Tootfinder

RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes
Fang Li, Hao Zhang, Narendra Ahuja
https://arxiv.org/abs/2509.15123 https://arxiv.org/p…

RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes
Although COLMAP has long remained the predominant method for camera parameter optimization in static scenes, it is constrained by its lengthy runtime and reliance on ground truth (GT) motion masks for application to dynamic scenes. Many efforts attempted to improve it by incorporating more priors as supervision such as GT focal length, motion masks, 3D point clouds, camera poses, and metric depth, which, however, are typically unavailable in casually captured RGB videos. In this paper, we propo…

A Comprehensive Framework for F-statistic-based Parameter Estimation of Binary Black Hole Signals
Hai-Tian Wang
https://arxiv.org/abs/2509.14849 https://ar…

A Comprehensive Framework for F-statistic-based Parameter Estimation of Binary Black Hole Signals
We present a comprehensive investigation of the F-statistic method for parameter estimation of gravitational wave (GW) signals from binary black hole mergers. By analytically maximizing the likelihood over the luminosity distance and polarization angle, this approach reduces the dimensionality of the parameter space to enhance computational efficiency. We also introduce a novel formulation for calculating the Bayes factor for the F-statistic, enabling a quantitative assessment of its performanc…

TITAN: A Trajectory-Informed Technique for Adaptive Parameter Freezing in Large-Scale VQE
Yifeng Peng, Xinyi Li, Samuel Yen-Chi Chen, Kaining Zhang, Zhiding Liang, Ying Wang, Yuxuan Du
https://arxiv.org/abs/2509.15193

TITAN: A Trajectory-Informed Technique for Adaptive Parameter Freezing in Large-Scale VQE
Variational quantum Eigensolver (VQE) is a leading candidate for harnessing quantum computers to advance quantum chemistry and materials simulations, yet its training efficiency deteriorates rapidly for large Hamiltonians. Two issues underlie this bottleneck: (i) the no-cloning theorem imposes a linear growth in circuit evaluations with the number of parameters per gradient step; and (ii) deeper circuits encounter barren plateaus (BPs), leading to exponentially increasing measurement overheads.…

FURINA: Free from Unmergeable Router via LINear Aggregation of mixed experts
Jiayi Han, Liang Du, Yinda Chen, Xiao Kang, Weiyang Ding, Donghong Han
https://arxiv.org/abs/2509.14900

FURINA: Free from Unmergeable Router via LINear Aggregation of mixed experts
The Mixture of Experts (MoE) paradigm has been successfully integrated into Low-Rank Adaptation (LoRA) for parameter-efficient fine-tuning (PEFT), delivering performance gains with minimal parameter overhead. However, a key limitation of existing MoE-LoRA methods is their reliance on a discrete router, which prevents the integration of the MoE components into the backbone model. To overcome this, we propose FURINA, a novel Free from Unmergeable Router framework based on the LINear Aggregation o…

CLAIP-Emo: Parameter-Efficient Adaptation of Language-supervised models for In-the-Wild Audiovisual Emotion Recognition
Yin Chen, Jia Li, Jinpeng Hu, Zhenzhen Hu, Richang Hong
https://arxiv.org/abs/2509.14527

CLAIP-Emo: Parameter-Efficient Adaptation of Language-supervised models for In-the-Wild Audiovisual Emotion Recognition
Audiovisual emotion recognition (AVER) in the wild is still hindered by pose variation, occlusion, and background noise. Prevailing methods primarily rely on large-scale domain-specific pre-training, which is costly and often mismatched to real-world affective data. To address this, we present CLAIP-Emo, a modular framework that reframes in-the-wild AVER as a parameter-efficient adaptation of language-supervised foundation models (CLIP/CLAP). Specifically, it (i) preserves language-supervised p…

On simultaneously preperiodic points for one-parameter families of polynomials in characteristic $p$
Jungin Lee, GyeongHyeon Nam
https://arxiv.org/abs/2509.15079 https://…

On simultaneously preperiodic points for one-parameter families of polynomials in characteristic $p$
For a field $L$ of characteristic $p$, a polynomial $f \in \overline{\mathbb{F}}_p[x]$ and $α, β\in L$, let $\mathrm{Prep}(f;α,β)$ be the set of all $λ\in \overline{L}$ such that both $α$ and $β$ are preperiodic under the action of $f_λ(x) := f(x) + λ$. Ghioca and Hsia proved that for certain families of polynomials, this set is infinite if and only if $f(α)=f(β)$ or $α, β\in \overline{\mathbb{F}}_p$. Building on their earlier work, we determine the condition that $\mathrm{Prep}(f;…

Deadbeat Robust Model Predictive Control for Linear Parameter-Varying Systems
Georg Schildbach, Hossam S. Abbas
https://arxiv.org/abs/2509.14885 https://ar…

Deadbeat Robust Model Predictive Control for Linear Parameter-Varying Systems
The concept of Deadbeat Robust Model Predictive Control (DRMPC) is to completely extinguish the effect of external disturbances within the first few steps of the prediction horizon. The benefit is that the remaining dynamics of the system can be planned with certainty. This means it is not necessary to employ a Robust Positive Invariant (RPI) set as a terminal condition, which is often complex or even intractable to compute. Recent work has shown that it is possible to obtain full system theore…

Parameter sensitivity of cosmic pairwise velocities in the non-linear regime of structure formation
Jorge Enrique Garc\'ia-Farieta, H\'ector J. Hort\'ua
https://arxiv.org/abs/2509.15223

Parameter sensitivity of cosmic pairwise velocities in the non-linear regime of structure formation
The peculiar velocities of dark matter tracers drive the growth of cosmic structures, providing a sensitive test of cosmological models and strengthening constraints on the nature of dark energy. In this work, we investigate the mean pairwise velocities, $v_{12}$, of dark matter tracers as a cosmological probe in the non-linear regime of cosmic structure formation. Using N-body dark matter-only simulations, we measure $v_{12}$ for pair separations up to 50 $h^{-1}$Mpc and model it by solving th…

Google releases Cell2Sentence-Scale 27B (C2S-Scale), a 27B-parameter foundation model for single-cell analysis built on its Gemma family of open models (The Keyword)
https://blog.google/technology/ai/google-gemma-ai-cancer-therapy-discovery/

How a Gemma model helped discover a new potential cancer therapy pathway
We’re launching a new 27 billion parameter foundation model for single-cell analysis built on the Gemma family of open models.

