Publications (58)
Simple Agents Outperform Experts in Biomedical Imaging Workflow Optimization
Xuefei, Wang, Kai A. Horstmann +9
Adapting production-level computer vision tools to bespoke scientific datasets is a critical "last mile" bottleneck. Current solutions are impractical: fine-tuning requires large a…
Cyber Intrusion Detection by Using Deep Neural Networks with Attack-sharing Loss
Boxiang Dong, Hui, Wang +5
Cyber attacks pose crucial threats to computer system security, and put digital treasuries at excessive risks. This leads to an urgent call for an effective intrusion detection sys…
High Dimensional Latent Panel Quantile Regression with an Application to Asset Pricing
Alexandre Belloni, Mingli Chen, Oscar Hernan Madrid Padilla +2
We propose a generalization of the linear panel quantile regression model to accommodate both \textit{sparse} and \textit{dense} parts: sparse means while the number of covariates…
Advancing Waterfall Plots for Cancer Treatment Response Assessment through Adjustment of Incomplete Follow-Up Time
Zhe, Wang, Linda Z. Sun +1
Waterfall plots are a key tool in early phase oncology clinical studies for visualizing individual patients' tumor size changes and provide efficacy assessment. However, comparing…
Ultrasensitive electrode-free and co-catalyst-free detection of nanomoles per hour hydrogen evolution for the discovery of new photocatalysts
Huaiyu, Wang, Rebecca Katz +3
High throughput theoretical methods are increasingly used to identify promising photocatalytic materials for hydrogen generation from water as a clean source of energy. While most…
Cost-efficient Data Acquisition on Online Data Marketplaces for Correlation Analysis
Yanying Li, Haipei Sun, Boxiang Dong +2
Incentivized by the enormous economic profits, the data marketplace platform has been proliferated recently. In this paper, we consider the data marketplace setting where a data sh…
Modeling Human Eye Movements with Neural Networks in a Maze-Solving Task
Jason Li, Nicholas Watters, Yingting +3
From smoothly pursuing moving objects to rapidly shifting gazes during visual search, humans employ a wide variety of eye movement strategies in different contexts. While eye movem…
EDRP: Enhanced Dynamic Relay Point Protocol for Data Dissemination in Multi-hop Wireless IoT Networks
Jothi Prasanna Shanmuga Sundaram, Magzhan Gabidolla, Luis Fujarte +11
Emerging IoT applications are transitioning from battery-powered to grid-powered nodes. DRP, a contention-based data dissemination protocol, was developed for these applications. T…
An adversarial learning framework for preserving users' anonymity in face-based emotion recognition
Vansh Narula, Zhangyang, Wang +1
Image and video-capturing technologies have permeated our every-day life. Such technologies can continuously monitor individuals' expressions in real-life settings, affording us ne…
Compact Molecular Gas Distribution in Quasar Host Galaxies
Molina, J., Wang +10
We use Atacama Large Millimeter/submillimeter Array CO(2-1) observations of six low-redshift Palomar-Green quasars to study the distribution and kinematics of the molecular gas of…
The Best of Both Worlds: Accurate Global and Personalized Models through Federated Learning with Data-Free Hyper-Knowledge Distillation
Huancheng Chen, Johnny, Wang +1
Heterogeneity of data distributed across clients limits the performance of global models trained through federated learning, especially in the settings with highly imbalanced class…
Multi-Band Wi-Fi Sensing with Matched Feature Granularity
Jianyuan Yu, Pu, Wang +4
Complementary to the fine-grained channel state information (CSI) from the physical layer and coarse-grained received signal strength indicator (RSSI) measurements, the mid-grained…
Improved Super-Resolution Convolution Neural Network for Large Images
Junyu, Wang, Rong Song
Single image super-resolution (SISR) is a very popular topic nowadays, which has both research value and practical value. In daily life, we crop a large image into sub-images to do…
Truth Inference on Sparse Crowdsourcing Data with Local Differential Privacy
Haipei Sun, Boxiang Dong, Hui +3
Crowdsourcing has arisen as a new problem-solving paradigm for tasks that are difficult for computers but easy for humans. However, since the answers collected from the recruited p…
