most citedEnhancing Code Understanding for Impact Analysis by Combining Transformers and Program Dependence Graphs

6 citations

7 papers

cs.LG2026

Defending against Model Extraction for GNNs with Model Reprogramming

Yan Wen, Zhenyi Wang, Heng Huang

Graph Neural Networks (GNNs) serve as the backbone for high-stakes applications in Machine-Learning-as-a-Service (MLaaS). Still, their black-box deployment exposes them to Model Ex…

astro-ph.IM2026

Early Exploration of the Scientific Discovery Space for the Habitable Worlds Observatory

Courtney D. Dressing, Danica Adams, Evelyne Alecian +324

The paper summarizes 70 science cases for the proposed NASA Habitable Worlds Observatory, outlining the observational needs across four scientific pillars and detailing required ca…

cs.CV2026

UniMod: Enhancing Multi-Modal Medical Diagnosis through Cross-Modality and Within-Modality Alignment

Zijian Gu, Weikai Lin, Shuang Zhou +2

Multi-modal learning combining medical images and clinical text is promising for disease diagnosis. However, standard multi-modal training leads to shortcut learning: models exploi…

cs.CV2026

FedVAR: Prototype-Aligned Federated Framework for Video Anomaly Recognition

Ghani Haider, Majid Kundroo, Boyun Eom +3

In the era of Industrial Internet of Things (IIoT) and Cyber-Physical Systems (CPS), Federated Learning (FL) offers a promising decentralized intelligence paradigm for Video Anomal…

astro-ph.EP2026

Kilometre-scale Jovian moon characterized for a potential JUICE flyby

Juan Luis Rizos, Jose Maria Gomez-Limon, Yucel Kilic +51

The paper presents new observations of Jupiter’s irregular moon Kallichore, using Hubble, ground‑based telescopes and stellar occultations to refine its orbit, size, shape and surf…

cs.SE20266 cited

Enhancing Code Understanding for Impact Analysis by Combining Transformers and Program Dependence Graphs

Yanfu Yan, Nathan Cooper, Kevin Moran +3

Impact analysis (IA) is a critical software maintenance task that identifies the effects of a given set of code changes on a larger software project with the intention of avoiding…