Tootfinder

Training Deep Normalization-Free Spiking Neural Networks with Lateral Inhibition
Peiyu Liu, Jianhao Ding, Zhaofei Yu
https://arxiv.org/abs/2509.23253 https://

Training Deep Normalization-Free Spiking Neural Networks with Lateral Inhibition
Spiking neural networks (SNNs) have garnered significant attention as a central paradigm in neuromorphic computing, owing to their energy efficiency and biological plausibility. However, training deep SNNs has critically depended on explicit normalization schemes, such as batch normalization, leading to a trade-off between performance and biological realism. To resolve this conflict, we propose a normalization-free learning framework that incorporates lateral inhibition inspired by cortical cir…

Fast Real-Time Pipeline for Robust Arm Gesture Recognition
Mil\'an Zsolt Bagladi, L\'aszl\'o Guly\'as, Gerg\H{o} Szalay
https://arxiv.org/abs/2509.25042 https://…

Fast Real-Time Pipeline for Robust Arm Gesture Recognition
This paper presents a real-time pipeline for dynamic arm gesture recognition based on OpenPose keypoint estimation, keypoint normalization, and a recurrent neural network classifier. The 1 x 1 normalization scheme and two feature representations (coordinate- and angle-based) are presented for the pipeline. In addition, an efficient method to improve robustness against camera angle variations is also introduced by using artificially rotated training data. Experiments on a custom traffic-control …

Achieving Fair Skin Lesion Detection through Skin Tone Normalization and Channel Pruning
Zihan Wei, Tapabrata Chakraborti
https://arxiv.org/abs/2509.22712 https://

Achieving Fair Skin Lesion Detection through Skin Tone Normalization and Channel Pruning
Recent works have shown that deep learning based skin lesion image classification models trained on unbalanced dataset can exhibit bias toward protected demographic attributes such as race, age,and gender. Current bias mitigation methods usually either achieve high level of fairness with the degradation of accuracy, or only improve the model fairness on a single attribute. Additionally usually most bias mitigation strategies are either pre hoc through data processing or post hoc through fairnes…

U-SWIFT: A Unified Surface Wave Inversion Framework with Transformer via Normalization of Dispersion Curves
Tianjian Cheng, Hongrui Xu, Jiayu Feng, Xiongyu Hu, Chaofan Yao
https://arxiv.org/abs/2509.24872

U-SWIFT: A Unified Surface Wave Inversion Framework with Transformer via Normalization of Dispersion Curves
Deep learning is an increasingly popular approach for inverting surface wave dispersion curves to obtain Vs profiles. However, its generalizability is constrained by the depth and velocity scales of training data. We propose a unified deep learning framework that overcomes this limitation via normalization of dispersion curves. By leveraging the scaling properties of dispersion curves, our approach enables a single, pre-trained model to predict Vs profiles across diverse scales, from shallow su…

Scaling with Collapse: Efficient and Predictable Training of LLM Families
Shane Bergsma, Bin Claire Zhang, Nolan Dey, Shaheer Muhammad, Gurpreet Gosal, Joel Hestness
https://arxiv.org/abs/2509.25087

Scaling with Collapse: Efficient and Predictable Training of LLM Families
Effective LLM training relies on *consistency*, meaning that key quantities -- such as final losses and optimal hyperparameters -- scale predictably across model sizes. Qiu et al. (2025) recently showed that this consistency extends beyond scalars: whole training loss curves can *collapse* onto a universal trajectory after a simple normalization. What remains unclear is whether this phenomenon holds for LLM families trained under *practical scaling recipes*, where width, depth, learning rate, b…

Factorizations of 3d Interval Partition Functions
Boan Zhao, Panos Betzios, Paul Luis Roehl
https://arxiv.org/abs/2509.23902 https://arxiv.org/pdf/2509.239…

Factorizations of 3d Interval Partition Functions
We show that interval partition functions (transition amplitudes) of three- dimensional N = 2 theories admit factorizations into sums of products of hemisphere partition functions with additional normalization factors. We prove the factorization explic- itly for supersymmetric quantum electrodynamics and Chern-Simons-Yang-Mills theories. In the former case, we interpret the factorization geometrically in terms of the factorization of equivariant K-theory classes. In the latter case, we prove th…

Addressing Methodological Uncertainty in MCDM with a Systematic Pipeline Approach to Data Transformation Sensitivity Analysis
Juan B. Cabral, Alvaro Roy Schachner
https://arxiv.org/abs/2509.24996

Addressing Methodological Uncertainty in MCDM with a Systematic Pipeline Approach to Data Transformation Sensitivity Analysis
Multicriteria decision-making methods exhibit critical dependence on the choice of normalization techniques, where different selections can alter 20-40% of the final rankings. Current practice is characterized by the ad-hoc selection of methods without systematic robustness evaluation. We present a framework that addresses this methodological uncertainty through automated exploration of the scaling transformation space. The implementation leverages the existing Scikit-Criteria infrastructure to…

Database Normalization via Dual-LLM Self-Refinement
Eunjae Jo, Nakyung Lee, Gyuyeong Kim
https://arxiv.org/abs/2508.17693 https://arxiv.org/pdf/2508.17693

Database Normalization via Dual-LLM Self-Refinement
Database normalization is crucial to preserving data integrity. However, it is time-consuming and error-prone, as it is typically performed manually by data engineers. To this end, we present Miffie, a database normalization framework that leverages the capability of large language models. Miffie enables automated data normalization without human effort while preserving high accuracy. The core of Miffie is a dual-model self-refinement architecture that combines the best-performing models for no…

Mitigating Distribution Shift in Stock Price Data via Return-Volatility Normalization for Accurate Prediction
Hyunwoo Lee, Jihyeong Jeon, Jaemin Hong, U Kang
https://arxiv.org/abs/2508.20108

Mitigating Distribution Shift in Stock Price Data via Return-Volatility Normalization for Accurate Prediction
How can we address distribution shifts in stock price data to improve stock price prediction accuracy? Stock price prediction has attracted attention from both academia and industry, driven by its potential to uncover complex market patterns and enhance decisionmaking. However, existing methods often fail to handle distribution shifts effectively, focusing on scaling or representation adaptation without fully addressing distributional discrepancies and shape misalignments between training and t…

On black holes in new general relativity
D. F. L\'opez, A. A. Coley, R. J. van den Hoogen
https://arxiv.org/abs/2508.20314 https://arxiv.org/pdf/2508.2…

On black holes in new general relativity
New General Relativity (NGR) is a class of teleparallel theories defined by three free parameters, effectively reduced to two after appropriate normalization, which are subject to experimental constraints. In this framework, matter couples minimally to the metric, ensuring that test particles follow geodesics and that null congruence expansions can be employed to detect local horizons. Assuming such horizons exist, we demonstrate that all physically viable NGR models--including the Teleparallel…

Microscopic study of the asymptotic behavior of the reduced width amplitude in $^7$Li and $^7$Be
H. J. Zhu, M. J. Lyu, Q. Zhao, Z. Cheng, J. Q. Tian, M. Kimura, T. Myo, H. Horiuchi, H. Toki, M. Isaka, H. Takemoto, Akinobu Dot\'e, N. Wan
https://arxiv.org/abs/2509.23613

Microscopic study of the asymptotic behavior of the reduced width amplitude in $^7$Li and $^7$Be
We investigate the effects of different basis model spaces on the calculation of reduced width amplitude (RWA) and asymptotic normalization coefficient (ANC) for the $^{7}$Li and $^{7}$Be nuclei. The two-cluster model ($α+t/^3$He) and three-cluster model ($α+d+n/p$) with the generator coordinates method (GCM) are applied to calculate the wave function of $^7$Li and $^7$Be. Specifically, the model space for the three-cluster model is constructed upon a sufficiently broad space of two-cluster c…

