output
20022026
most citedStealing Machine Learning Models via Prediction APIs

733 citations

75 papers

cs.IR2026

Multilingual and Domain-Agnostic Tip-of-the-Tongue Query Generation for Simulated Evaluation

Xuhong He, To Eun Kim, Maik Fröbe +3

Tip-of-the-Tongue (ToT) retrieval benchmarks have largely focused on English, limiting their applicability to multilingual information access. In this work, we construct multilingu…

cs.LG2026

Muscle Synergy Priors Enhance Biomechanical Fidelity in Predictive Musculoskeletal Locomotion Simulation

Ilseung Park, Eunsik Choi, Jangwhan Ahn +1

Human locomotion emerges from high-dimensional neuromuscular control, making predictive musculoskeletal simulation challenging. We present a physiology-informed reinforcement-learn…

q-bio.NC2026★ 3 cited

Explore Brain-Inspired Machine Intelligence for Connecting Dots on Graphs Through Holographic Blueprint of Oscillatory Synchronization

Tingting Dan, Jiaqi Ding, Guorong Wu

Neural coupling in both neuroscience and artificial intelligence emerges as dynamic oscillatory patterns that encode abstract concepts. To this end, we hypothesize that a deeper un…

astro-ph.EP2026★ 12 cited

A young progenitor for the most common planetary systems in the Galaxy

John H. Livingston, Erik A. Petigura, Trevor J. David +39

The Galaxy's most common known planetary systems have several Earth-to-Neptune-size planets in compact orbits. At small orbital separations, larger planets are less common than the…

econ.GN2025

There's Nothing in the Air

Jacob Adenbaum, Fil Babalievsky, William Jungerman

Why do wages grow faster in bigger cities? We use French administrative data to decompose the urban wage growth premium and find that the answer has surprisingly little to do with…

nucl-ex2025

Investigation of P levels near the proton threshold by Nuclear Resonance Fluorescence and the impact on the Si(p,)P thermonuclear rate

David Gribble, Christian Iliadis, Robert V. F. Janssens +13

We investigated the nuclear structure of P near the proton threshold using Nuclear Resonance Fluorescence (NRF) to refine the properties of key resonances in the Si(p…

hep-th2025

The Nature of Phantom Dark Energy and its Relation to Time Crystals

Laura Mersini-Houghton

In this letter we show that, at its fundamental level, phantom dark energy is a fluid made up of time crystals that permeate the fabric of space-time. In turn, any well-behaved sta…

cs.LG2024★ 2 cited

PedSleepMAE: Generative Model for Multimodal Pediatric Sleep Signals

Saurav R. Pandey, Aaqib Saeed, Harlin Lee

Pediatric sleep is an important but often overlooked area in health informatics. We present PedSleepMAE, a generative model that fully leverages multimodal pediatric sleep signals…

math.QA2024

Superpolynomials of algebraic links

Ivan Cherednik

Theory of motivic superpolynomials is developed, including its extension to algebraic links colored by rows, relations to -functions of plane curve singularities, the justificat…

cs.CL2024★ 3 cited

LLM Self-Correction with DeCRIM: Decompose, Critique, and Refine for Enhanced Following of Instructions with Multiple Constraints

Thomas Palmeira Ferraz, Kartik Mehta, Yu-Hsiang Lin +7

Instruction following is a key capability for LLMs. However, recent studies have shown that LLMs often struggle with instructions containing multiple constraints (e.g. a request to…

cs.HC2024★ 2 cited

Striking the Right Balance: Systematic Assessment of Evaluation Method Distribution Across Contribution Types

Feng Lin, Arran Zeyu Wang, Md Dilshadur Rahman +2

In the rapidly evolving field of information visualization, rigorous evaluation is essential for validating new techniques, understanding user interactions, and demonstrating the e…

physics.ins-det2024★ 8 cited

Development of a Silicon Drift Detector Array to Search for keV-scale Sterile Neutrinos with the KATRIN Experiment