Bayesian Parameter Inference and Uncertainty-Informed Sensitivity Analysis in a 0D Cardiovascular Model for Intraoperative Hypotension
Jan-Niklas Thiel, Marko Zlicar, Ulrich Steinseifer, Borut Kirn, Michael Neidlin
https://arxiv.org/abs/2509.14354

Bayesian Parameter Inference and Uncertainty-Informed Sensitivity Analysis in a 0D Cardiovascular Model for Intraoperative Hypotension
Computational cardiovascular models are promising tools for clinical decision support, particularly in complex conditions, such as intraoperative hypotension (IOH). IOH arises from different mechanisms, making treatment selection non-trivial. Patient-specific predictions require calibration, typically performed using deterministic approaches prone to parameter non-identifiability and lacking uncertainty quantification, hindering clinical translation. Consequently, Bayesian approaches are needed…

Bell Meets General Philosophers of Science : Reassessing Measurement Independence
Yuichiro Kitajima
https://arxiv.org/abs/2509.14458 https://arxiv.org/pdf/…

Bell Meets General Philosophers of Science : Reassessing Measurement Independence
Bell's inequality is derived from three assumptions: measurement independence, outcome independence, and parameter independence. Among these, measurement independence, often taken for granted, holds that hidden variables are statistically uncorrelated with measurement settings. Under this assumption, the violation of Bell's inequality implies that either outcome independence or parameter independence fails to hold, meaning that local hidden variables do not exist. In this paper, we refer to thi…

Evolution of meta's llama models and parameter-efficient fine-tuning of large language models: a survey
Abdulhady Abas Abdullah, Arkaitz Zubiaga, Seyedali Mirjalili, Amir H. Gandomi, Fatemeh Daneshfar, Mohammadsadra Amini, Alan Salam Mohammed, Hadi Veisi
https://arxiv.org/abs/2510.12178

Evolution of meta's llama models and parameter-efficient fine-tuning of large language models: a survey
This review surveys the rapid evolution of Meta AI's LLaMA (Large Language Model Meta AI) series - from LLaMA 1 through LLaMA 4 and the specialized parameter-efficient fine-tuning (PEFT) methods developed for these models. We first describe the LLaMA family of foundation models (7B-65B to 288B parameters), their architectures (including native multimodal and Mixtureof-Experts variants), and key performance characteristics. We then describe and discuss the concept of PEFT, which adapts large pre…

Learning Rate Should Scale Inversely with High-Order Data Moments in High-Dimensional Online Independent Component Analysis
M. Oguzhan Gultekin, Samet Demir, Zafer Dogan
https://arxiv.org/abs/2509.15127

Learning Rate Should Scale Inversely with High-Order Data Moments in High-Dimensional Online Independent Component Analysis
We investigate the impact of high-order moments on the learning dynamics of an online Independent Component Analysis (ICA) algorithm under a high-dimensional data model composed of a weighted sum of two non-Gaussian random variables. This model allows precise control of the input moment structure via a weighting parameter. Building on an existing ordinary differential equation (ODE)-based analysis in the high-dimensional limit, we demonstrate that as the high-order moments increase, the algorit…

Twist fields in many-body physics
Benjamin Doyon
https://arxiv.org/abs/2509.15064 https://arxiv.org/pdf/2509.15064

Twist fields in many-body physics
The notion of twist fields has played a fundamental role in many-body physics. It is used to construct the so-called disorder parameter for the study of phase transitions in the classical Ising model of statistical mechanics, it is involved in the Jordan-Wigner transformation in quantum chains and bosonisation in quantum field theory, and it is related to measures of entanglement in many-body quantum systems. I provide a pedagogical introduction to the notion of twist field and the concepts at …

Integrated Sensing and Communication for Vehicular Networks: A Rate-Distortion Fundamental Limits of State Estimator
Lugaoze Feng, Guocheng Lv, Xunan Li, Ye Jin
https://arxiv.org/abs/2509.15025

Integrated Sensing and Communication for Vehicular Networks: A Rate-Distortion Fundamental Limits of State Estimator
The state-dependent memoryless channel (SDMC) is employed to model the integrated sensing and communication (ISAC) system for connected vehicular networks, where the transmitter conveys messages to the receiver while simultaneously estimating the state parameter of interest via the received echo signals. However, the performance of sensing has often been neglected in existing works. To address this gap, we establish the rate-distortion function for sensing performance in the SDMC model, which i…

Optimal Algorithms for Bandit Learning in Matching Markets
Tejas Pagare, Agniv Bandyopadhyay, Sandeep Juneja
https://arxiv.org/abs/2509.14466 https://arxiv…

Optimal Algorithms for Bandit Learning in Matching Markets
We study the problem of pure exploration in matching markets under uncertain preferences, where the goal is to identify a stable matching with confidence parameter $δ$ and minimal sample complexity. Agents learn preferences via stochastic rewards, with expected values indicating preferences. This finds use in labor market platforms like Upwork, where firms and freelancers must be matched quickly despite noisy observations and no prior knowledge, in a stable manner that prevents dissatisfaction…

Shedding Light on Dark Matter at the LHC with Machine Learning
Ernesto Arganda, Mart\'in de los Rios, Andres D. Perez, Subhojit Roy, Rosa M. Sand\'a Seoane, Carlos E. M. Wagner
https://arxiv.org/abs/2509.15121

Shedding Light on Dark Matter at the LHC with Machine Learning
We investigate a WIMP dark matter (DM) candidate in the form of a singlino-dominated lightest supersymmetric particle (LSP) within the $Z_3$-symmetric Next-to-Minimal Supersymmetric Standard Model. This framework gives rise to regions of parameter space where DM is obtained via co-annihilation with nearby higgsino-like electroweakinos and DM direct detection~signals are suppressed, the so-called ``blind spots". On the other hand, collider signatures remain promising due to enhanced radiative de…

Stochastic Finite Volume Approximation with Clustering in the Parameter Space for Forward Uncertainty Quantification of PDEs with Random Parameters
Zhao Zhang, Na Ou
https://arxiv.org/abs/2510.12109

Stochastic Finite Volume Approximation with Clustering in the Parameter Space for Forward Uncertainty Quantification of PDEs with Random Parameters
The uncertainty quantification (UQ) for partial differential equations (PDEs) with random parameters is important for science and engineering. Forward UQ quantifies the impact of random parameters on the solution or the quantity-of-interest (QoI). In the current study, we propose a new extension of the stochastic finite volume (SFV) method by clustering samples in the parameter space. Compared to classic SFV based on structured grid in the parameter space, the new scheme based on clustering ext…

Constraining Cosmology with Double-Source-Plane Strong Gravitational Lenses From the AGEL Survey
Duncan J. Bowden, Nandini Sahu, Anowar J. Shajib, Kim-Vy Tran, Tania M. Barone, Keerthi Vasan G. C., Daniel J. Ballard, Thomas E. Collett, Faith Dalessandro, Giovanni Ferrami, Karl Glazebrook, William J. Gottemoller, Leena Iwamoto, Tucker Jones, Glenn G. Kacprzak, Geraint F. Lewis, Haven McIntosh-Lombardo, Hannah Skobe, Sherry H. Suyu, Sarah M. Sweet

Constraining Cosmology with Double-Source-Plane Strong Gravitational Lenses From the AGEL Survey
Double-source-plane strong gravitational lenses (DSPLs), with two sources at different redshifts, are independent cosmological probes of the dark energy equation of state parameter $w$ and the matter density parameter $Ω_{\rm m}$. We present the lens model for the DSPL AGEL035346$-$170639 and infer cosmological constraints from this system for flat $Λ$CDM and flat $w$CDM cosmologies. From the joint posterior of $w$ and $Ω_{\rm m}$ in the flat $w$CDM cosmology, we extract the following median…

Julia Set in Quantum Evolution: The case of Dynamical Quantum Phase Transitions
Manmeet Kaur, Somendra M. Bhattacharjee
https://arxiv.org/abs/2509.14923 https://

Julia Set in Quantum Evolution: The case of Dynamical Quantum Phase Transitions
Dynamical quantum phase transitions (DQPTs) are a class of non-equilibrium phase transitions that occur in many-body quantum systems during real-time evolution, rather than through parameter tuning as in conventional phase transitions. This paper presents an exact analytical approach to studying DQPTs by combining complex dynamics with the real-space renormalization group (RG). RG transformations are interpreted as iterated maps on the complex plane, establishing a connection betw…