Forecasting 21-cm power spectrum sensitivity to dark Matter-baryon scattering
Aryan Rahimieh, Priyank Parashari, Vera Gluscevic
https://arxiv.org/abs/2508.20507 https://

Forecasting 21-cm power spectrum sensitivity to dark Matter-baryon scattering
We explore the potential of upcoming 21-cm interferometric observations to probe interacting dark matter (IDM). We focus on scenarios where the dark matter-baryon scattering cross-section scales as $σ(v) =σ_{0} v^n$, with $σ_{0}$ being the normalization constant, $v$ the relative velocity between dark matter and baryons, and $n$ characterizing the velocity dependence. Specifically, we emphasize two cases: Coulomb-like interaction ($n = -4$) and velocity-independent interaction ($n = 0$). Usi…

CaRe-BN: Precise Moving Statistics for Stabilizing Spiking Neural Networks in Reinforcement Learning
Zijie Xu, Xinyu Shi, Yiting Dong, Zihan Huang, Zhaofei Yu
https://arxiv.org/abs/2509.23791

CaRe-BN: Precise Moving Statistics for Stabilizing Spiking Neural Networks in Reinforcement Learning
Spiking Neural Networks (SNNs) offer low-latency and energy-efficient decision-making on neuromorphic hardware by mimicking the event-driven dynamics of biological neurons. However, due to the discrete and non-differentiable nature of spikes, directly trained SNNs rely heavily on Batch Normalization (BN) to stabilize gradient updates. In online Reinforcement Learning (RL), imprecise BN statistics hinder exploitation, resulting in slower convergence and suboptimal policies. This challenge limits…

From Research to Reality: Feasibility of Gradient Inversion Attacks in Federated Learning
Viktor Valadi, Mattias {\AA}kesson, Johan \"Ostman, Salman Toor, Andreas Hellander
https://arxiv.org/abs/2508.19819

From Research to Reality: Feasibility of Gradient Inversion Attacks in Federated Learning
Gradient inversion attacks have garnered attention for their ability to compromise privacy in federated learning. However, many studies consider attacks with the model in inference mode, where training-time behaviors like dropout are disabled and batch normalization relies on fixed statistics. In this work, we systematically analyze how architecture and training behavior affect vulnerability, including the first in-depth study of inference-mode clients, which we show dramatically simplifies inv…

Bayesian Framework for the E1 and E2 Astrophysical Factors at 300 keV from Subthreshold and Ground-State Asymptotic Normalization Coefficients
A. M. Mukhamedzhanov
https://arxiv.org/abs/2509.17102

Bayesian Framework for the E1 and E2 Astrophysical Factors at 300 keV from Subthreshold and Ground-State Asymptotic Normalization Coefficients
The $^{12}\mathrm{C}(α,γ)^{16}\mathrm{O}$ reaction governs the carbon-to-oxygen ratio set during helium burning, shaping white-dwarf structure and Type~Ia supernova yields. At the astrophysical energy $E \approx 300~\mathrm{keV}$, the cross section is controlled by the subthreshold $1^{-}$ (7.12~MeV) and $2^{+}$ (6.92~MeV) states, whose contributions depend on their asymptotic normalization coefficients (ANCs) $C_{1}$ and $C_{2}$, respectively. We perform a Bayesian analysis of the $S_{E1}(30…

Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
Yibin Wang, Zhimin Li, Yuhang Zang, Yujie Zhou, Jiazi Bu, Chunyu Wang, Qinglin Lu, Cheng Jin, Jiaqi Wang
https://arxiv.org/abs/2508.20751

Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
Recent advancements highlight the importance of GRPO-based reinforcement learning methods and benchmarking in enhancing text-to-image (T2I) generation. However, current methods using pointwise reward models (RM) for scoring generated images are susceptible to reward hacking. We reveal that this happens when minimal score differences between images are amplified after normalization, creating illusory advantages that drive the model to over-optimize for trivial gains, ultimately destabilizing the…

Exploring Database Normalization Effects on SQL Generation
Ryosuke Kohita
https://arxiv.org/abs/2510.01989 https://arxiv.org/pdf/2510.01989

Exploring Database Normalization Effects on SQL Generation
Schema design, particularly normalization, is a critical yet often overlooked factor in natural language to SQL (NL2SQL) systems. Most prior research evaluates models on fixed schemas, overlooking the influence of design on performance. We present the first systematic study of schema normalization's impact, evaluating eight leading large language models on synthetic and real-world datasets with varied normalization levels. We construct controlled synthetic datasets with formal normalization (1N…

Unified theory of testing relevant hypothesis in functional time series
Leheng Cai, Qirui Hu
https://arxiv.org/abs/2508.18624 https://arxiv.org/pdf/2508.18…

Unified theory of testing relevant hypothesis in functional time series
In this paper, we present a general framework for testing relevant hypotheses in functional time series. Our unified approach covers one-sample, two-sample, and change point problems under contaminated observations with arbitrary sampling schemes. By employing B-spline estimators and the self-normalization technique, we propose nuisance-parameter-free testing procedures, obviating the need for additional procedures such as estimating long-run covariance or measurement-error variance functions. …

Augmentation Technologies and AI - An Ethical Design Futures Framework
Ann Hill Duin, Isabel Pedersen
https://arxiv.org/abs/2508.16615 https://arxiv.org/pd…

Augmentation Technologies and AI - An Ethical Design Futures Framework
Augmentation technologies, fueled by Artificial Intelligence (AI), are undergoing a process of adaptation and normalization geared to everyday users in various roles as practitioners, educators, and students. While new innovations, applications, and algorithms are developed as augmentation technology, Chapter 1 focuses on human subjects, contexts, and rhetorical strategies proposed for them by external actors. The chapter discusses core functions of technical and professional communication and …

A Unified Cortical Circuit Model with Divisive Normalization and Self-Excitation for Robust Representation and Memory Maintenance
Jie Su, Weiwei Wang, Zhaotian Gu, Dahui Wang, Tianyi Qian
https://arxiv.org/abs/2508.12702

A Unified Cortical Circuit Model with Divisive Normalization and Self-Excitation for Robust Representation and Memory Maintenance
Robust information representation and its persistent maintenance are fundamental for higher cognitive functions. Existing models employ distinct neural mechanisms to separately address noise-resistant processing or information maintenance, yet a unified framework integrating both operations remains elusive -- a critical gap in understanding cortical computation. Here, we introduce a recurrent neural circuit that combines divisive normalization with self-excitation to achieve both robust encodin…

Accepting Normalization via Markov Magmoids
Elena Di Lavore, Mario Rom\'an
https://arxiv.org/abs/2510.01131 https://arxiv.org/pdf/2510.01131

Accepting Normalization via Markov Magmoids
Normalization of probability distributions is not a distributive law. We introduce distributive sesquilaws to abstract normalization and, from their axioms, we derive some of its properties. In particular, normalized channels form a unital magmoid with an action of the category of subdistributions; its possibilistic analogue is the action from may-must relations into the category of relations. We argue that the magmoid of normalized channels is the stochastic analog of the category of relations.

Normalized Indexing for Ramification Subgroups
Stephen DeBacker, David Schwein, Cheng-Chiang Tsai
https://arxiv.org/abs/2509.14881 https://arxiv.org/pdf/25…

Normalized Indexing for Ramification Subgroups
This expository note introduces a normalization of the indexing of the lower and upper numbering ramification subgroups of local class field theory. We then look at how this normalization interacts with base change for Langlands parameters.

