Papers
Research papers from arXiv and related sources
The Good, the Better, and the Best: Improving the Discriminability of Face Embeddings through Attribute-aware Learning
Despite recent advances in face recognition, robust performance remains challenging under large variations in age, pose, and occlusion. A common strategy to address these issues is to guide represe...
Ana Dias, João Ribeiro Pinto, Hugo Proença, João C. Neves
Prompt Readiness Levels (PRL): a maturity scale and scoring framework for production grade prompt assets
Prompt engineering has become a production critical component of generative AI systems. However, organizations still lack a shared, auditable method to qualify prompt assets against operational obj...
Sebastien Guinard
Interpretable Predictability-Based AI Text Detection: A Replication Study
This paper replicates and extends the system used in the AuTexTification 2023 shared task for authorship attribution of machine-generated texts. First, we tried to reproduce the original results. E...
Adam Skurla, Dominik Macko, Jakub Simko
Scalable Self-Testing of Mutually Anticommuting Observables and Maximally Entangled Two-Qudits
The next frontier in device-independent quantum information lies in the certification of scalable and parallel quantum resources, which underpin advanced quantum technologies. We put forth a simult...
Souradeep Sasmal, Ritesh K. Singh, Prabuddha Roy, A. K. Pan
Gravity from surface triangulation: convergence acceleration with nested grids
The determination of the gravitational potential by the polyhedral method is revisited in the case where the surface of a body is composed of triangular facets. Based upon six test-shapes of astrop...
Jean-Marc Huré
Rethinking LLM Watermark Detection in Black-Box Settings: A Non-Intrusive Third-Party Framework
While watermarking serves as a critical mechanism for LLM provenance, existing secret-key schemes tightly couple detection with injection, requiring access to keys or provider-side scheme-specific ...
Zhuoshang Wang, Yubing Ren, Yanan Cao, Fang Fang, Xiaoxue Li, Li Guo
Performance of Efron and Tibshirani's semiparametric density estimator
Recently, Efron and Tibshirani (Annals of Statistics, 1996) proposed a semiparametric density estimator, which works by multiplying an initial kernel type estimate with a parametric exponential typ...
Nils Lid Hjort
Probing the first generations of massive stars through fluorine in CEMP-no stars
We investigate whether the first discovered fluorine-rich CEMP-no star, CS 29498$-$043, can be explained by a very metal-poor rotating massive star. We consider single rotating stellar models of 20...
Arthur Choplin, Georges Meynet
Directional Routing in Transformers
We introduce directional routing, a lightweight mechanism that gives each transformer attention head learned suppression directions controlled by a shared router, at 3.9% parameter cost. We train a...
Kevin Taylor
Which stylistic features fool ChatGPT research evaluations?
Large Language Models (LLMs) have the potential to be used to support research evaluation and have a moderate capability to estimate the research quality of a journal article from its title and abs...
Kayvan Kousha, Mike Thelwall
Integrated Channel Sounding and Communication: Requirements, Architecture, Challenges, and Key Technologies
Channel models are essential for the design, evaluation, and optimization of wireless communication systems. The emerging space-air-ground-sea integrated network (SAGSIN), characterized by diverse ...
Nanhao Zhou, Chao Zou, Yu Zhou, Yanqun Tang, Xiaoying Zhang, Haoran Yin, Xuefeng Yin, Yuxiang Zha...
Fine-tuning RoBERTa for CVE-to-CWE Classification: A 125M Parameter Model Competitive with LLMs
We present a fine-tuned RoBERTa-base classifier (125M parameters) for mapping Common Vulnerabilities and Exposures (CVE) descriptions to Common Weakness Enumeration (CWE) categories. We construct a...
Nikita Mosievskiy
Machine learning for sustainable geoenergy: uncertainty, physics and decision-ready inference
Geoenergy projects (CO2 storage, geothermal, subsurface H2 generation/storage, critical minerals from subsurface fluids, or nuclear waste disposal) increasingly follow a petroleum-style funnel from...
Hannah P. Menke, Ahmed H. Elsheikh, Lingli Wei, Nanzhe Wang, Andreas Busch
T-DAQ-P: a portable tablet-form multi-stream data acquisition and contextual telemetry platform based on COTS modules and a custom integration layer
We present T-DAQ-P, a compact and portable data acquisition and telemetry platform designed to support detector deployments in laboratory and field conditions by integrating event streaming, slow-c...
D. Tagnani, M. Andreotti
BiTro: Bidirectional Transfer Learning Enhances Bulk and Spatial Transcriptomics Prediction in Cancer Pathological Images
Cancer pathological analysis requires modeling tumor heterogeneity across multiple modalities, primarily through transcriptomics and whole slide imaging (WSI), along with their spatial relations. O...
Jingkun Yu, Guangkai Shang, Changtao Li, Xun Gong, Tianrui Li, Yazhou He, Zhipeng Luo
LLMs as Signal Detectors: Sensitivity, Bias, and the Temperature-Criterion Analogy
Large language models (LLMs) are evaluated for calibration using metrics such as Expected Calibration Error that conflate two distinct components: the model's ability to discriminate correct from i...
Jon-Paul Cacioli
Demonstration of AI-Assisted Scientific Workflow on Canonical Benchmarks
We present a fully reproducible demonstration of an AI-assisted scientific workflow designed for a broad physics, mathematics, and computer-science readership. The initial project artifact stack wa...
Kin Hung Fung
LLMind: Bio-inspired Training-free Adaptive Visual Representations for Vision-Language Models
Vision-Language Models (VLMs) typically assume a uniform spatial fidelity across the entire field of view of visual inputs, dedicating equal precision to even the uninformative regions. By contrast...
Soumyaratna Debnath, Bui Duc Manh, Zinan Liu, Lin Wang
Improved Degree Bounds for Hyperbolicity of Surfaces and Curve Complements
This paper establishes new degree bounds for Kobayashi hyperbolicity in dimension two. Our main results are: - A very generic surface in $\mathbb{P}^3$ of degree at least $17$ is Kobayashi hyperb...
Lei Hou, Dinh Tuan Huynh, Joël Merker, Song-Yan Xie
IgPose: A Generative Data-Augmented Pipeline for Robust Immunoglobulin-Antigen Binding Prediction
Predicting immunoglobulin-antigen (Ig-Ag) binding remains a significant challenge due to the paucity of experimentally-resolved complexes and the limited accuracy of de novo Ig structure prediction...
Tien-Cuong Bui, Injae Chung, Wonjun Lee, Junsu Ko, Juyong Lee