Papers
Research papers from arXiv and related sources
Semantics for 2D Rasterization
Rasterization is the process of determining the color of every pixel drawn by an application. Powerful rasterization libraries like Skia, CoreGraphics, and Direct2D put exceptional effort into draw...
Bhargav Kulkarni, Henry Whiting, Pavel Panchekha
Assessment Design in the AI Era: A Method for Identifying Items Functioning Differentially for Humans and Chatbots
The rapid adoption of large language models (LLMs) in education raises profound challenges for assessment design. To adapt assessments to the presence of LLM-based tools, it is crucial to character...
Licol Zeinfeld, Alona Strugatski, Ziva Bar-Dov, Ron Blonder, Shelley Rap, Giora Alexandron
Prototype Fusion: A Training-Free Multi-Layer Approach to OOD Detection
Deep learning models are increasingly deployed in safety-critical applications, where reliable out-of-distribution (OOD) detection is essential to ensure robustness. Existing methods predominantly ...
Shreen Gul, Mohamed Elmahallawy, Ardhendu Tripathy, Sanjay Madria
PerturbationDrive: A Framework for Perturbation-Based Testing of ADAS
Advanced driver assistance systems (ADAS) often rely on deep neural networks to interpret driving images and support vehicle control. Although reliable under nominal conditions, these systems remai...
Hannes Leonhard, Stefano Carlo Lambertenghi, Andrea Stocco
Ethio-ASR: Joint Multilingual Speech Recognition and Language Identification for Ethiopian Languages
We present Ethio-ASR, a suite of multilingual CTC-based automatic speech recognition (ASR) models jointly trained on five Ethiopian languages: Amharic, Tigrinya, Oromo, Sidaama, and Wolaytta. These...
Badr M. Abdullah, Israel Abebe Azime, Atnafu Lambebo Tonja, Jesujoba O. Alabi, Abel Mulat Alemu, ...
Foundation Model Embeddings Meet Blended Emotions: A Multimodal Fusion Approach for the BLEMORE Challenge
We present our system for the BLEMORE Challenge at FG 2026 on blended emotion recognition with relative salience prediction. Our approach combines six encoder families through late probability fusi...
Masoumeh Chapariniya, Aref Farhadipour, Sarah Ebling, Volker Dellwo, Teodora Vukovic
QuickQudits: A Framework for Efficient Simulation of Noisy Qudit Clifford Circuits via an Extended Stabilizer Tableau Formalism
We present a comprehensive and self-contained framework for the efficient classical simulation of Clifford circuits acting on $d$-dimensional qudits, including realistic Pauli/Weyl noise via stocha...
Nina Brandl, Mykyta Cherniak, Johannes Kofler, Richard Kueng
Testing Dark Energy with Black Hole Ringdown
We show that dynamical dark energy theories can imprint $O(1)$ modifications on the quasi-normal mode (QNM) spectrum characterising black hole ringdown. The time dependence of dynamical dark energy...
Laurens Smulders, Johannes Noller, Sergi Sirera
Detect--Repair--Verify for LLM-Generated Code: A Multi-Language, Multi-Granularity Empirical Study
Large language models can generate runnable software artifacts, but their security remains difficult to evaluate end to end. This study examines that problem through a Detect--Repair--Verify (DRV) ...
Cheng Cheng
OccAny: Generalized Unconstrained Urban 3D Occupancy
Relying on in-domain annotations and precise sensor-rig priors, existing 3D occupancy prediction methods are limited in both scalability and out-of-domain generalization. While recent visual geomet...
Anh-Quan Cao, Tuan-Hung Vu
MedObvious: Exposing the Medical Moravec's Paradox in VLMs via Clinical Triage
Vision Language Models (VLMs) are increasingly used for tasks like medical report generation and visual question answering. However, fluent diagnostic text does not guarantee safe visual understand...
Ufaq Khan, Umair Nawaz, L D M S S Teja, Numaan Saeed, Muhammad Bilal, Yutong Xie, Mohammad Yaqub,...
UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation
Unified models capable of interleaved generation have emerged as a promising paradigm, with the community increasingly converging on autoregressive modeling for text and flow matching for image gen...
Jie Liu, Zilyu Ye, Linxiao Yuan, Shenhan Zhu, Yu Gao, Jie Wu, Kunchang Li, Xionghui Wang, Xiaonan...
Estimating Flow Velocity and Vehicle Angle-of-Attack from Non-invasive Piezoelectric Structural Measurements Using Deep Learning
Accurate estimation of aerodynamic state variables such as freestream velocity and angle of attack (AoA) is important for aerodynamic load prediction, flight control, and model validation. This wor...
Chandler B. Smith, S. Hales Swift, Andrew Steyer, Ihab El-Kady
Failure of contextual invariance in gender inference with large language models
Standard evaluation practices assume that large language model (LLM) outputs are stable under contextually equivalent formulations of a task. Here, we test this assumption in the setting of gender ...
Sagar Kumar, Ariel Flint, Luca Maria Aiello, Andrea Baronchelli
SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning
Agentic multimodal large language models (MLLMs) (e.g., OpenAI o3 and Gemini Agentic Vision) achieve remarkable reasoning capabilities through iterative visual tool invocation. However, the cascade...
Haoyu Huang, Jinfa Huang, Zhongwei Wan, Xiawu Zheng, Rongrong Ji, Jiebo Luo
ReqFusion: A Multi-Provider Framework for Automated PEGS Analysis Across Software Domains
Requirements engineering is a vital, yet labor-intensive, stage in the software development process. This article introduces ReqFusion: an AI-enhanced system that automates the extraction, classifi...
Muhammad Khalid, Manuel Oriol, Yilmaz Uygun
Evidence of political bias in search engines and language models before major elections
Search engines (SEs) and large language models (LLMs) are central to political information access, yet their algorithmic decisions and potential underlying biases remain underexplored. We developed...
Íris Damião, Paulo Almeida, João Franco, Nuno Santos, Pedro C. Magalhães, Joana Gonçalves-Sá
Regulating AI Agents
AI agents -- systems that can independently take actions to pursue complex goals with only limited human oversight -- have entered the mainstream. These systems are now being widely used to produce...
Kathrin Gardhouse, Amin Oueslati, Noam Kolt
ConceptCoder: Improve Code Reasoning via Concept Learning
Large language models (LLMs) have shown promising results for software engineering applications, but still struggle with code reasoning tasks such as vulnerability detection (VD). We introduce Conc...
Md Mahbubur Rahman, Hengbo Tong, Wei Le
CSTS: A Canonical Security Telemetry Substrate for AI-Native Cyber Detection
AI-driven cybersecurity systems often fail under cross-environment deployment due to fragmented, event-centric telemetry representations. We introduce the Canonical Security Telemetry Substrate (CS...
Abdul Rahman