G\"odel Mirror: A Formal System For Contradiction-Driven Recursion
Jhet Chan
https://arxiv.org/abs/2509.16239 https://arxiv.org/pdf/2509.16239

Gödel Mirror: A Formal System For Contradiction-Driven Recursion
We introduce the Gödel Mirror, a formal system defined in Lean 4 that treats contradiction as a control signal for recursive structural evolution. Inspired by Gödelian self-reference, our system's operational semantics encode symbolic paradoxes as deterministic transitions. Unlike systems designed to guarantee normalization, the Gödel Mirror is a minimal and verifiable architecture that leverages a controlled, non-terminating loop as a productive feature. Our Lean 4 mechanization proves …

Online Adaptation via Dual-Stage Alignment and Self-Supervision for Fast-Calibration Brain-Computer Interfaces
Sheng-Bin Duan, Jian-Long Hao, Tian-Yu Xiang, Xiao-Hu Zhou, Mei-Jiang Gui, Xiao-Liang Xie, Shi-Qi Liu, Zeng-Guang Hou
https://arxiv.org/abs/2509.19403

Online Adaptation via Dual-Stage Alignment and Self-Supervision for Fast-Calibration Brain-Computer Interfaces
Individual differences in brain activity hinder the online application of electroencephalogram (EEG)-based brain computer interface (BCI) systems. To overcome this limitation, this study proposes an online adaptation algorithm for unseen subjects via dual-stage alignment and self-supervision. The alignment process begins by applying Euclidean alignment in the EEG data space and then updates batch normalization statistics in the representation space. Moreover, a self-supervised loss is designed …

Ever needed to duplicate a #keycloak realm.json, change a few values and re-import into the same keycloak ?
this is a Keycloak realm rekeying utility, safe UUID regeneration and alias normalization to avoid duplicate constraints during import https://

GitHub - rmdes/realm-duplicator-keycloak: Tools to rekey Keycloak realm JSON: regenerate IDs, normalize references, and eliminate collisions for seamless multi-realm imports.
Tools to rekey Keycloak realm JSON: regenerate IDs, normalize references, and eliminate collisions for seamless multi-realm imports. - rmdes/realm-duplicator-keycloak

Self-Normalization for CUSUM-based Change Detection in Locally Stationary Time Series
Florian Heinrichs
https://arxiv.org/abs/2509.07112 https://arxiv.org/…

Self-Normalization for CUSUM-based Change Detection in Locally Stationary Time Series
A novel self-normalization procedure for CUSUM-based change detection in the mean of a locally stationary time series is introduced. Classical self-normalization relies on the factorization of a constant long-run variance and a stochastic factor. In this case, the CUSUM statistic can be divided by another statistic proportional to the long-run variance, so that the latter cancels. Thereby, a tedious estimation of the long-run variance can be avoided. Under local stationarity, the partial sum pr…

A multi-object approach for studying exoplanet atmospheres using high-resolution spectrographs
Manjunath Bestha, Athira Unni, T. Sivarani, Dhanush S R, Lokesh Manickavasaham, Parvathy M, Devika K Divakar, Arun Surya
https://arxiv.org/abs/2509.18721

On the normalization of trigonometric and hyperbolic B-splines
Hendrik Speleers
https://arxiv.org/abs/2508.01817 https://arxiv.org/pdf/2508.01817

On the normalization of trigonometric and hyperbolic B-splines
Trigonometric and hyperbolic B-splines can be computed via recurrence relations analogous to the classical polynomial B-splines. However, in their original formulation, these two types of B-splines do not form a partition of unity and consequently do not admit the notion of control polygons with the convex hull property for design purposes. In this paper, we look into explicit expressions for their normalization and provide a recursive algorithm to compute the corresponding normalization weight…

DoSReMC: Domain Shift Resilient Mammography Classification using Batch Normalization Adaptation
U\u{g}urcan Aky\"uz, Deniz Katircioglu-\"Ozt\"urk, Emre K. S\"usl\"u, Burhan Kele\c{s}, Mete C. Kaya, Gamze Durhan, Meltem G. Akp{\i}nar, Figen B. Demirkaz{\i}k, G\"ozde B. Akar
https://arxiv.org/abs/2508.15452

DoSReMC: Domain Shift Resilient Mammography Classification using Batch Normalization Adaptation
Numerous deep learning-based solutions have been developed for the automatic recognition of breast cancer using mammography images. However, their performance often declines when applied to data from different domains, primarily due to domain shift - the variation in data distributions between source and target domains. This performance drop limits the safe and equitable deployment of AI in real-world clinical settings. In this study, we present DoSReMC (Domain Shift Resilient Mammography Class…

$\Delta L$ Normalization: Rethink Loss Aggregation in RLVR
Zhiyuan He, Xufang Luo, Yike Zhang, Yuqing Yang, Lili Qiu
https://arxiv.org/abs/2509.07558 https://

$ΔL$ Normalization: Rethink Loss Aggregation in RLVR
We propose $ΔL$ Normalization, a simple yet effective loss aggregation method tailored to the characteristic of dynamic generation lengths in Reinforcement Learning with Verifiable Rewards (RLVR). Recently, RLVR has demonstrated strong potential in improving the reasoning capabilities of large language models (LLMs), but a major challenge lies in the large variability of response lengths during training, which leads to high gradient variance and unstable optimization. Although previous methods…

Effective normalization of sub-Riemannian connections
Erlend Grong, Jan Slovak
https://arxiv.org/abs/2508.00108 https://arxiv.org/pdf/2508.00108

Effective normalization of sub-Riemannian connections
We give a new normalization condition for connections on sub-Riemannian manifolds with constant symbols. The condition is formulated in terms of Cartan connections and depends only on the first degree of homogeneity of the curvature. The essential part of our result is to show how a Cartan connection can be uniquely determined by a partial connection on the horizontal bundle. Viewed from the manifold, this observation is equivalent to the following claim: a compatible partial affine connection …

Nonlinear-linear duality for multipath quantum interference
Yi Zheng, Jin-Shi Xu, Chuan-Feng Li, Guang-Can Guo
https://arxiv.org/abs/2508.13855 https://arx…

Nonlinear-linear duality for multipath quantum interference
In quantum optics, the postselection amplitude of a nondegenerate parametric down-conversion (PDC) process is linked to a beamsplitter (BS) via partial time reversal, up to a normalization coefficient which is related to the parametric gain [Proc. Natl. Acad. Sci. USA 117, 33107 (2020)]. A special example where the gain is low is reminiscent of Klyshko's advanced-wave picture in quantum imaging. Here, we propose and prove a generalized duality for multiple spatial paths connecting a quantum non…

RLNVR: Reinforcement Learning from Non-Verified Real-World Rewards
Rohit Krishnan, Jon Evans
https://arxiv.org/abs/2508.12165 https://arxiv.org/pdf/2508.12…

RLNVR: Reinforcement Learning from Non-Verified Real-World Rewards
This paper introduces RLNVR (Reinforcement Learning from Non-Verified Rewards), a framework for training language models using noisy, real-world feedback signals without requiring explicit human verification. Traditional RLHF requires expensive, verified reward signals that are impractical in many real-world domains. RLNVR addresses this challenge through baseline normalization and semantic similarity-based reward transfer. We demonstrate RLNVR through Walter, a prototype system that optimizes …

from my link log —
Synthetic aperture radar autofocus and calibration.
https://hforsten.com/synthetic-aperture-radar-autofocus-and-calibration.html
saved 2025-10-11

Synthetic aperture radar autofocus and calibration
3D trajectory position error estimation autofocus, antenna pattern normalization, and polarimetric calibration for drone mounted SAR radar.