Large-order perturbation theory of linear eigenvalue problems
Stephen Jonathan Chapman
https://arxiv.org/abs/2509.14763 https://arxiv.org/pdf/2509.14763

Large-order perturbation theory of linear eigenvalue problems
We consider a class of linear eigenvalue problems depending on a small parameter epsilon in which the series expansion for the eigenvalue in powers of epsilon is divergent. We develop a new technique to determine the precise nature of this divergence. We illustrate the technique through its application to four examples: the anharmonic oscillator, a simplified model of equitorially-trapped Rossby waves, and two simplified models based on quasinormal modes of Reissner-Normstrom de Sitterblack hol…

Zero Indirect Band Gap in Non-Hermitian Systems
Rahul S, Giandomenico Palumbo
https://arxiv.org/abs/2509.15102 https://arxiv.org/pdf/2509.15102

Zero Indirect Band Gap in Non-Hermitian Systems
Zero indirect gaps in band models are typically viewed as unstable and achievable only through fine-tuning. Recent works, however, have revealed robust semimetallic phases in Hermitian systems where the indirect gap remains pinned at zero over a finite parameter range. Here, we extend this paradigm to non-Hermitian lattice models by studying a one-dimensional diamond-like system with gain and loss. We show that a zero indirect band gap can remain stable against non-Hermitian perturbations and i…

FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts
Heming Zou, Yunliang Zang, Wutong Xu, Yao Zhu, Xiangyang Ji
https://arxiv.org/abs/2510.08396

FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts
Low-Rank Adaptation (LoRA) is a widely used parameter-efficient fine-tuning method for foundation models, but it suffers from parameter interference, resulting in suboptimal performance. Although Mixture-of-Experts (MoE)-based LoRA variants show promise in mitigating intra-task correlations in single-task instruction tuning, they introduce additional router parameters and remain ineffective in multi-task model merging where inter-task interference arises. Inspired by the fly olfactory circuit, …

Exploring new construction schemes for extended-hierarchy CI (ehCI) wavefunctions
Rugwed A. Lokhande, Carlos E. V. de Moura, Pratiksha B. Gaikwad, Ram\'on Alain Miranda-Quintana
https://arxiv.org/abs/2509.15190

Exploring new construction schemes for extended-hierarchy CI (ehCI) wavefunctions
Following the work of Loos et al. on hierarchy CI (hCI) we propose an extended way of partitioning the Hilbert space by combining the excitation and the seniority sectors in a more general way. We define the hierarchy parameter, h, involving two "weights" (alphas), measuring the importance of excitation (e) and seniority (s) contributions to the wavefunction according to: h = α1.e + α2.s. We test these new CI methods on the dissociation of chemical systems and analyze them based on the import…

An Empirical Study of Reducing AV1 Decoder Complexity and Energy Consumption via Encoder Parameter Tuning
Vibhoothi Vibhoothi, Julien Zouein, Shanker Shreejith, Jean-Baptiste Kempf, Anil Kokaram
https://arxiv.org/abs/2510.12380

An Empirical Study of Reducing AV1 Decoder Complexity and Energy Consumption via Encoder Parameter Tuning
The widespread adoption of advanced video codecs such as AV1 is often hindered by their high decoding complexity, posing a challenge for battery-constrained devices. While encoders can be configured to produce bitstreams that are decoder-friendly, estimating the decoding complexity and energy overhead for a given video is non-trivial. In this study, we systematically analyse the impact of disabling various coding tools and adjusting coding parameters in two AV1 encoders, libaom-av1 and SVT-AV1.…

Enhanced Angle-Range Cluster Parameter Estimation in Full-Duplex ISAC Systems
Muhammad Talha, Besma Smida, David Gonz\'alez G
https://arxiv.org/abs/2510.12711 https://

Enhanced Angle-Range Cluster Parameter Estimation in Full-Duplex ISAC Systems
This work studies an integrated sensing and communication (ISAC) framework for targets that are spread both in the angle and range domains. We model each target using a cluster of rays parameterized by a specific density function, and propose a truncated Multiple Signal Classification (MUSIC) spread (TMS) algorithm to accurately estimate the parameters of the density function. Unlike the conventional MUSIC spread (CMS), TMS restricts the signal subspace rank based on the eigen decomposition of …

Robust Functional Logistic Regression
Berkay Akturk, Ufuk Beyaztas, Han Lin Shang
https://arxiv.org/abs/2510.12048 https://arxiv.org/pdf/2510.12048

Robust Functional Logistic Regression
Functional logistic regression is a popular model to capture a linear relationship between binary response and functional predictor variables. However, many methods used for parameter estimation in functional logistic regression are sensitive to outliers, which may lead to inaccurate parameter estimates and inferior classification accuracy. We propose a robust estimation procedure for functional logistic regression, in which the observations of the functional predictor are projected onto a set …

Distributed Batch Matrix Multiplication: Trade-Offs in Download Rate, Randomness, and Privacy
Amirhosein Morteza, Remi A. Chou
https://arxiv.org/abs/2509.15047 https://

Distributed Batch Matrix Multiplication: Trade-Offs in Download Rate, Randomness, and Privacy
We study the trade-off between communication rate and privacy for distributed batch matrix multiplication of two independent sequences of matrices $\bold{A}$ and $\bold{B}$ with uniformly distributed entries. In our setting, $\bold{B}$ is publicly accessible by all the servers while $\bold{A}$ must remain private. A user is interested in evaluating the product $\bold{AB}$ with the responses from the $k$ fastest servers. For a given parameter $α\in [0, 1]$, our privacy constraint must ensure th…

Monojet and direct detection constraints on real scalar dark matter: EFT and a simple UV completion
Arnab Roy, Michael A. Schmidt, German Valencia
https://arxiv.org/abs/2509.14869

Monojet and direct detection constraints on real scalar dark matter: EFT and a simple UV completion
We consider constraints that can be placed on certain invisible scalar particles through monojet studies at the LHC and compare them with those from direct detection experiments when interpreted as dark matter. Whereas direct detection constraints are typically more restrictive, we identify regions of parameter space where monojet studies provide important complementary bounds. We carry out our analysis using both a $ϕ$SMEFT for real scalar particle pairs coupled to standard-model fields throu…

Black Hole Quasi-Periodic Oscillations in the Presence of Gauss-Bonnet Trace Anomaly
Rupam Jyoti Borah, Umananda Dev Goswami
https://arxiv.org/abs/2509.14629 https://

Black Hole Quasi-Periodic Oscillations in the Presence of Gauss-Bonnet Trace Anomaly
We investigate the effects of the Gauss-Bonnet (GB) gravitational trace anomaly on the circular motion of test particles around black holes (BHs) and its implications for quasi-periodic oscillations (QPOs) in various theoretical models. Beginning with the equations of motion, we study the effects on effective potential, angular momentum, specific energy, and the innermost stable circular orbit (ISCO) induced by the anomaly parameter $α$. The fundamental frequencies are calculated. Moreover, we…

Observability and parameter estimation of a generic model for aggregated distributed energy resources
Bukunmi Gabriel Odunlami, Marcos Netto
https://arxiv.org/abs/2510.10892 htt…