Daniel Siegmann, Frank Edzards, Christina Bruch +25

Sterile neutrinos in the keV mass range present a viable candidate for dark matter. They can be detected through single decay, where they cause small spectral distortions. The…

stat.AP2023★ 2 cited

A Statistical Model of Bipartite Networks: Application to Cosponsorship in the United States Senate

Adeline Lo, Santiago Olivella, Kosuke Imai

Many networks in political and social research are bipartite, with edges connecting exclusively across two distinct types of nodes. A common example includes cosponsorship networks…

astro-ph.IM2023★ 9 cited

The Evryscope Fast Transient Engine: Real-Time Detection for Rapidly Evolving Transients

Hank Corbett, Jonathan Carney, Ramses Gonzalez +8

Astrophysical transients with rapid development on sub-hour timescales are intrinsically rare. Due to their short durations, events like stellar superflares, optical flashes from g…

stat.ME2022★ 19 cited

Differential item functioning via robust scaling

Peter F. Halpin

This paper proposes a method for assessing differential item functioning (DIF) in item response theory (IRT) models. The method does not require pre-specification of anchor items,…

q-bio.QM2022★ 22 cited

Distribution-based Sketching of Single-Cell Samples

Vishal Athreya Baskaran, Jolene Ranek, Siyuan Shan +2

Modern high-throughput single-cell immune profiling technologies, such as flow and mass cytometry and single-cell RNA sequencing can readily measure the expression of a large numbe…

cs.CV2022★ 13 cited

Local Spatiotemporal Representation Learning for Longitudinally-consistent Neuroimage Analysis

Mengwei Ren, Neel Dey, Martin A. Styner +2

Recent self-supervised advances in medical computer vision exploit global and local anatomical self-similarity for pretraining prior to downstream tasks such as segmentation. Howev…

cs.CV2022★ 17 cited

Learning to Retrieve Videos by Asking Questions

Avinash Madasu, Junier Oliva, Gedas Bertasius

The majority of traditional text-to-video retrieval systems operate in static environments, i.e., there is no interaction between the user and the agent beyond the initial textual…

cs.LG2022★ 11 cited

Transparent Single-Cell Set Classification with Kernel Mean Embeddings

Siyuan Shan, Vishal Baskaran, Haidong Yi +3

Modern single-cell flow and mass cytometry technologies measure the expression of several proteins of the individual cells within a blood or tissue sample. Each profiled biological…

cs.CV2021

VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks

Yi-Lin Sung, Jaemin Cho, Mohit Bansal

Recently, fine-tuning language models pre-trained on large text corpora have provided huge improvements on vision-and-language (V&L) tasks as well as on pure language tasks. Howeve…

physics.optics2021★ 195 cited

Roadmap on Wavefront Shaping and deep imaging in complex media

Sylvain Gigan, Ori Katz, Hilton B. de Aguiar +42

The last decade has seen the development of a wide set of tools, such as wavefront shaping, computational or fundamental methods, that allow to understand and control light propaga…

astro-ph.HE2021

SOAR/Goodman Spectroscopic Assessment of Candidate Counterparts of the LIGO-Virgo Event GW190814

Douglas Tucker, Matthew Wiesner, Sahar Allam +140

On 2019 August 14 at 21:10:39 UTC, the LIGO/Virgo Collaboration (LVC) detected a possible neutron star-black hole merger (NSBH), the first ever identified. An extensive search for…

cs.HC2021★ 5 cited

Enabling Longitudinal Exploratory Analysis of Clinical COVID Data

David Borland, Irena Brain, Karamarie Fecho +5

As the COVID-19 pandemic continues to impact the world, data is being gathered and analyzed to better understand the disease. Recognizing the potential for visual analytics technol…

cs.CL2021

ChrEnTranslate: Cherokee-English Machine Translation Demo with Quality Estimation and Corrective Feedback

Shiyue Zhang, Benjamin Frey, Mohit Bansal

We introduce ChrEnTranslate, an online machine translation demonstration system for translation between English and an endangered language Cherokee. It supports both statistical an…