Training a Foundation Model for Materials on a Budget
Teddy Koker, Tess Smidt
https://arxiv.org/abs/2508.16067 https://arxiv.org/pdf/2508.16067

Training a Foundation Model for Materials on a Budget
Foundation models for materials modeling are advancing quickly, but their training remains expensive, often placing state-of-the-art methods out of reach for many research groups. We introduce Nequix, a compact E(3)-equivariant potential that pairs a simplified NequIP design with modern training practices, including equivariant root-mean-square layer normalization and the Muon optimizer, to retain accuracy while substantially reducing compute requirements. Built in JAX, Nequix has 700K paramete…

Mechanizing Synthetic Tait Computability in Istari
Runming Li, Yue Yao, Robert Harper
https://arxiv.org/abs/2509.11418 https://arxiv.org/pdf/2509.11418

Mechanizing Synthetic Tait Computability in Istari
Categorical gluing is a powerful technique for proving meta-theorems of type theories such as canonicity and normalization. Synthetic Tait Computability (STC) provides an abstract treatment of the complex gluing models by internalizing the gluing category into a modal dependent type theory with a phase distinction. This work presents a mechanization of STC in the Istari proof assistant. Istari is a Martin-Löf-style extensional type theory with equality reflection. Equality reflection eliminate…

Fibering of double twist knots via the adjoint hyperbolic torsion polynomial
Anh T. Tran
https://arxiv.org/abs/2508.14731 https://arxiv.org/pdf/2508.14731

Fibering of double twist knots via the adjoint hyperbolic torsion polynomial
For a hyperbolic knot $K$ in $S^3$, the adjoint hyperbolic torsion polynomial $\mathcal T^{\mathrm{Ad}}_K(t) \in \mathbb C[t^{\pm 1}]$ is defined as a normalization of the twisted Alexander polynomial of $K$ associated with the $\mathrm{SL}_3(\mathbb C)$-representation obtained by composing the holonomy representation of $K$ with the adjoint action of $\mathrm{SL}_2(\mathbb C)$ on its Lie algebra $\mathfrak{sl}_2(\mathbb C)$. In this paper we consider the adjoint hyperbolic torsion polynomial f…

On analytic functions related to Booth-lemniscate
Md Firoz Ali, Md Nurezzaman, Lokenath Thakur
https://arxiv.org/abs/2509.15534 https://arxiv.org/pdf/2509.…

On analytic functions related to Booth-lemniscate
For $0\le α\le 1 $, let $\mathcal{BS}(α)$ be the class of all analytic functions in the unit disk $\mathbb{D}:=\{~z\in\mathbb{C}:|z|<1\}$ with normalization $f(0)=0$ and $f'(0)=1$ that satisfy the subordinate relation $zf'(z)/f(z)-1\prec z/(1-αz^2)$ and $\mathcal{BK}(α)$ be the class of all functions $f$ for which $zf' \in \mathcal{BS}(α)$. In this article, we obtain a sharp estimate of the initial Taylor coefficients and logarithmic coefficients for functions in the classes $\ma…

A Dual Optimization View to Empirical Risk Minimization with f-Divergence Regularization
Francisco Daunas, I\~naki Esnaola, Samir M. Perlaza
https://arxiv.org/abs/2508.03314 htt…

A Dual Optimization View to Empirical Risk Minimization with f-Divergence Regularization
The dual formulation of empirical risk minimization with f-divergence regularization (ERM-fDR) is introduced. The solution of the dual optimization problem to the ERM-fDR is connected to the notion of normalization function introduced as an implicit function. This dual approach leverages the Legendre-Fenchel transform and the implicit function theorem to provide a nonlinear ODE expression to the normalization function. Furthermore, the nonlinear ODE expression and its properties provide a compu…

EffiFusion-GAN: Efficient Fusion Generative Adversarial Network for Speech Enhancement
Bin Wen, Tien-Ping Tan
https://arxiv.org/abs/2508.14525 https://arxi…

EffiFusion-GAN: Efficient Fusion Generative Adversarial Network for Speech Enhancement
We introduce EffiFusion-GAN (Efficient Fusion Generative Adversarial Network), a lightweight yet powerful model for speech enhancement. The model integrates depthwise separable convolutions within a multi-scale block to capture diverse acoustic features efficiently. An enhanced attention mechanism with dual normalization and residual refinement further improves training stability and convergence. Additionally, dynamic pruning is applied to reduce model size while maintaining performance, making…

Hubness Reduction with Dual Bank Sinkhorn Normalization for Cross-Modal Retrieval
Zhengxin Pan, Haishuai Wang, Fangyu Wu, Peng Zhang, Jiajun Bu
https://arxiv.org/abs/2508.02538 …

Hubness Reduction with Dual Bank Sinkhorn Normalization for Cross-Modal Retrieval
The past decade has witnessed rapid advancements in cross-modal retrieval, with significant progress made in accurately measuring the similarity between cross-modal pairs. However, the persistent hubness problem, a phenomenon where a small number of targets frequently appear as nearest neighbors to numerous queries, continues to hinder the precision of similarity measurements. Despite several proposed methods to reduce hubness, their underlying mechanisms remain poorly understood. To bridge thi…

This guy made a Synthetic Aperture Radar (i.e. a radar that gives you camera-like pictures) mounted on a drone. Scroll to the bottom for actual sample pictures and a movie. Lots of tech detail and open-source designs and software.
https://hforsten.com/synthetic-apertur

Local Density-Based Anomaly Score Normalization for Domain Generalization
Kevin Wilkinghoff, Haici Yang, Janek Ebbers, Fran\c{c}ois G. Germain, Gordon Wichern, Jonathan Le Roux
https://arxiv.org/abs/2509.10951

Local Density-Based Anomaly Score Normalization for Domain Generalization
State-of-the-art anomalous sound detection (ASD) systems in domain-shifted conditions rely on projecting audio signals into an embedding space and using distance-based outlier detection to compute anomaly scores. One of the major difficulties to overcome is the so-called domain mismatch between the anomaly score distributions of a source domain and a target domain that differ acoustically and in terms of the amount of training data provided. A decision threshold that is optimal for one domain m…

Robust Symbolic Reasoning for Visual Narratives via Hierarchical and Semantically Normalized Knowledge Graphs
Yi-Chun Chen
https://arxiv.org/abs/2508.14941 https://

Robust Symbolic Reasoning for Visual Narratives via Hierarchical and Semantically Normalized Knowledge Graphs
Understanding visual narratives such as comics requires structured representations that capture events, characters, and their relations across multiple levels of story organization. However, symbolic narrative graphs often suffer from inconsistency and redundancy, where similar actions or events are labeled differently across annotations or contexts. Such variance limits the effectiveness of reasoning and generalization. This paper introduces a semantic normalization framework for hierarchica…

Mathematical proof concerning the additivity problem of nonlinear normalized citation counts
Xing Wang, Zhihui Zhang
https://arxiv.org/abs/2508.14595 https://

Mathematical proof concerning the additivity problem of nonlinear normalized citation counts
The issue of whether nonlinear normalized citation counts can be added is critically important in scientometrics because it touches upon the theoretical foundation of underlying computation in the field. In this paper, we provide rigorous mathematical proofs for the key theorems underlying this fundamental issue. Based on these proofs, we ultimately arrive at the following conclusion: a nonlinear normalization method for citation counts must be a non-equidistant transformation; consequently, th…

Domain Adaptation via Feature Refinement
Savvas Karatsiolis, Andreas Kamilaris
https://arxiv.org/abs/2508.16124 https://arxiv.org/pdf/2508.16124