Observability and parameter estimation of a generic model for aggregated distributed energy resources
We propose a novel framework for estimating the parameters of an aggregated distributed energy resources (der_a) model. First, we introduce a rigorous method to determine whether all model parameters are estimable. When they are not, our approach identifies the subset of parameters that can be estimated. The proposed framework offers new insights into the number and specific parameters that can be reliably estimated based on commonly available measurements. It also highlights the limitations of…

TAG-K: Tail-Averaged Greedy Kaczmarz for Computationally Efficient and Performant Online Inertial Parameter Estimation
Shuo Sha, Anupam Bhakta, Zhenyuan Jiang, Kevin Qiu, Ishaan Mahajan, Gabriel Bravo, Brian Plancher
https://arxiv.org/abs/2510.04839

TAG-K: Tail-Averaged Greedy Kaczmarz for Computationally Efficient and Performant Online Inertial Parameter Estimation
Accurate online inertial parameter estimation is essential for adaptive robotic control, enabling real-time adjustment to payload changes, environmental interactions, and system wear. Traditional methods such as Recursive Least Squares (RLS) and the Kalman Filter (KF) often struggle to track abrupt parameter shifts or incur high computational costs, limiting their effectiveness in dynamic environments and for computationally constrained robotic systems. As such, we introduce TAG-K, a lightweigh…

Mixed order phase transition in a locally constrained exclusion process
Gunter Schutz, Ali Zahra
https://arxiv.org/abs/2509.14467 https://arxiv.org/pdf/250…

Mixed order phase transition in a locally constrained exclusion process
We investigate a novel variant of the exclusion process in which particles perform asymmetric nearest-neighbor jumps across a bond \((k, k+1)\) only if the preceding site \((k-1)\) is unoccupied. This next-nearest-neighbor constraint significantly enriches the system's dynamics, giving rise to long-range correlations and a mixed-order transition controlled by the asymmetry parameter. We focus on the critical case of half filling, where the system splits into two ergodic components, each associa…

Efficient Group Lasso Regularized Rank Regression with Data-Driven Parameter Determination
Meixia Lin, Meijiao Shi, Yunhai Xiao, Qian Zhang
https://arxiv.org/abs/2510.11546 http…

Efficient Group Lasso Regularized Rank Regression with Data-Driven Parameter Determination
High-dimensional regression often suffers from heavy-tailed noise and outliers, which can severely undermine the reliability of least-squares based methods. To improve robustness, we adopt a non-smooth Wilcoxon score based rank objective and incorporate structured group sparsity regularization, a natural generalization of the lasso, yielding a group lasso regularized rank regression method. By extending the tuning-free parameter selection scheme originally developed for the lasso, we introduce …

N-Parties Private Structure and Parameter Learning for Sum-Product Networks
Xenia Heilmann, Ernst Althaus, Mattia Cerrato, Nick Johannes Peter Rassau, Mohammad Sadeq Dousti, Stefan Kramer
https://arxiv.org/abs/2510.05946

N-Parties Private Structure and Parameter Learning for Sum-Product Networks
A sum-product network (SPN) is a graphical model that allows several types of probabilistic inference to be performed efficiently. In this paper, we propose a privacy-preserving protocol which tackles structure generation and parameter learning of SPNs. Additionally, we provide a protocol for private inference on SPNs, subsequent to training. To preserve the privacy of the participants, we derive our protocol based on secret sharing, which guarantees privacy in the honest-but-curious setting ev…

Refining open cluster parameters with Gaia XP metallicities
M. Nizovkina, S. S. Larsen, A. G. A. Brown, A. Helmi
https://arxiv.org/abs/2510.10385 https://a…

Refining open cluster parameters with Gaia XP metallicities
The precision of cluster parameter determination has significantly improved with the availability of homogeneous photometric Gaia data, however, challenges such as age-metallicity degeneracy and lack of spectroscopic observations remain. In this paper we investigate whether metallicities derived from low-resolution Gaia XP spectra can be effectively used to break degeneracies and improve the accuracy of OC parameter determinations. We analysed 20 OCs using isochrone fitting methods on Gaia DR…

Statistical framework for nuclear parameter uncertainties in nucleosynthesis modeling of r- and i-process
S. Martinet, G. Goriely, A. Choplin, L. Siess
https://arxiv.org/abs/2510.03138

Statistical framework for nuclear parameter uncertainties in nucleosynthesis modeling of r- and i-process
Propagating nuclear uncertainties to nucleosynthesis simulations is key to understand the impact of theoretical uncertainties on the predictions, especially for processes far from the stability region, where nuclear properties are scarcely known. While systematic (model) uncertainties have been thoroughly studied, the statistical (parameter) ones have been more rarely explored, as constraining them is more challenging. We present here a methodology to determine coherently parameter uncertaintie…

Understanding Modal Interactions in Non-classically Damped Linear Oscillators with Closely Spaced Modes
Luis M. Baldelomar Pinto, Alireza Mojahed, Sobhan Mohammadi, Keegan J. Moore, Lawrence A. Bergman, Alexander F. Vakakis
https://arxiv.org/abs/2509.14857

Understanding Modal Interactions in Non-classically Damped Linear Oscillators with Closely Spaced Modes
This work addresses non-classically damped coupled oscillators with closely spaced modes focusing on the physics of modal interactions. Considering the simplest representative example in the form of an impulsively excited two-degree-of-freedom (two-DOF) system, we show that there is a single parameter defined as a coupling versus damping non-proportionality ratio, that separates two different dynamical regimes. Based on complexification-averaging analysis, we show that, below the critical value…

Exponential quintessence with momentum coupling to dark matter
Alkistis Pourtsidou
https://arxiv.org/abs/2509.15091 https://arxiv.org/pdf/2509.15091…

Exponential quintessence with momentum coupling to dark matter
We present updated constraints on an interacting dark energy - dark matter model with pure momentum transfer, where dark energy is in the form of a quintessence scalar field with an exponential potential. We run a suite of MCMC analyses using the DESI DR2 BAO measurements, in combination with CMB data from Planck and supernovae data from DESY5. In contrast to the standard case of uncoupled quintessence, we find that values for the potential's slope parameter $λ\geq \sqrt{2}$, which are conject…

A Deep Multi-Task Learning Approach to Impulsive Noise Parameter Estimation
Abdullahi Mohammad, Bdah Eya, Bassant Selim
https://arxiv.org/abs/2510.12179 https://

A Deep Multi-Task Learning Approach to Impulsive Noise Parameter Estimation
Impulsive noise poses a significant challenge to the reliability of wireless communication systems, necessitating accurate estimation of its statistical parameters for effective mitigation. This paper introduces a multitask learning (MTL) framework based on a CNN-LSTM architecture enhanced with an attention mechanism for the joint estimation of impulsive noise parameters. The proposed model leverages a unified weighted-loss function to enable simultaneous learning of multiple parameters within …

Non-conformally Einstein instantons in Conformal Gravity with and without nonlinear matter fields
Crist\'obal Corral, Borja Diez, Eleftherios Papantonopoulos
https://arxiv.org/abs/2510.11854

Non-conformally Einstein instantons in Conformal Gravity with and without nonlinear matter fields
In this work, we study non-conformally Einstein gravitational instantons in four-dimensional Conformal Gravity, both in vacuum and in the presence of nonlinear conformal matter. First, the one-parameter extension of the Kerr-NUT-AdS metric is analyzed. We obtain their conserved charges by using the Noether-Wald formalism. It turns out that they receive corrections from the linear modes present in Conformal Gravity, which are properly identified. Then, we perform the analytic continuation into t…