VeriDL: Integrity Verification of Outsourced Deep Learning Services (Extended Version)
Boxiang Dong, Bo Zhang, Hui +1
Deep neural networks (DNNs) are prominent due to their superior performance in many fields. The deep-learning-as-a-service (DLaaS) paradigm enables individuals and organizations (c…
Episodic Multi-Task Learning with Heterogeneous Neural Processes
Jiayi Shen, Xiantong Zhen, Qi +2
This paper focuses on the data-insufficiency problem in multi-task learning within an episodic training setup. Specifically, we explore the potential of heterogeneous information a…
NSF-DOE Vera C. Rubin Observatory Observations of Interstellar Comet 3I/ATLAS (C/2025 N1)
Colin Orion Chandler, Pedro H. Bernardinelli, Mario JuriÄ +305
We report on the observation and measurement of astrometry, photometry, morphology, and activityof the interstellar object 3I/ATLAS, also designated C/2025 N1 (ATLAS) with the NSF-…
MOPO-LSI: A User Guide
Yong Zheng, Kumar Neelotpal Shukla, Jasmine Xu +3
MOPO-LSI is an open-source Multi-Objective Portfolio Optimization Library for Sustainable Investments. This document provides a user guide for MOPO-LSI version 1.0, including probl…
Harmonizing the Generation and Pre-publication Stewardship of FAIR Image Data
Nikki Bialy, Frank Alber, Brenda Andrews +44
Alongside molecular insights into genes and proteins, biological imaging holds great promise for deepening scientific understanding of complex cellular systems and advancing predic…
Bipolaronic nature of the pseudogap in (TaSe4)2I revealed via weak photoexcitation
Yingchao Zhang, Tika Kafle, Wenjing You +12
The origin of the pseudogap in many strongly correlated materials has been a longstanding puzzle. Here, we uncover which many-body interactions underlie the pseudogap in quasi-one-…
Measuring Average Treatment Effect from Heavy-tailed Data
Jason, Wang, Pauline Burke
Heavy-tailed metrics are common and often critical to product evaluation in the online world. While we may have samples large enough for Central Limit Theorem to kick in, experimen…
LibFewShot: A Comprehensive Library for Few-shot Learning
Wenbin Li, Ziyi, Wang +9
Few-shot learning, especially few-shot image classification, has received increasing attention and witnessed significant advances in recent years. Some recent studies implicitly sh…
D-LiFT: Improving LLM-based Decompiler Backend via Code Quality-driven Fine-tuning
Muqi Zou, Hongyu Cai, Hongwei Wu +9
The paper introduces D-LiFT, a system that fine‑tunes large language models with a code‑quality‑aware reinforcement learning approach to improve the accuracy and readability of dec…
UpDown: Programmable fine-grained Events for Scalable Performance on Irregular Applications
Andronicus Rajasukumar, Jiya Su, Yuqing +12
Applications with irregular data structures, data-dependent control flows and fine-grained data transfers (e.g., real-world graph computations) perform poorly on cache-based system…
Operon Dynamics with State Dependent Transcription and/or Translation Delays
Tomas Gedeon, Antony R. Humphries, Michael C. Mackey +3
Transcription and translation retrieve and operationalize gene encoded information in cells. These processes are not instantaneous and incur significant delays. In this paper we st…
Future Semantic Segmentation with Convolutional LSTM
Seyed shahabeddin Nabavi, Mrigank Rochan, Yang +1
We consider the problem of predicting semantic segmentation of future frames in a video. Given several observed frames in a video, our goal is to predict the semantic segmentation…
Generative AI for Industrial Contour Detection: A Language-Guided Vision System
Liang Gong, Tommy, Wang +5
Industrial computer vision systems often struggle with noise, material variability, and uncontrolled imaging conditions, limiting the effectiveness of classical edge detectors and…
Man-in-the-Middle Attacks against Machine Learning Classifiers via Malicious Generative Models
Derui, Wang, Chaoran Li +3
Deep Neural Networks (DNNs) are vulnerable to deliberately crafted adversarial examples. In the past few years, many efforts have been spent on exploring query-optimisation attacks…