Domain Adaptation via Feature Refinement
We propose Domain Adaptation via Feature Refinement (DAFR2), a simple yet effective framework for unsupervised domain adaptation under distribution shift. The proposed method synergistically combines three key components: adaptation of Batch Normalization statistics using unlabeled target data, feature distillation from a source-trained model and hypothesis transfer. By aligning feature distributions at the statistical and representational levels, DAFR2 produces robust and domain-invariant feat…

Comparing Normalization Methods for Portfolio Optimization with Reinforcement Learning
Caio de Souza Barbosa Costa, Anna Helena Reali Costa
https://arxiv.org/abs/2508.03910 http…

On the Benefits of Weight Normalization for Overparameterized Matrix Sensing
Yudong Wei, Liang Zhang, Bingcong Li, Niao He
https://arxiv.org/abs/2510.01175 https://

On the Benefits of Weight Normalization for Overparameterized Matrix Sensing
While normalization techniques are widely used in deep learning, their theoretical understanding remains relatively limited. In this work, we establish the benefits of (generalized) weight normalization (WN) applied to the overparameterized matrix sensing problem. We prove that WN with Riemannian optimization achieves linear convergence, yielding an exponential speedup over standard methods that do not use WN. Our analysis further demonstrates that both iteration and sample complexity improve p…

Principles of Safe AI Companions for Youth: Parent and Expert Perspectives
Yaman Yu, Mohi, Aishi Debroy, Xin Cao, Karen Rudolph, Yang Wang
https://arxiv.org/abs/2510.11185 http…

Principles of Safe AI Companions for Youth: Parent and Expert Perspectives
AI companions are increasingly popular among teenagers, yet current platforms lack safeguards to address developmental risks and harmful normalization. Despite growing concerns, little is known about how parents and developmental psychology experts assess these interactions or what protections they consider necessary. We conducted 26 semi structured interviews with parents and experts, who reviewed real world youth GenAI companion conversation snippets. We found that stakeholders assessed risks…

Asymptotic behavior of the extremal position in a multi-type branching random walk with heavy-tailed displacements
Krzysztof Kowalski
https://arxiv.org/abs/2509.14808 https://…

Asymptotic behavior of the extremal position in a multi-type branching random walk with heavy-tailed displacements
We consider a multi-type branching random walk with displacements that have either regularly varying or semi-exponential tails. We investigate the asymptotic behavior of the rightmost particle in irreducible and reducible regimes and identify the correct normalization for different settings.

A New Normalization Form for Limited Distinct Attributes
Niko S. Snell, Rayen C. Lee
https://arxiv.org/abs/2510.02865 https://arxiv.org/pdf/2510.02865

A New Normalization Form for Limited Distinct Attributes
In modern databases, the practice of data normalization continues to be important in improving data integrity, minimizing redundancies, and eliminating anomalies. However, since its inception and consequent improvements, there have been no attempts to document a method which constrains the values of attributes capable of only possessing a limited quantity of values. These non-limited distinct attributes pose a problem throughout many relational databases as they have the potential to cause data…

Accelerated stochastic first-order method for convex optimization under heavy-tailed noise
Chuan He, Zhaosong Lu
https://arxiv.org/abs/2510.11676 https://a…

Accelerated stochastic first-order method for convex optimization under heavy-tailed noise
We study convex composite optimization problems, where the objective function is given by the sum of a prox-friendly function and a convex function whose subgradients are estimated under heavy-tailed noise. Existing work often employs gradient clipping or normalization techniques in stochastic first-order methods to address heavy-tailed noise. In this paper, we demonstrate that a vanilla stochastic algorithm -- without additional modifications such as clipping or normalization -- can achieve op…

Normalized Derivations for Milnor's Primitive Operations on the Dickson Algebra and Applications
Dang Vo Phuc
https://arxiv.org/abs/2509.08861 https://…

Normalized Derivations for Milnor's Primitive Operations on the Dickson Algebra and Applications
Our work investigates the action of primitive Milnor operations $St^{Δ_i}$ on the Dickson algebra $D_n$ over $\mathbb{F}_p$, building upon a foundational formula by Nguyen Sum [3]. Our central contribution is the introduction of a normalized operator, $δ_i$, by factoring out the ubiquitous invariant $Q_{n, 0}$. This normalization transforms $St^{Δ_i}$ into a true derivation on the localized Dickson algebra, thereby establishing an elegant differential framework. This framework yields two new…

Adaptive Stain Normalization for Cross-Domain Medical Histology
Tianyue Xu, Yanlin Wu, Abhai K. Tripathi, Matthew M. Ippolito, Benjamin D. Haeffele
https://arxiv.org/abs/2510.06592

Adaptive Stain Normalization for Cross-Domain Medical Histology
Deep learning advances have revolutionized automated digital pathology analysis. However, differences in staining protocols and imaging conditions can introduce significant color variability. In deep learning, such color inconsistency often reduces performance when deploying models on data acquired under different conditions from the training data, a challenge known as domain shift. Many existing methods attempt to address this problem via color normalization but suffer from several notable dra…

Normalization-equivariant Diffusion Models: Learning Posterior Samplers From Noisy And Partial Measurements
Brett Levac, Jon Tamir, Marcelo Pereyra, Julian Tachella
https://arxiv.org/abs/2510.11964

Normalization-equivariant Diffusion Models: Learning Posterior Samplers From Noisy And Partial Measurements
Diffusion models (DMs) have rapidly emerged as a powerful framework for image generation and restoration. However, existing DMs are primarily trained in a supervised manner by using a large corpus of clean images. This reliance on clean data poses fundamental challenges in many real-world scenarios, where acquiring noise-free data is hard or infeasible, and only noisy and potentially incomplete measurements are available. While some methods can train DMs using noisy data, they are generally eff…

HELIOS -- Hybrid Evaluation of Lifecycle and Impact of Outstanding Science v-2.0
Eduardo Garbayo
https://arxiv.org/abs/2508.21329 https://arxiv.org/pdf/250…

HELIOS -- Hybrid Evaluation of Lifecycle and Impact of Outstanding Science v-2.0
This paper presents a substantial enhancement of the HELIOS (Hybrid Evaluation of Lifecycle and Impact of Outstanding Science) model, transforming it from a static assessment tool into a dynamic and predictive framework for technological maturity. It addresses the limitations of the original model, which relied on linear normalization and fixed weights. Key modifications include the adoption of non-linear normalization functions (sigmoids), the integration of S-curve growth models for forecasti…

T-Detect: Tail-Aware Statistical Normalization for Robust Detection of Adversarial Machine-Generated Text
Alva West, Luodan Zhang, Liuliu Zhang, Minjun Zhu, Yixuan Weng, Yue Zhang
https://arxiv.org/abs/2507.23577

T-Detect: Tail-Aware Statistical Normalization for Robust Detection of Adversarial Machine-Generated Text
The proliferation of sophisticated text generation models necessitates the development of robust detection methods capable of identifying machine-generated content, particularly text designed to evade detection through adversarial perturbations. Existing zero-shot detectors often rely on statistical measures that implicitly assume Gaussian distributions, a premise that falters when confronted with the heavy-tailed statistical artifacts characteristic of adversarial or non-native English texts. …

Thermodynamics of the Reissner-Nordstr\"om black hole with quintessence matter on the EGUP framework
Hao Chen, Bekir Can L\"utf\"uo\u{g}lu, Hassan Hassanabadi, Zheng-Wen Long
https://arxiv.org/abs/2508.15467