PRAXA: A Framework for What-If Analysis
Sneha Gathani, Kevin Li, Raghav Thind, Sirui Zeng, Matthew Xu, Peter J. Haas, Cagatay Demiralp, Zhicheng Liu
https://arxiv.org/abs/2510.09791

PRAXA: A Framework for What-If Analysis
Various analytical techniques-such as scenario modeling, sensitivity analysis, perturbation-based analysis, counterfactual analysis, and parameter space analysis-are used across domains to explore hypothetical scenarios, examine input-output relationships, and identify pathways to desired results. Although termed differently, these methods share common concepts and methods, suggesting unification under what-if analysis. Yet a unified framework to define motivations, core components, and its dis…

Leveraging Language Semantics for Collaborative Filtering with TextGCN and TextGCN-MLP: Zero-Shot vs In-Domain Performance
Andrei Chernov, Haroon Wahab, Oleg Novitskij
https://arxiv.org/abs/2510.12461 …

Leveraging Language Semantics for Collaborative Filtering with TextGCN and TextGCN-MLP: Zero-Shot vs In-Domain Performance
In recent years, various approaches have been proposed to leverage large language models (LLMs) for incorporating textual information about items into recommender systems. Existing methods primarily focus on either fine-tuning LLMs to generate recommendations or integrating LLM-based embeddings into downstream models. In this work, we follow the latter direction and propose \textbf{TextGCN}, which applies parameter-free graph convolution layers directly over LLM-based item-title embeddings, ins…

Cosmology in the Hoyle Narlikar gravity
J. K. Singh, Sonal Aggarwal, Shaily, Hamid Shabani
https://arxiv.org/abs/2510.11762 https://arxiv.org/pdf/2510.117…

Cosmology in the Hoyle Narlikar gravity
In this paper, we study the late time cosmic acceleration of the Quintessence model within the framework of Hoyle Narlikar Gravity, consisting of a creation field. Using the Hubble tension as a function of the density parameter for matter, the density parameter for radiation, and the density parameter for dark energy in the covariant formulation, we find the gravitational field equations in the spatially flat, homogeneous, and isotropic spacetime to examine the dynamical mechanism that leads to…

Asymptotics of the solution of the Cauchy problem for a singularly perturbed system of hyperbolic equations. Part 2. Initial conditions
Andrey Nesterov
https://arxiv.org/abs/2510.12550

Asymptotics of the solution of the Cauchy problem for a singularly perturbed system of hyperbolic equations. Part 2. Initial conditions
An asymptotic small parameter expansion of a single Cauchy problem is constructed for a singularly perturbed system of hyperbolic equations describing vibrations of two rigidly connected strings. Equations (such as generalized Korteweg-de Vriesequations) and initial conditions for the terms of the asymptotic expansion of the solution are determined, and under certain assumptions, the residual term is estimated from the residual.

From amoebas to pluripotential theory on hybrid analytic spaces
Sebastien Boucksom
https://arxiv.org/abs/2510.10239 https://arxiv.org/pdf/2510.10239…

From amoebas to pluripotential theory on hybrid analytic spaces
These lecture notes are an introduction to the use of non-Archimedean geometry in the study of meromorphic degenerations of complex algebraic varieties. They provide a self-contained discussion of hybrid spaces, which fill in one-parameter degenerations with the associated non-Archimedean Berkovich space as a central fiber. The main focus is on the interplay between complex and non-Archimedean pluripotential theory, and on the relation between convergence of psh metrics and the associated Monge…

Lanthanide Impact on the Infra-Red Spectra of Nebular Phase Kilonovae
Quentin Pognan, Kyohei Kawaguchi, Shinya Wanajo, Sho Fujibayashi, Anders Jerkstrand
https://arxiv.org/abs/2510.12413

Lanthanide Impact on the Infra-Red Spectra of Nebular Phase Kilonovae
Nebular phase kilonovae (KNe) have significant infra-red (IR) emission thought to be mostly forbidden emission lines from rapid neutron capture (r-process) species in neutron star merger ejecta. Lanthanide elements in particular have complex atomic structures with many IR transitions. Using non-local thermodynamic equilibrium (NLTE) radiative transfer simulations, we explore the impact of lanthanides on the IR spectra of KNe in the nebular phase, exploring a parameter space of ejecta mass and l…

Noch einige der zuletzt hier besonders häufig geteilten #News:
Web-Tipps: Stau verstehen
https://www.heise.de/news/Web-Tip…

Sources: Apple plans to use a custom 1.2T-parameter Google Gemini model to help power the new Siri next year and will be paying Google ~$1B annually for it (Mark Gurman/Bloomberg)
https://www.bloomberg.com/news/articles/20

AMAQ: Adaptive Mixed-bit Activation Quantization for Collaborative Parameter Efficient Fine-tuning
Yurun Song, Zhuoyi Yang, Ian G. Harris, Sangeetha Abdu Jyothi
https://arxiv.org/abs/2510.05468

AMAQ: Adaptive Mixed-bit Activation Quantization for Collaborative Parameter Efficient Fine-tuning
Large Language Models (LLMs) are scaling rapidly, creating significant challenges for collaborative server client distributed training, particularly in terms of communication efficiency and computational overheads. To address these challenges, we implement Parameter-efficient Split Learning, which effectively balances efficiency and performance for collaborative training on low-resource devices. To reduce communication overhead in collaborative training, we introduce Adaptive Mixed bit Activa…

Fragmentation-limited dust filtration in 2D simulations of planet-disk systems with dust coagulation. Parameter study and implications for the inner disk's dust mass budget and composition
Thomas Pfeil, Philip J. Armitage, Yan-Fei Jiang
https://arxiv.org/abs/2510.08574

Fragmentation-limited dust filtration in 2D simulations of planet-disk systems with dust coagulation. Parameter study and implications for the inner disk's dust mass budget and composition
Super-thermal gas giant planets or their progenitor cores are known to open deep gaps in protoplanetary disks, which stop large, drifting dust particles on their way to the inner disk. The possible separation of the disk into distinct reservoirs and the resulting dust depletion interior to the gap have important implications for planetesimal formation and the chemical and isotopic composition of the inner regions of protoplanetary disks. Dust fragmentation, however, maintains a reservoir of sma…

Unitary representations attached to parabolic subgroups: the case of abelian unipotent radical
Dan Ciubotaru
https://arxiv.org/abs/2510.11862 https://arxiv…

Unitary representations attached to parabolic subgroups: the case of abelian unipotent radical
We classify the unitary representations with integral infinitesimal character in Lusztig's category of unipotent representations in the case when the geometric parameter space comes from the action of a Levi subgroup on the abelian nilradical of a (maximal) parabolic subalgebra. We organise the unitary representations into microlocal Arthur packets. This is a test case for investigating a conjectural description of unitary representations with integral infinitesimal character.

