Tootfinder

My brilliant @… colleagues beat me to it. The evaluation for #Antarctica is out before I have done the model protocol paper! It's a great piece of work and if you're interested in high resolution climate information from RCMs, read it ❄️🌊🥼⚒️
https://egusphere.copernicus.org/preprints/2025/egusphere-2025-4214/

Viel Lektüre für den 30. November #schweiz #demokratie

Evaluating Fundus-Specific Foundation Models for Diabetic Macular Edema Detection
Franco Javier Arellano, Jos\'e Ignacio Orlando
https://arxiv.org/abs/2510.07277 https://

Evaluating Fundus-Specific Foundation Models for Diabetic Macular Edema Detection
Diabetic Macular Edema (DME) is a leading cause of vision loss among patients with Diabetic Retinopathy (DR). While deep learning has shown promising results for automatically detecting this condition from fundus images, its application remains challenging due the limited availability of annotated data. Foundation Models (FM) have emerged as an alternative solution. However, it is unclear if they can cope with DME detection in particular. In this paper, we systematically compare different FM an…

Axion Perturbations: A General Analytical Treatment
Itamar J. Allali, Priyesh Chakraborty, JiJi Fan, Matthew Reece
https://arxiv.org/abs/2510.07371 https://

Axion Perturbations: A General Analytical Treatment
Cosmological data provides us two key constraints on dark matter (DM): it must have a particular abundance, and it must have an adiabatic spectrum of density perturbations in the early universe. Many different cosmological scenarios have been proposed that establish the abundance of axion DM in qualitatively different ways. In this paper we emphasize that, despite this variety of backgrounds, the perturbations in axion DM can be understood from universal principles. How does a feebly interactin…

On the optimization dynamics of RLVR: Gradient gap and step size thresholds
Joe Suk, Yaqi Duan
https://arxiv.org/abs/2510.08539 https://arxiv.org/pdf/2510.…

On the optimization dynamics of RLVR: Gradient gap and step size thresholds
Reinforcement Learning with Verifiable Rewards (RLVR), which uses simple binary feedback to post-train large language models, has shown significant empirical success. However, a principled understanding of why it works has been lacking. This paper builds a theoretical foundation for RLVR by analyzing its training process at both the full-response (trajectory) and token levels. Central to our analysis is a quantity called the Gradient Gap, which formalizes the direction of improvement from low-r…

Wideband dynamic metasurface antenna performance with practical design characteristics
Joseph M. Carlson, Nitish V. Deshpande, Miguel Rodrigo Castellanos, Robert W. Heath Jr
https://arxiv.org/abs/2510.07827

Wideband dynamic metasurface antenna performance with practical design characteristics
Dynamic metasurface antennas (DMA) provide low-power beamforming through reconfigurable radiative slots. Each slot has a tunable component that consumes low power compared to typical analog components like phase shifters. This makes DMAs a potential candidate to minimize the power consumption of multiple-input multiple-output (MIMO) antenna arrays. In this paper, we investigate the use of DMAs in a wideband communication setting with practical DMA design characteristics. We develop approximatio…

CRACI: A Cloud-Native Reference Architecture for the Industrial Compute Continuum
Hai Dinh-Tuan
https://arxiv.org/abs/2509.07498 https://arxiv.org/pdf/2509…

CRACI: A Cloud-Native Reference Architecture for the Industrial Compute Continuum
The convergence of Information Technology (IT) and Operational Technology (OT) in Industry 4.0 exposes the limitations of traditional, hierarchical architectures like ISA-95 and RAMI 4.0. Their inherent rigidity, data silos, and lack of support for cloud-native technologies impair the development of scalable and interoperable industrial systems. This paper addresses this issue by introducing CRACI, a Cloud-native Reference Architecture for the Industrial Compute Continuum. Among other features,…

TransMPC: Transformer-based Explicit MPC with Variable Prediction Horizon
Sichao Wu, Jiang Wu, Xingyu Cao, Fawang Zhang, Guangyuan Yu, Junjie Zhao, Yue Qu, Fei Ma, Jingliang Duan
https://arxiv.org/abs/2509.07381

TransMPC: Transformer-based Explicit MPC with Variable Prediction Horizon
Traditional online Model Predictive Control (MPC) methods often suffer from excessive computational complexity, limiting their practical deployment. Explicit MPC mitigates online computational load by pre-computing control policies offline; however, existing explicit MPC methods typically rely on simplified system dynamics and cost functions, restricting their accuracy for complex systems. This paper proposes TransMPC, a novel Transformer-based explicit MPC algorithm capable of generating highl…

Reinforcement Learning from Probabilistic Forecasts for Safe Decision-Making via Conditional Value-at-Risk Planning
Michal Koren, Or Peretz, Tai Dinh, Philip S. Yu
https://arxiv.org/abs/2510.08226

Reinforcement Learning from Probabilistic Forecasts for Safe Decision-Making via Conditional Value-at-Risk Planning
Sequential decisions in volatile, high-stakes settings require more than maximizing expected return; they require principled uncertainty management. This paper presents the Uncertainty-Aware Markov Decision Process (UAMDP), a unified framework that couples Bayesian forecasting, posterior-sampling reinforcement learning, and planning under a conditional value-at-risk (CVaR) constraint. In a closed loop, the agent updates its beliefs over latent dynamics, samples plausible futures via Thompson sa…

Feature Space Analysis by Guided Diffusion Model
Kimiaki Shirahama, Miki Yanobu, Kaduki Yamashita, Miho Ohsaki
https://arxiv.org/abs/2509.07936 https://arx…

Feature Space Analysis by Guided Diffusion Model
One of the key issues in Deep Neural Networks (DNNs) is the black-box nature of their internal feature extraction process. Targeting vision-related domains, this paper focuses on analysing the feature space of a DNN by proposing a decoder that can generate images whose features are guaranteed to closely match a user-specified feature. Owing to this guarantee that is missed in past studies, our decoder allows us to evidence which of various attributes in an image are encoded into a feature by th…