Papers
Research papers from arXiv and related sources
Multivariate lattice deformation: A spatially explicit framework for assessing crop rotation impacts on soil nutrient dynamics
Crop rotation impacts on soil nutrients are typically assessed using field-averaged or single-nutrient analyses that ignore spatial heterogeneity and multivariate interactions. We propose a multiva...
Marco Mandap
Explainable AI Using Inherently Interpretable Components for Wearable-based Health Monitoring
The use of wearables in medicine and wellness, enabled by AI-based models, offers tremendous potential for real-time monitoring and interpretable event detection. Explainable AI (XAI) is required t...
Maurice Kuschel, Solveig Vieluf, Claus Reinsberger, Tobias Loddenkemper, Tanuj Hasija
Test-time RL alignment exposes task familiarity artifacts in LLM benchmarks
Direct evaluation of LLMs on benchmarks can be misleading because comparatively strong performance may reflect task familiarity rather than capability. The train-before-test approach controls for t...
Kun Wang, Reinhard Heckel
CLARIN-PT-LDB: An Open LLM Leaderboard for Portuguese to assess Language, Culture and Civility
This paper reports on the development of a leaderboard of Open Large Language Models (LLM) for European Portuguese (PT-PT), and on its associated benchmarks. This leaderboard comes as a way to addr...
João Silva, Luís Gomes, António Branco
Weak Adversarial Neural Pushforward Method for Fractional Fokker-Planck Equations
We extend the Weak Adversarial Neural Pushforward Method (WANPM) to fractional Fokker-Planck equations (fFPE), in which the classical Laplacian diffusion operator is replaced by the fractional Lapl...
Andrew Qing He, Wei Cai
Breaking the Winner's Curse with Bayesian Hybrid Shrinkage
The widespread adoption of randomized controlled trials (A/B Tests) for decision-making has introduced a pervasive "Winner's Curse": experiments selected for launch often exhibit upwardly biased ef...
Richard Mudd, Abbas Zaidi, Rina Friedberg, Ilya Gorbachev, Anchal Choubey, Houssam Nassif
Composing Driving Worlds through Disentangled Control for Adversarial Scenario Generation
A major challenge in autonomous driving is the "long tail" of safety-critical edge cases, which often emerge from unusual combinations of common traffic elements. Synthesizing these scenarios is cr...
Yifan Zhan, Zhengqing Chen, Qingjie Wang, Zhuo He, Muyao Niu, Xiaoyang Guo, Wei Yin, Weiqiang Ren...
Design of a Dichroic Transmissive Huygens' Metasurface Unit-Cell Presenting Refraction Angle Duality
A purely transmissive Huygens' metasurface model under plane-wave illumination is used to derive circuit parameters describing a constituent unit cell, such that diverse refraction angles are attai...
Georgios Kyriakou, Giampaolo Pisano, Luca Olmi, Francesco Piacentini
Quantifying Perovskite Solar Cell Degradation via Machine Learning from Spatially Resolved Multimodal Luminescence Time Series
Perovskite solar cells (PSCs) have experienced a remarkable rise in power conversion efficiency (PCE) over the past 15 years, positioning them as a promising alternative or complement to silicon fo...
Giulio Barletta, Simon Ternes, Saif Ali, Zohair Abbas, Chiara Ostendi, Marialucia D'Addio, Erica ...
On Linear Separability of the MNIST Handwritten Digits Dataset
The MNIST dataset containing thousands of handwritten digit images is still a fundamental benchmark for evaluating various pattern-recognition and image-classification models. Linear separability i...
Ákos Hajnal
Team LEYA in 10th ABAW Competition: Multimodal Ambivalence/Hesitancy Recognition Approach
Ambivalence/hesitancy recognition in unconstrained videos is a challenging problem due to the subtle, multimodal, and context-dependent nature of this behavioral state. In this paper, a multimodal ...
Elena Ryumina, Alexandr Axyonov, Dmitry Sysoev, Timur Abdulkadirov, Kirill Almetov, Yulia Morozov...
Serving Hybrid LLM Loads with SLO Guarantees Using CPU-GPU Attention Piggybacking
Nowadays, service providers often deploy multiple types of LLM services within shared clusters. While the service colocation improves resource utilization, it introduces significant interference ri...
Zizhao Mo, Junlin Chen, Huanle Xu, Chengzhong Xu
From AI Weather Prediction to Infrastructure Resilience: A Correction-Downscaling Framework for Tropical Cyclone Impacts
This paper addresses a missing capability in infrastructure resilience: turning fast, global AI weather forecasts into asset-scale, actionable risk. We introduce the AI-based Correction-Downscaling...
You Wu, Zhenguo Wang, Naiyu Wang
Rethinking Multiple-Choice Questions for RLVR: Unlocking Potential via Distractor Design
Reinforcement Learning with Verifiable Rewards (RLVR) significantly enhances the reasoning capabilities of Large Language Models. When applied to RLVR, Multiple-Choice Questions (MCQs) offer a scal...
Xu Guo, Qiming Ge, Jian Tong, Kedi Chen, Jin Zhang, Xiaogui Yang, Xuan Gao, Haijun Lv, Zhihui Lu,...
Polynomial curvelets on higher-dimensional spheres
In this article, we introduce and investigate polynomial curvelets on spheres, which form a class of Parseval frames for $L^2(\mathbb{S}^{d-1})$, $d \geq 3$. The proposed construction offers a dire...
Frederic Schoppert
Does supernova feedback regulate the star formation rate in dwarf galaxies?
Stars form in cold, dense clouds embedded in galactic discs, but whether their formation is primarily regulated by gravitational collapse, turbulence, or stellar feedback remains unclear. Using fou...
D. Whitworth, E. Vázquez-Semadeni, J. Ballesteros-Paredes, G. O. Gómez
Context is all you need: Towards autonomous model-based process design using agentic AI in flowsheet simulations
Agentic AI systems integrating large language models (LLMs) with reasoning and tooluse capabilities are transforming various domains - in particular, software development. In contrast, their applic...
Pascal Schäfer, Lukas J. Krinke, Martin Wlotzka, Norbert Asprion
Gaia GraL X.: The GraL catalogue of gravitationally lensed quasars Matched with \textit{Gaia} data, redshifts, and time delays
Determining the Hubble constant tension requires alternative strategies, and multiply imaged quasars, with their intermediate redshifts, can potentially be used in this regard. We provide a current...
C. Ducourant, R. Teixeira, P. H. Vale-Cunha, L. Delchambre, A. Krone-Martins, J. Braine, L. Gallu...
Cheers: Decoupling Patch Details from Semantic Representations Enables Unified Multimodal Comprehension and Generation
A recent cutting-edge topic in multimodal modeling is to unify visual comprehension and generation within a single model. However, the two tasks demand mismatched decoding regimes and visual repres...
Yichen Zhang, Da Peng, Zonghao Guo, Zijian Zhang, Xuesong Yang, Tong Sun, Shichu Sun, Yidan Zhang...
Motion-Specific Battery Health Assessment for Quadrotors Using High-Fidelity Battery Models
Quadrotor endurance is ultimately limited by battery behavior, yet most energy aware planning treats the battery as a simple energy reservoir and overlooks how flight motions induce dynamic current...
Joonhee Kim, Sanghyun Park, Donghyeong Kim, Eunseon Choi, Soohee Han