Kinetic modelling of the CO2 capture and utilisation on NiRu-Ca/Al dual function material via parameter estimation
Meshkat Dolat, Andrew David Wright, Soudabeh Bahrami Gharamaleki, Loukia-Pantzechroula Merkouri, Melis S. Duyar, Michael Short
https://arxiv.org/abs/2510.12439

Kinetic modelling of the CO2 capture and utilisation on NiRu-Ca/Al dual function material via parameter estimation
This study presents a detailed, open-source kinetic modelling computational framework for CO2 capture and utilisation using a newly formulated dual-function material (DFM) comprising 15 wt% Ni, 1 wt% Ru, and 10 wt% CaO supported on spherical alumina. A finite difference reactor model was developed to simulate the cyclic adsorption, purge, and hydrogenation stages. The model incorporates experimentally-derived rate expressions, accounts for system delay via a second-order response function, and …

Efficient Prior Sensitivity and Tipping-point Analysis for Medical Research: Revisiting Sampling Importance Resampling
Tomohiro Ohigashi, Shonosuke Sugasawa
https://arxiv.org/abs/2510.10034

Efficient Prior Sensitivity and Tipping-point Analysis for Medical Research: Revisiting Sampling Importance Resampling
Bayesian methods have received increasing attention in medical research, where sensitivity analysis of prior distributions is essential. Such analyses typically require the evaluation of the posterior distribution of a parameter under multiple alternative prior settings. When the posterior distribution of the parameter of interest cannot be derived analytically, the standard approach is to re-fit the Markov chain Monte Carlo (MCMC) algorithm for each setting, which incurs substantial computatio…

SubApSnap: Solving parameter-dependent linear systems with a snapshot and subsampling
Eleanor Jones, Yuji Nakatsukasa
https://arxiv.org/abs/2510.04825 https://

SubApSnap: Solving parameter-dependent linear systems with a snapshot and subsampling
A growing number of problems in computational mathematics can be reduced to the solution of many linear systems that are related, often depending smoothly or slowly on a parameter $p$, that is, $A(p)x(p)=b(p)$. We introduce an efficient algorithm for solving such parameter-dependent linear systems for many values of $p$. The algorithm, which we call SubApSnap (for \emph{Sub}sampled $A(p)$ times \emph{Snap}shot), is based on combining ideas from model order reduction and randomised linear algebr…

The CEERS Photometric and Physical Parameter Catalog
Isa G. Cox, Jeyhan S. Kartaltepe, Micaela B. Bagley, Steven L. Finkelstein, Caitlin Rose, Ali Ahmad Khostovan, Katherine Chworowsky, Olivier Ilbert, Anton M. Koekemoer, Henry C. Ferguson, Pablo Arrabal Haro, Bren E. Backhaus, Mark Dickinson, Adriano Fontana, Yuchen Guo, Andrea Grazian, Norman A. Grogin, Santosh Harish, Nimish P. Hathi, Benne W. Holwerda, Kartheik G. Iyer, Lisa J. Kewley, Allison Kirkpatrick, Dale D. Kocevski, Rebecca…

The CEERS Photometric and Physical Parameter Catalog
We present the Cosmic Evolution Early Release Science Survey (CEERS) catalog, including space-based photometry, photometric redshifts, and physical parameters for more than 80,000 galaxies. The imaging used for this catalog comes from the CEERS survey, which has NIRCam coverage over ~100 sq. arcmin of the Extended Groth Strip (EGS) in seven filters from 1.15$μ$m to 4.44$μ$m. Alongside these data, we also include ancillary HST imaging in seven filters from 0.435$μ$m to 1.6$μ$m. We used Sourc…

Agent-Based Genetic Algorithm for Crypto Trading Strategy Optimization
Qiushi Tian, Churong Liang, Kairan Hong, Runnan Li
https://arxiv.org/abs/2510.07943 https://

Agent-Based Genetic Algorithm for Crypto Trading Strategy Optimization
Cryptocurrency markets present formidable challenges for trading strategy optimization due to extreme volatility, non-stationary dynamics, and complex microstructure patterns that render conventional parameter optimization methods fundamentally inadequate. We introduce Cypto Genetic Algorithm Agent (CGA-Agent), a pioneering hybrid framework that synergistically integrates genetic algorithms with intelligent multi-agent coordination mechanisms for adaptive trading strategy parameter optimization…

On the $v$-adic values of G-functions I
Georgios Papas
https://arxiv.org/abs/2510.11806 https://arxiv.org/pdf/2510.11806

On the $v$-adic values of G-functions I
This is the first in a series of papers aimed at studying families of G-functions associated to $1$-parameter families of abelian schemes. In particular, the construction of relations, in both the archimedean and non-archimedean settings, at values of specific interest to problems of unlikely intersections. In this first text in this series, we record what we expect to be the theoretical foundations of this series in a uniform way. After this, we study values corresponding to ``splittings'' i…

MeTA-LoRA: Data-Efficient Multi-Task Fine-Tuning for Large Language Models
Bo Cheng, Xu Wang, Jinda Liu, Yi Chang, Yuan Wu
https://arxiv.org/abs/2510.11598 https://

MeTA-LoRA: Data-Efficient Multi-Task Fine-Tuning for Large Language Models
Low-Rank Adaptation (LoRA) has emerged as one of the most widely used parameter-efficient fine-tuning (PEFT) methods for adapting large language models (LLMs) to downstream tasks. While highly effective in single-task settings, it struggles to efficiently leverage inter-task knowledge in complex multi-task learning scenarios, often requiring substantial task-specific data to achieve optimal performance. To address this limitation, we introduce MeTA-LoRA, a two-stage optimization framework that …

Parameter Identification of a Differentiable Human Arm Musculoskeletal Model without Deep Muscle EMG Reconstruction
Philip Sanderink, Yingfan Zhou, Shuzhen Luo, Cheng Fang
https://arxiv.org/abs/2509.22825

Parameter Identification of a Differentiable Human Arm Musculoskeletal Model without Deep Muscle EMG Reconstruction
Accurate parameter identification of a subject-specific human musculoskeletal model is crucial to the development of safe and reliable physically collaborative robotic systems, for instance, assistive exoskeletons. Electromyography (EMG)-based parameter identification methods have demonstrated promising performance for personalized musculoskeletal modeling, whereas their applicability is limited by the difficulty of measuring deep muscle EMGs invasively. Although several strategies have been pr…

Parameter-Efficient Multi-Task Learning via Progressive Task-Specific Adaptation
Neeraj Gangwar, Anshuka Rangi, Rishabh Deshmukh, Holakou Rahmanian, Yesh Dattatreya, Nickvash Kani
https://arxiv.org/abs/2509.19602

Parameter-Efficient Multi-Task Learning via Progressive Task-Specific Adaptation
Parameter-efficient fine-tuning methods have emerged as a promising solution for adapting pre-trained models to various downstream tasks. While these methods perform well in single-task learning, extending them to multi-task learning exacerbates common challenges, such as task interference and negative transfer, due to the limited number of trainable parameters. To address these issues, we introduce progressive task-specific multi-task adaptation, a novel parameter-efficient approach for multi-…

Constraint Qualification for Generic Parameter Families of Constraints in Optimization
Naoki Hamada, Kenta Hayano, Hiroshi Teramoto
https://arxiv.org/abs/2510.02381 https://

Constraint Qualification for Generic Parameter Families of Constraints in Optimization
Constraint qualifications (CQs) are central to the local analysis of constrained optimization. In this paper, we completely determine the validity of the four classical CQs -- LICQ, MFCQ, ACQ, and GCQ -- for constraint map-germs that arise in generic four-parameter families. Our approach begins by proving that all four CQs are invariant under the action of the group $\mathcal{K}[G]$ and under the operation of reduction. As a consequence, the verification of CQ-validity for a generic constraint …