Can LLM Agents Simulate Multi-Turn Human Behavior? Evidence from Real Online Customer Behavior Data
Yuxuan Lu, Jing Huang, Yan Han +9
Recent research shows that LLM Agents can generate ``believable'' human behaviors via prompt-only methods, and such agents have been increasingly adopted in downstream applications…
: Better Prompt Optimization with Fewer Prompts
Zhaolin Gao, Yu, Wang +4
Prompt optimization improves language models without updating their weights by searching for a better system prompt, but its effectiveness varies widely across tasks. We study what…
Macroeconomic Forecasting and Machine Learning
Ta-Chung Chi, Ting-Han Fan, Raffaele M. Ghigliazza +3
We forecast the full conditional distribution of macroeconomic outcomes by systematically integrating three key principles: using high-dimensional data with appropriate regularizat…
MiniCLEAN Dark Matter Experiment
JuiJen, Wang
The MiniCLEAN dark matter experiment will exploit a single-phase liquid-argon detector instrumented with 92 photomultiplier tubes placed in the cryogen temperature with 4- cove…
High Dimensional Data Modeling Techniques for Detection of Chemical Plumes and Anomalies in Hyperspectral Images and Movies
Yi, Wang, Guangliang Chen +1
We briefly review recent progress in techniques for modeling and analyzing hyperspectral images and movies, in particular for detecting plumes of both known and unknown chemicals.…
A Cross-direction Task Decoupling Network for Small Logo Detection
Hou, Sujuan, Li +10
Logo detection plays an integral role in many applications. However, handling small logos is still difficult since they occupy too few pixels in the image, which burdens the extrac…
Implementing Bayesian inference on a stochastic CO2-based grey-box model for assessing indoor air quality in Canadian primary schools
Shujie Yan, Jiwei Zou, Chang Shu +11
The COVID-19 pandemic brought global attention to indoor air quality (IAQ), which is intrinsically linked to clean air change rates. Estimating the air change rate in indoor enviro…
Muse Spark Safety & Preparedness Report
Cristina Menghini, Peter Ney, Hamza Kwisaba +117
Muse Spark is the latest large language model developed by Meta. In this report, we first present evaluations for catastrophic risk domains under Meta's Advanced AI Scaling Framewo…
Multi-Modal Recurrent Fusion for Indoor Localization
Jianyuan Yu, Pu, Wang +2
This paper considers indoor localization using multi-modal wireless signals including Wi-Fi, inertial measurement unit (IMU), and ultra-wideband (UWB). By formulating the localizat…
Growing Through Experience: Scaling Episodic Grounding in Language Models
Chunhui Zhang, Sirui, Wang +3
Language models (LMs) require robust episodic grounding-the capacity to learn from and apply past experiences-to excel at physical planning tasks. Current episodic grounding approa…
Fourier neural operator for large eddy simulation of compressible Rayleigh-Taylor turbulence
Tengfei Luo, Zhijie Li, Zelong Yuan +5
The Fourier neural operator (FNO) framework is applied to the large eddy simulation (LES) of three-dimensional compressible Rayleigh-Taylor (RT) turbulence with miscible fluids at…
TuneComp: Joint Fine-tuning and Compression for Large Foundation Models
Xiangyu Chen, Jing Liu, Ye Wang +4
To reduce model size during post-training, compression methods, including knowledge distillation, low-rank approximation, and pruning, are often applied after fine-tuning the model…
Unit interval parking functions and the -Fubini numbers
S. Alex Bradt, Jennifer Elder, Pamela E. Harris +5
We recall that unit interval parking functions of length are a subset of parking functions in which every car parks in its preference or in the spot after its preference, and F…
47 Tuc in Rubin Data Preview 1: Exploring Early LSST Data and Science Potential
Yumi Choi, Knut A. G. Olsen, Jeffrey L. Carlin +12
We present analyses of the early data from Rubin Observatory's Data Preview 1 (DP1) for the globular cluster 47 Tuc field. The DP1 dataset for 47 Tuc includes four nights of observ…
Optical Counterparts to X-ray sources in LSST DP1
Yuankun, Wang, Eric C. Bellm +9
The paper crossmatches a combined X‑ray source catalog with the Vera C. Rubin Observatory LSST Data Preview 1 to identify optical counterparts across six fields, reporting 2314 mat…