Thermodynamics of the Reissner-Nordström black hole with quintessence matter on the EGUP framework
In this paper, we investigate the quantum correction on thermodynamics of the Reissner-Nordström black hole in the presence of the quintessence matter associated with dark energy. To this end, the modified Hawking temperature, heat capacity, and entropy functions of the black hole are derived. { Investigation reveals that the modified uncertainty principles and normalization factor $α$ restrict the lower bound value of horizon radius to affect the Hawking temperature and the parameter $η_{0}…

The AURORA Survey: Ionizing Photon Production Efficiency with Minimal Nebular Dust Attenuation Systematics
Anthony J. Pahl, Alice Shapley, Naveen A. Reddy, Ryan Sanders, Michael W. Topping, Danielle A. Berg, Callum T. Donnan, James S. Dunlop, Richard S. Ellis, N. M. F\"orster Schreiber, K. Glazebrook, Derek J. McLeod, Max Pettini, Daniel Schaerer
https://

The AURORA Survey: Ionizing Photon Production Efficiency with Minimal Nebular Dust Attenuation Systematics
We present ionizing photon production efficiencies ($ξ_{\rm ion}$) for 63 z=1.5-6.9 star-forming galaxies using precise nebular dust attenuation corrections from the JWST/AURORA survey. A subset of objects within AURORA have individually-determined nebular dust attenuation curves, which vary significantly in shape and normalization, resulting in reduced systematic uncertainty when constraining the total attenuation of H$α$ luminosity, and thus the intrinsic ionizing output within our sample. …

The Structure of Extremal Bad Science Matrices
Shridhar Sinha
https://arxiv.org/abs/2509.10580 https://arxiv.org/pdf/2509.10580

The Structure of Extremal Bad Science Matrices
We study the 'bad science matrix problem': among all matrices $A\in\mathbb{R}^{n\times n}$ whose rows have unit $\ell_2$-norm, determine the maximum of $β(A)=\frac{1}{2^n}\sum_{x\in\{\pm1\}^n}\|Ax\|_\infty$. Steinerberger [1] (arXiv:2402.03205) showed that the optimal asymptotic rate is $(1+o(1))\sqrt{2\log n}$, and that this rate is attained with high probability by matrices with i.i.d. $\pm1$ entries after normalization. More recent explicit constructions [2] (arXiv:2408.00933) ach…

DeepWKB: Learning WKB Expansions of Invariant Distributions for Stochastic Systems
Yao Li, Yicheng Liu, Shirou Wang
https://arxiv.org/abs/2508.09529 https://

DeepWKB: Learning WKB Expansions of Invariant Distributions for Stochastic Systems
This paper introduces a novel deep learning method, called DeepWKB, for estimating the invariant distribution of randomly perturbed systems via its Wentzel-Kramers-Brillouin (WKB) approximation $u_ε(x) = Q(ε)^{-1} Z_ε(x) \exp\{-V(x)/ε\}$, where $V$ is known as the quasi-potential, $ε$ denotes the noise strength, and $Q(ε)$ is the normalization factor. By utilizing both Monte Carlo data and the partial differential equations satisfied by $V$ and $Z_ε$, the DeepWKB method computes $V$ and …

Validation of Various Normalization Methods for Brain Tumor Segmentation: Can Federated Learning Overcome This Heterogeneity?
Jan Fiszer, Dominika Ciupek, Maciej Malawski
https://arxiv.org/abs/2510.07126

Validation of Various Normalization Methods for Brain Tumor Segmentation: Can Federated Learning Overcome This Heterogeneity?
Deep learning (DL) has been increasingly applied in medical imaging, however, it requires large amounts of data, which raises many challenges related to data privacy, storage, and transfer. Federated learning (FL) is a training paradigm that overcomes these issues, though its effectiveness may be reduced when dealing with non-independent and identically distributed (non-IID) data. This study simulates non-IID conditions by applying different MRI intensity normalization techniques to separate da…

Crosslisted article(s) found for cs.IT. https://arxiv.org/list/cs.IT/new
[1/1]:
- Insights from Gradient Dynamics: Gradient Autoscaled Normalization
Vincent-Daniel Yun

On the Normalization of Confusion Matrices: Methods and Geometric Interpretations
Johan Erbani, Pierre-Edouard Portier, Elod Egyed-Zsigmond, Sonia Ben Mokhtar, Diana Nurbakova
https://arxiv.org/abs/2509.04959

On the Normalization of Confusion Matrices: Methods and Geometric Interpretations
The confusion matrix is a standard tool for evaluating classifiers by providing insights into class-level errors. In heterogeneous settings, its values are shaped by two main factors: class similarity -- how easily the model confuses two classes -- and distribution bias, arising from skewed distributions in the training and test sets. However, confusion matrix values reflect a mix of both factors, making it difficult to disentangle their individual contributions. To address this, we introduce b…

Replaced article(s) found for cs.LO. https://arxiv.org/list/cs.LO/new
[1/1]:
- Strong normalization through idempotent intersection types: a new syntactical approach
Pablo Barenbaum, Simona Ronchi Della Rocca, Cristian Sottile

Some Structures arising from the Farey Fractal
Shai Haran
https://arxiv.org/abs/2509.10959 https://arxiv.org/pdf/2509.10959

Some Structures arising from the Farey Fractal
This work explores new arithmetic and combinatorial structures arising from the interplay between Farey-type graphs, Fibonacci expansions, and operadic constructions. We introduce Fibonadic numbers, defined as an inverse limit under the Zeckendorf shift, equipped with a metric, order, and commutative rig structure. A normalization lemma provides canonical representatives, while quotients of the non-zero Fibonadic numbers under shifts and it's fundamental domain covering the circle via phi-value…

Finding a Maximal Determinant Principal Submatrix via Hadamard's Inequality and Conic Relaxations
Hao Hu, Stefan Sremac, Hugo J. Woerdeman, Henry Wolkowicz
https://arxiv.org/abs/2508.15608

Finding a Maximal Determinant Principal Submatrix via Hadamard's Inequality and Conic Relaxations
An important yet challenging problem in numerical linear algebra is finding a principal submatrix with the maximum determinant. In this paper, we examine several exact and approximate approaches to this problem. We first propose an upper bound based on Hadamard's inequality, along with a projection scheme based on the Gram-Schmidt process without normalization. This scheme yields a highly effective exact algorithm for solving small- to medium-scale instances. We then study a linear programming …

A Scalable Formula for the Moments of a Family of Self-Normalized Statistics
Haolin Zou, Heyuan Yao, Victor de la Pe\~na
https://arxiv.org/abs/2509.14428 https://

A Scalable Formula for the Moments of a Family of Self-Normalized Statistics
Following the student t-statistic, normalization has been a widely used method in statistic and other disciplines including economics, ecology and machine learning. We focus on statistics taking the form of a ratio over (some power of) the sample mean, the probabilistic features of which remain unknown. We develop a unified formula for the moments of these self-normalized statistics with non-negative observations, yielding closed-form expressions for several important cases. Moreover, the compl…

Genome-Factory: An Integrated Library for Tuning, Deploying, and Interpreting Genomic Models
Weimin Wu, Xuefeng Song, Yibo Wen, Qinjie Lin, Zhihan Zhou, Jerry Yao-Chieh Hu, Zhong Wang, Han Liu
https://arxiv.org/abs/2509.12266

Genome-Factory: An Integrated Library for Tuning, Deploying, and Interpreting Genomic Models
We introduce Genome-Factory, an integrated Python library for tuning, deploying, and interpreting genomic models. Our core contribution is to simplify and unify the workflow for genomic model development: data collection, model tuning, inference, benchmarking, and interpretability. For data collection, Genome-Factory offers an automated pipeline to download genomic sequences and preprocess them. It also includes quality control, such as GC content normalization. For model tuning, Genome-Factory…