Asteroseismic calibration of the Rossby number and its connection to the stellar dynamo and fundamental properties
Alfio Bonanno, Enrico Corsaro, Travis S. Metcalfe, Sylvain Breton, Orlagh L. Creevey, Christopher J. Lindsay
https://arxiv.org/abs/2510.12471

Asteroseismic calibration of the Rossby number and its connection to the stellar dynamo and fundamental properties
The stellar Rossby number, a dimensionless parameter quantifying the influence of Coriolis forces on convective motions, plays a pivotal role in understanding magnetic stellar evolution. In this work, we explore the connection between the Rossby number and potential dynamo mechanisms in Sun-like stars, as well as its dependence on fundamental stellar properties. We present a novel, detailed asteroseismic calibration of the convective turnover time, incorporating for the first time Gaia photomet…

Quantum Trigonometric B\'ezier Curves
\c{C}etin Di\c{s}ib\"uy\"uk
https://arxiv.org/abs/2510.09336 https://arxiv.org/pdf/2510.09336

Quantum Trigonometric Bézier Curves
In order to construct quantum trigonometric Bézier curves with shape parameter, one parameter family of trigonometric Bernstein basis functions are introduced. We study the total positivity of the basis functions to analyze the shape preserving properties of the quantum trigonometric Bézier curves. We also showed that quantum trigonometric Bézier curves can be evaluated by two different recursive evaluation algorithms. Finally, we have defined rational counterpart of quantum trigonometric B�…

Parameter estimation of the four-parameter Harris extended Weibull distribution with applications to real-life data
Prithul Chaturvedi, Himanshu Pokhriyal
https://arxiv.org/abs/2509.26162

Parameter estimation of the four-parameter Harris extended Weibull distribution with applications to real-life data
This paper explores the extension of the classical two-parameter Weibull distribution to a four-parameter Harris extended Weibull (HEW) distribution. The flexibility of this probability distribution is illustrated by the varying shapes of HEW density function. Estimation of HEW parameters is explored using estimation methods such as the least-squares, maximum product of spacings, and minimum distance method. We provide Bayesian inference on the random parameters of the HEW distribution using Me…

Contraction and entropy production in continuous-time Sinkhorn dynamics
Anand Srinivasan, Jean-Jacques Slotine
https://arxiv.org/abs/2510.12639 https://arx…

Contraction and entropy production in continuous-time Sinkhorn dynamics
Recently, the vanishing-step-size limit of the Sinkhorn algorithm at finite regularization parameter $\varepsilon$ was shown to be a mirror descent in the space of probability measures. We give $L^2$ contraction criteria in two time-dependent metrics induced by the mirror Hessian, which reduce to the coercivity of certain conditional expectation operators. We then give an exact identity for the entropy production rate of the Sinkhorn flow, which was previously known only to be nonpositive. Exam…

Enhancing Speech Emotion Recognition via Fine-Tuning Pre-Trained Models and Hyper-Parameter Optimisation
Aryan Golbaghi, Shuo Zhou
https://arxiv.org/abs/2510.07052 https://

Enhancing Speech Emotion Recognition via Fine-Tuning Pre-Trained Models and Hyper-Parameter Optimisation
We propose a workflow for speech emotion recognition (SER) that combines pre-trained representations with automated hyperparameter optimisation (HPO). Using SpeechBrain wav2vec2-base model fine-tuned on IEMOCAP as the encoder, we compare two HPO strategies, Gaussian Process Bayesian Optimisation (GP-BO) and Tree-structured Parzen Estimators (TPE), under an identical four-dimensional search space and 15-trial budget, with balanced class accuracy (BCA) on the German EmoDB corpus as the objective.…

Stable determination of the nonlinear parameter in the non-diffusive Westervelt equation from the Dirichlet-to-Neumann map
Mike Wendels
https://arxiv.org/abs/2510.02553 https://…

Stable determination of the nonlinear parameter in the non-diffusive Westervelt equation from the Dirichlet-to-Neumann map
The Westervelt equation models the propagation of nonlinear acoustic waves in a regime well-suited for applications such as medical ultrasound imaging. In this work, we prove that the nonlinear parameter, as well as the sound speed, can be stably recovered from the Dirichlet-to-Neumann map associated with the non-diffusive Westervelt equation in (1+3)-dimensions. This result is essential for the feasibility of reconstruction methods. The Dirichlet-to-Neumann map encodes boundary measurements by…

Beyond CPL: Evidence for dynamical dark energy in three-parameter models
Sonej Alam, Md. Wali Hossain
https://arxiv.org/abs/2510.03779 https://arxiv.org/pd…

Beyond CPL: Evidence for dynamical dark energy in three-parameter models
We introduce three-parameter extensions of the two-parameter minimal Akhtar-Hossain (mAH) parametrization, termed modified minimal AH (MmAH1,2), which provide greater flexibility in the dynamics of dark energy. These models are compared with $Λ$CDM, $w$CDM, mAH, CPL, and three-parameter CPL (CPL-$w_{\rm b}$) using a joint data set of the CMB compressed likelihood, DESI DR2, Pantheon$+$ supernovae, $H(z)$ measurements, and redshift-space distortions. While the common cosmological parameters rem…

Time-dependent Variational Principles for Hybrid Non-Unitary Dynamics: Application to Driven-Dissipative Superconductors
Pasquale Filice, Marco Schir\`o, Giacomo Mazza
https://arxiv.org/abs/2510.12737 …

Time-dependent Variational Principles for Hybrid Non-Unitary Dynamics: Application to Driven-Dissipative Superconductors
We introduce time-dependent variational principles to study the non-unitary dynamics of open quantum many-body systems, including dynamics described by the full Lindblad master equation, the non-Hermitian dynamics corresponding to the no-click limit of the fully post-selected quantum trajectories, and the dynamics described by a hybrid Lindbladian with a control parameter $α$ which interpolates between the full post-selection and averaging over all quantum trajectories. As an application we st…

A Samsung researcher introduces the Tiny Recursion Model, a 7M-parameter model that was able to outperform LLMs 10,000x larger like o3-mini on specific problems (Carl Franzen/VentureBeat)
https://venturebeat.com/ai/samsung-ai-researchers-n…

On the $v$-adic values of G-functions II
Georgios Papas
https://arxiv.org/abs/2510.11814 https://arxiv.org/pdf/2510.11814

On the $v$-adic values of G-functions II
This is the second in a series of papers by the author centered around the study of values of G-functions associated to $1$-parameter families of abelian varieties $f:\CX\rightarrow S$ and a point $s_0\in S(K)$ with smooth fiber over some number field $K$. Here we study the case where $f:\CX\rightarrow S$ is a family of elliptic curves. We construct relations among the values of G-functions in this setting at points whose fiber is a CM elliptic curve. These lead to bounds for the height of su…

An exactly solvable asymmetric simple inclusion process
Arvind Ayyer, Samarth Misra
https://arxiv.org/abs/2510.09191 https://arxiv.org/pdf/2510.09191

An exactly solvable asymmetric simple inclusion process
We study a generalization of the asymmetric simple inclusion process (ASIP) on a periodic one-dimensional lattice, where the integers in the particles rates are deformed to their $t$-analogues. We call this the $(q, t, θ)$~ASIP, where $q$ is the asymmetric hopping parameter and $θ$ is the diffusion parameter. We show that this process is a misanthrope process, and consequently the steady state is independent of $q$. We compute the steady state, the one-point correlation and the current in the…