Forecasting Liquidity Withdraw with Machine Learning Models
Haochuan, Wang
Liquidity withdrawal is a critical indicator of market fragility. In this project, I test a framework for forecasting liquidity withdrawal at the individual-stock level, ranging fr…
An AI system to help scientists write expert-level empirical software
Eser Aygün, Anastasiya Belyaeva, Gheorghe Comanici +39
The cycle of scientific discovery is frequently bottlenecked by the slow, manual creation of software to support computational experiments\cite{hannay2009how}. To address this, we…
Influence of Myocardial Infarction on QRS Properties: A Simulation Study
Lei Li, Julia Camps, Zhinuo +4
The interplay between structural and electrical changes in the heart after myocardial infarction (MI) plays a key role in the initiation and maintenance of arrhythmia. The anatomic…
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431
In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…
LatentLLM: Attention-Aware Joint Tensor Compression
Toshiaki Koike-Akino, Xiangyu Chen, Jing Liu +4
Modern foundation models such as large language models (LLMs) and large multi-modal models (LMMs) require a massive amount of computational and memory resources. We propose a new f…
An Earth-sized Planet on the Verge of Tidal Disruption
Fei Dai, Andrew W. Howard, Samuel Halverson +95
TOI-6255~b (GJ 4256) is an Earth-sized planet (1.079 ) with an orbital period of only 5.7 hours. With the newly commissioned Keck Planet Finder (KPF) and CARMEN…
Predicting Long-term Urban Overheating and Their Mitigations from Nature Based Solutions Using Machine Learning and Field Measurements
Jiwei Zou, Lin Wang, Senwen Yang +3
Urban overheating, exacerbated by climate change, threatens public health and urban sustainability. Traditional approaches, such as numerical simulations and field measurements, fa…
Multi-Objective Recommendations: A Tutorial
Yong Zheng, David, Wang
Recommender systems (RecSys) have been well developed to assist user decision making. Traditional RecSys usually optimize a single objective (e.g., rating prediction errors or rank…
Polarization-Engineering in III-V Nitride Heterostructures: New Opportunities For Device Design
Debdeep Jena, John Simon, Albert +12
The role of spontaneous and piezoelectric polarization in III-V nitride heterostructure devices is discussed. Problems as well as opportunities in incorporating polarization in abr…
Crowded Field Photometry with Rubin: Exploring 47 Tucanae with Data Preview 1
Tobin M. Wainer, James R. A. Davenport, Eric C. Bellm +15
We analyze imaging from Data Preview 1 of the Vera C. Rubin Observatory to explore the performance of early LSST pipelines in the 47 Tucanae field. The coadd-\texttt{object} catalo…
Towards Enabling Cardiac Digital Twins of Myocardial Infarction Using Deep Computational Models for Inverse Inference
Lei Li, Julia Camps, Zhinuo +5
Cardiac digital twins (CDTs) have the potential to offer individualized evaluation of cardiac function in a non-invasive manner, making them a promising approach for personalized d…
Architectural Insights for Post-Tornado Damage Recognition
Robinson Umeike, Thang Dao, Shane Crawford +8
Rapid and accurate building damage assessment in the immediate aftermath of tornadoes is critical for coordinating life-saving search and rescue operations, optimizing emergency re…
The Llama 3 Herd of Models
Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri +556
Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It is a herd of language models th…
Masked Co-attentional Transformer reconstructs 100x ultra-fast/low-dose whole-body PET from longitudinal images and anatomically guided MRI
Yan-Ran, Wang, Liangqiong Qu +10
Despite its tremendous value for the diagnosis, treatment monitoring and surveillance of children with cancer, whole body staging with positron emission tomography (PET) is time co…
Modeling Light Curves for Improved Classification
Julian Faraway, Ashish Mahabal, Jiayang Sun +4
Many synoptic surveys are observing large parts of the sky multiple times. The resulting lightcurves provide a wonderful window to the dynamic nature of the universe. However, ther…