Scaling properties of nuclear parton distributions in short-range-correlation motivated two-component parametrization
Petja Paakkinen
https://arxiv.org/abs/2510.00252 https://…

Scaling properties of nuclear parton distributions in short-range-correlation motivated two-component parametrization
We provide some critical remarks on the recently proposed two-component parametrization of nuclear parton distribution functions, which was motivated by the apparent correlation between the nuclear modifications of structure functions and nucleon-nucleon short-range correlation phenomena. This parametrization, we show, is invariant under a rescaling transformation of the involved abundance coefficients, which means that the global normalization of these coefficients cannot be meaningfully deter…

Machine Learning Prediction of Charged Defect Formation Energies from Crystal Structures
Shin Kiyohara, Chisa Shibui, Soungmin Bae, Yu Kumagai
https://arxiv.org/abs/2510.00513 h…

Machine Learning Prediction of Charged Defect Formation Energies from Crystal Structures
Recent advances in materials informatics have expanded the number of synthesizable materials. However, screening promising candidates, such as semiconductors, based on defect properties remains challenging. This is primarily due to the lack of a general framework for predicting defect formation energies in multiple charge states from structural data. In this Letter, we present a protocol, namely data normalization, Fermi level alignment, and treatment of perturbed host states, and validate it b…

Tokenization Disparities as Infrastructure Bias: How Subword Systems Create Inequities in LLM Access and Efficiency
Hailay Kidu Teklehaymanot, Wolfgang Nejdl
https://arxiv.org/abs/2510.12389

Tokenization Disparities as Infrastructure Bias: How Subword Systems Create Inequities in LLM Access and Efficiency
Tokenization disparities pose a significant barrier to achieving equitable access to artificial intelligence across linguistically diverse populations. This study conducts a large-scale cross-linguistic evaluation of tokenization efficiency in over 200 languages to systematically quantify computational inequities in large language models (LLMs). Using a standardized experimental framework, we applied consistent preprocessing and normalization protocols, followed by uniform tokenization through …

UNISELF: A Unified Network with Instance Normalization and Self-Ensembled Lesion Fusion for Multiple Sclerosis Lesion Segmentation
Jinwei Zhang, Lianrui Zuo, Blake E. Dewey, Samuel W. Remedios, Yihao Liu, Savannah P. Hays, Dzung L. Pham, Ellen M. Mowry, Scott D. Newsome, Peter A. Calabresi, Aaron Carass, Jerry L. Prince
https://arxiv.org/a…

UNISELF: A Unified Network with Instance Normalization and Self-Ensembled Lesion Fusion for Multiple Sclerosis Lesion Segmentation
Automated segmentation of multiple sclerosis (MS) lesions using multicontrast magnetic resonance (MR) images improves efficiency and reproducibility compared to manual delineation, with deep learning (DL) methods achieving state-of-the-art performance. However, these DL-based methods have yet to simultaneously optimize in-domain accuracy and out-of-domain generalization when trained on a single source with limited data, or their performance has been unsatisfactory. To fill this gap, we propose …

A new application of the Fox-Wright functions: the coherent states formalism
Dusan Popov
https://arxiv.org/abs/2510.04874 https://arxiv.org/pdf/2510.04874

A new application of the Fox-Wright functions: the coherent states formalism
In this paper we extend the applicability of Fox-Wright functions beyond mathematics, specifically in quantum physics. We focused our attention on a new application, on the connection between the Fox-Wright functions and the generalized coherent states formalism. We constructed the generalized coherent states in the Barut-Girardello manner, in which the Fox-Wright functions play the role of normalization functions, and we demonstrated that the Fox-Wright coherent states satisfy all general cond…

Quantum entropy and cardinality of the rational numbers
Kaushik Ghosh
https://arxiv.org/abs/2509.12972 https://arxiv.org/pdf/2509.12972

Quantum entropy and cardinality of the rational numbers
We compare two methods for evaluating cardinality of the Cartesian product $N \times N$ of the set of natural numbers $N$. The first is used to explain the thermodynamics of black body radiation by using convergent functions on $N \times N$. Cardinality of $N \times N$ enters through the partition function that acts as the normalization constant of a probability distribution over $N \times N$. Here, $N \times N$ is given a greater cardinality than $N$. The expression of the partition function a…

Probing the energy-dependent temporal nature of MAXI J1803-298 with AstroSat and NICER
Arbind Pradhan, Akash Garg, Ranjeev Misra, Biplob Sarkar
https://arxiv.org/abs/2508.07843 …

Probing the energy-dependent temporal nature of MAXI J1803-298 with AstroSat and NICER
We performed the spectral and temporal analysis of MAXI J1803-298 using AstroSat/LAXPC and NICER observations taken in May 2021 during the initial phase of the outburst. We found that the source traverses through the hard, intermediate, and soft spectral states during the outburst. The spectrum in all states can be described using soft emissions from the thermal disk and hard emissions from the coronal regions. The variation in the inner disk temperature and normalization of the disk indicates …

From Autoencoders to CycleGAN: Robust Unpaired Face Manipulation via Adversarial Learning
Collin Guo
https://arxiv.org/abs/2509.12176 https://arxiv.org/pdf…

From Autoencoders to CycleGAN: Robust Unpaired Face Manipulation via Adversarial Learning
Human face synthesis and manipulation are increasingly important in entertainment and AI, with a growing demand for highly realistic, identity-preserving images even when only unpaired, unaligned datasets are available. We study unpaired face manipulation via adversarial learning, moving from autoencoder baselines to a robust, guided CycleGAN framework. While autoencoders capture coarse identity, they often miss fine details. Our approach integrates spectral normalization for stable training, i…

Crosslisted article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[1/2]:
- Limitations of Normalization in Attention Mechanism
Timur Mudarisov, Mikhail Burtsev, Tatiana Petrova, Radu State

Comparing Normalization Methods for Portfolio Optimization with Reinforcement Learning
Caio de Souza Barbosa Costa, Anna Helena Reali Costa
https://arxiv.org/abs/2508.03910 http…

13 Billion Years of MgII Absorber Evolution
Christopher W. Churchill (New Mexico State University), Asif Abbas (New Mexico State University), Glenn G. Kapcrzak (Swinburne University of Technology), Nikole M. Nielsen (Swinburne University of Technology, University of Oklahoma)
https://arxiv.org/abs/2510.01430

13 Billion Years of MgII Absorber Evolution
Applying "apportioned integrals," we use dN/dX measurements to determine the MgII absorber equivalent width distribution function for Wr > 0.03 [angstroms] and 0 < z < 7. Adopting a Schechter distribution, f(z,W)dW = Phi* (W/W*)^alpha e^{-W/W*} dW/W*, we present the normalization, Phi*(z), the characteristic equivalent width, W*(z), and the weak-end slope, alpha(z), as smooth functions of redshift. Measurements of dN/dX are robust for z < 4 but less so at z > 4 for weaker absorbers (Wr < 0.3 [a…

Non-commutative multiple bi-orthogonal polynomials: formal approach and integrability
Adam Doliwa
https://arxiv.org/abs/2510.02207 https://arxiv.org/pdf/25…

Non-commutative multiple bi-orthogonal polynomials: formal approach and integrability
We define the non-commutative multiple bi-orthogonal polynomial systems, which simultaneously generalize the concepts of multiple orthogonality, matrix orthogonal polynomials and of the bi-orthogonality. We present quasideterminantal expressions for such polynomial systems in terms of formal bi-moments. The normalization functions for such monic polynomials satisfy the non-commutative Hirota equations, while the polynomials provide solution of the corresponding linear system. This shows, in par…

MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data
Antoine Labatie, Michael Vaccaro, Nina Lardiere, Anatol Garioud, Nicolas Gonthier
https://arxiv.org/abs/2508.10894

MAESTRO: Masked AutoEncoders for Multimodal, Multitemporal, and Multispectral Earth Observation Data
Self-supervised learning holds great promise for remote sensing, but standard self-supervised methods must be adapted to the unique characteristics of Earth observation data. We take a step in this direction by conducting a comprehensive benchmark of fusion strategies and reconstruction target normalization schemes for multimodal, multitemporal, and multispectral Earth observation data. Based on our findings, we propose MAESTRO, a novel adaptation of the Masked Autoencoder, featuring optimized …

Studying $\textrm{QED}_3$ with radial quantization on the lattice -- I. Free limit
Peter A. Boyle, Richard C. Brower, George T. Fleming, Emanuel Katz, Nobuyuki Matsumoto, Rohan Misra
https://arxiv.org/abs/2510.03085

Studying $\textrm{QED}_3$ with radial quantization on the lattice -- I. Free limit
To investigate the three-dimensional quantum electrodynamics in the radial quantization on the lattice, the lattice action is constructed and the free limit is studied on $S^2 \times \mathbb{R}$. With the overlap fermion, it is numerically verified that the important symmetries of the theory can be realized on the lattice. The analytic correlators are derived and compared to the lattice results, which agree including the overall normalization. The $O(a^2)$-scaling is confirmed toward the analyt…

On convergence of normal form transformations
Valery G. Romanovski, Sebastian Walcher
https://arxiv.org/abs/2510.00925 https://arxiv.org/pdf/2510.00925

On convergence of normal form transformations
We discuss various aspects concerning transformations of local analytic, or formal, vector fields to Poincare-Dulac normal form, and the convergence of such transformations. We first review A.D. Bruno's approach to formal normalization, as well as convergence results in presence of certain (simplified) versions of Bruno's ``Condition A'', and along the way we also identify a large class of systems that satisfy Bruno's diophantine ``Condition omega''. We retrace the proof steps in Bruno's work, …

Replaced article(s) found for q-fin.ST. https://arxiv.org/list/q-fin.ST/new
[1/1]:
- Mitigating Distribution Shift in Stock Price Data via Return-Volatility Normalization for Accurat...
Hyunwoo Lee, Jihyeong Jeon, Jaemin Hong, U Kang

Lyapunov exponents and phase transition of charged Ads black hole in quintessence
Xiaobo Guo, Rui Yang, Yizhi Liang, Jun Tao
https://arxiv.org/abs/2508.03519 https://

Lyapunov exponents and phase transition of charged Ads black hole in quintessence
This study investigates the phase transitions of RN-AdS black holes immersed in a quintessence field, employing Lyapunov exponents as a dynamical probe to characterize the thermodynamics of black hole. Incorporating quintessence dark energy into the RN-AdS framework, we find that the Lyapunov exponents for null and timelike geodesics display diminished chaotic behavior with increasing normalization factor of the quintessence field. This feature introduces a finite cutoff to the Lyapunov exponen…

Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation
Vaibhav Srivastav, Steven Zheng, Eric Bezzam, Eustache Le Bihan, Nithin Koluguri, Piotr \.Zelasko, Somshubra Majumdar, Adel Moumen, Sanchit Gandhi
https://arxiv.org/abs/2510.06961

Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation
Despite rapid progress, ASR evaluation remains saturated with short-form English, and efficiency is rarely reported. We present the Open ASR Leaderboard, a fully reproducible benchmark and interactive leaderboard comparing 60+ open-source and proprietary systems across 11 datasets, including dedicated multilingual and long-form tracks. We standardize text normalization and report both word error rate (WER) and inverse real-time factor (RTFx), enabling fair accuracy-efficiency comparisons. For E…

Physics-Informed Neural Networks for Nonlocal Beam Eigenvalue Problems
Baidehi Das, Raffaele Barretta, Marko \v{C}ana{\dj}ija
https://arxiv.org/abs/2509.04321 https://

Physics-Informed Neural Networks for Nonlocal Beam Eigenvalue Problems
The present study investigates the dynamics of nonlocal beams by establishing a consistent stress-driven integral elastic using the Physics-Informed Neural Network (PINN) approach. Specifically, a PINN is developed to compute the first eigenfunction and eigenvalue arising from the underlying sixth-order ordinary differential equation. The PINN is based on a feedforward neural network, with a loss function composed of terms from the differential equation, the normalization condition, and both bo…

Use ADAS Data to Predict Near-Miss Events: A Group-Based Zero-Inflated Poisson Approach
Xinbo Zhang, Montserrat Guillen, Lishuai Li, Xin Li, Youhua Frank Chen
https://arxiv.org/abs/2509.02614

Use ADAS Data to Predict Near-Miss Events: A Group-Based Zero-Inflated Poisson Approach
Driving behavior big data leverages multi-sensor telematics to understand how people drive and powers applications such as risk evaluation, insurance pricing, and targeted intervention. Usage-based insurance (UBI) built on these data has become mainstream. Telematics-captured near-miss events (NMEs) provide a timely alternative to claim-based risk, but weekly NMEs are sparse, highly zero-inflated, and behaviorally heterogeneous even after exposure normalization. Analyzing multi-sensor telematic…

Crosslisted article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[1/1]:
- Database Normalization via Dual-LLM Self-Refinement
Eunjae Jo, Nakyung Lee, Gyuyeong Kim

LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation
Jianxiong Gao, Zhaoxi Chen, Xian Liu, Jianfeng Feng, Chenyang Si, Yanwei Fu, Yu Qiao, Ziwei Liu
https://arxiv.org/abs/2508.03694

LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation
Controllable ultra-long video generation is a fundamental yet challenging task. Although existing methods are effective for short clips, they struggle to scale due to issues such as temporal inconsistency and visual degradation. In this paper, we initially investigate and identify three key factors: separate noise initialization, independent control signal normalization, and the limitations of single-modality guidance. To address these issues, we propose LongVie, an end-to-end autoregressive fr…

Noncoincidence $f(Q)$-Cosmology with Dark Matter Coupled to Gravity
A. Abebe, P. S. Apostolopoulos, A. Giacomini, G. Leon, F. Moncada, A. Paliathanasis
https://arxiv.org/abs/2510.00535

Noncoincidence $f(Q)$-Cosmology with Dark Matter Coupled to Gravity
We investigate FLRW cosmology in the framework of symmetric teleparallel $f(Q)$ gravity with a nonminimal coupling between dark matter and the gravitational field. In the noncoincidence gauge, the field equations admit an equivalent multi-scalar field representation, which we investigate the phase-space using the Hubble-normalization approach. We classify all stationary points for arbitrary function $f(Q)$ and we discuss the physical properties of the asymptotic solutions. For the power-law the…

Deep Learning-Based Pneumonia Detection from Chest X-ray Images: A CNN Approach with Performance Analysis and Clinical Implications
P K Dutta, Anushri Chowdhury, Anouska Bhattacharyya, Shakya Chakraborty, Sujatra Dey
https://arxiv.org/abs/2510.00035

Deep Learning-Based Pneumonia Detection from Chest X-ray Images: A CNN Approach with Performance Analysis and Clinical Implications
Deep learning integration into medical imaging systems has transformed disease detection and diagnosis processes with a focus on pneumonia identification. The study introduces an intricate deep learning system using Convolutional Neural Networks for automated pneumonia detection from chest Xray images which boosts diagnostic precision and speed. The proposed CNN architecture integrates sophisticated methods including separable convolutions along with batch normalization and dropout regularizati…