Qi Yu +2
Why do state-of-the-art OOD detection methods exhibit catastrophic failure when models are trained on single-domain datasets? We provide the first theoretical explanation for this…
Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learning
Wentao Bao, Qi Yu, Yu Kong
Traffic accident anticipation aims to predict accidents from dashcam videos as early as possible, which is critical to safety-guaranteed self-driving systems. With cluttered traffi…