Image of a quantum-corrected black hole without Cauchy horizons illuminated by a static thin accretion disk
Shilong Huang, Jiawei Chen, Jinsong Yang
https://arxiv.org/abs/2510.09956

Image of a quantum-corrected black hole without Cauchy horizons illuminated by a static thin accretion disk
Latest advances in effective quantum gravity propose a quantum-corrected black hole solution that avoids Cauchy horizons. In this paper, we study the image of the black hole and explore the influence of the quantum parameter $ζ$ on its image. First, we investigate the influence of $ζ$ on the event horizon, photon sphere, critical impact parameter, and innermost stable circular orbit associated with the black hole. We find that all these quantities exhibit an increase with increasing $ζ$. Mea…

Statistical Analysis of Target Parameter Estimation Using Passive Radar
Mats Viberg, Daniele Gerosa, Tomas McKelvey, Thomas Eriksson
https://arxiv.org/abs/2510.07948 https://

Statistical Analysis of Target Parameter Estimation Using Passive Radar
A passive radar system uses one or more so-called Illuminators of Opportunity (IO) to detect and localize targets. In such systems, a reference channel is often used at each receiving node to capture the transmitted IO signal, while targets are detected using the main surveillance channel. The purpose of the present contribution is to analyze a method for estimating the target parameters in such a system. Specifically, we quantify the additional error contribution due to not knowing the transmi…

FLRC: Fine-grained Low-Rank Compressor for Efficient LLM Inference
Yu-Chen Lu, Chong-Yan Chen, Chi-Chih Chang, Yu-Fang Hu, Kai-Chiang Wu
https://arxiv.org/abs/2510.09332 https:/…

FLRC: Fine-grained Low-Rank Compressor for Efficient LLM Inference
Although large language models (LLM) have achieved remarkable performance, their enormous parameter counts hinder deployment on resource-constrained hardware. Low-rank compression can reduce both memory usage and computational demand, but applying a uniform compression ratio across all layers often leads to significant performance degradation, and previous methods perform poorly during decoding. To address these issues, we propose the Fine-grained Low-Rank Compressor (FLRC), which efficiently d…

Simulation-based inference for neutrino interaction model parameter tuning
Karla Tame-Narvaez, Aleksandra \'Ciprijanovi\'c, Steven Gardiner, Giuseppe Cerati
https://arxiv.org/abs/2510.07454

Simulation-based inference for neutrino interaction model parameter tuning
High-energy physics experiments studying neutrinos rely heavily on simulations of their interactions with atomic nuclei. Limitations in the theoretical understanding of these interactions typically necessitate ad hoc tuning of simulation model parameters to data. Traditional tuning methods for neutrino experiments have largely relied on simple algorithms for numerical optimization. While adequate for the modest goals of initial efforts, the complexity of future neutrino tuning campaigns is expe…

Sampling Strategies for Robust Universal Quadrupedal Locomotion Policies
David Rytz, Kim Tien Ly, Ioannis Havoutis
https://arxiv.org/abs/2510.07094 https://

Sampling Strategies for Robust Universal Quadrupedal Locomotion Policies
This work focuses on sampling strategies of configuration variations for generating robust universal locomotion policies for quadrupedal robots. We investigate the effects of sampling physical robot parameters and joint proportional-derivative gains to enable training a single reinforcement learning policy that generalizes to multiple parameter configurations. Three fundamental joint gain sampling strategies are compared: parameter sampling with (1) linear and polynomial function mappings of ma…

Localist LLMs -- A Mathematical Framework for Dynamic Locality Control
Joachim Diederich
https://arxiv.org/abs/2510.09338 https://arxiv.org/pdf/2510.09338

Localist LLMs -- A Mathematical Framework for Dynamic Locality Control
We present a novel framework for training large language models with continuously adjustable internal representations that span the full spectrum from localist (interpretable, rule-based) to distributed (generalizable, efficient) encodings. The key innovation is a locality dial, a tunable parameter that dynamically controls the degree of localization during both training and inference without requiring model retraining. This is achieved through group sparsity penalties on attention mechanisms, …

Dendrograms of Mixing Measures for Softmax-Gated Gaussian Mixture of Experts: Consistency without Model Sweeps
Do Tien Hai, Trung Nguyen Mai, TrungTin Nguyen, Nhat Ho, Binh T. Nguyen, Christopher Drovandi
https://arxiv.org/abs/2510.12744

Dendrograms of Mixing Measures for Softmax-Gated Gaussian Mixture of Experts: Consistency without Model Sweeps
We develop a unified statistical framework for softmax-gated Gaussian mixture of experts (SGMoE) that addresses three long-standing obstacles in parameter estimation and model selection: (i) non-identifiability of gating parameters up to common translations, (ii) intrinsic gate-expert interactions that induce coupled differential relations in the likelihood, and (iii) the tight numerator-denominator coupling in the softmax-induced conditional density. Our approach introduces Voronoi-type loss f…

Prime Intellect debuts INTELLECT-3, an RL-trained 106B parameter open source MOE model it claims outperforms larger models across math, code, science, reasoning (Prime Intellect)
https://www.primeintellect.ai/blog/intellect-3

INTELLECT-3: A 100B+ MoE trained with large-scale RL
Today, we release INTELLECT-3, a 100B+ parameter Mixture-of-Experts model trained on our RL stack, achieving state-of-the-art performance for its size across math, code, science and reasoning benchmarks, outperforming many larger frontier models.

Periods detecting Eisenstein series and sums of $L$-values I
Weixiao Lu, Guodong Xi
https://arxiv.org/abs/2510.12446 https://arxiv.org/pdf/2510.12446

Periods detecting Eisenstein series and sums of $L$-values I
We study the automorphic period associated to a $G$-Hamiltonian variety $M$ whose dual is $\check{M} = T^*(\check{G}/\check{L})$, where $\check{G}$ is a general linear group and $\check{L}$ is a Levi subgroup. For certain cuspidal Eisenstein series, we prove that their period is equal to a finite sum of special values of $L$-functions. This sum is indexed by the fixed points of the associated extended $L$-parameter on $\check{M}$, confirming a conjecture by Ben-Zvi-Sakellaridis-Venkatesh in thi…

Optimal smoothing parameter in Eilers-Wittaker smoother
Roberto Bernal-Arencibia, Karel Garcia Medina, Ernesto Estevez-Rams, Beatriz Aragon-Fernandez
https://arxiv.org/abs/2510.01798

Optimal smoothing parameter in Eilers-Wittaker smoother
The Eilers-Whittaker method for data smoothing effectiveness depends on the choice of the regularisation parameter, and automatic selection is a necessity for large datasets. Common methods, such as leave-one-out cross-validation, can perform poorly when serially correlated noise is present. We propose a novel procedure for selecting the control parameter based on the spectral entropy of the residuals. We define an S-curve from the Euclidean distance between points in a plot of the spectral ent…

Phys2Real: Fusing VLM Priors with Interactive Online Adaptation for Uncertainty-Aware Sim-to-Real Manipulation
Maggie Wang, Stephen Tian, Aiden Swann, Ola Shorinwa, Jiajun Wu, Mac Schwager
https://arxiv.org/abs/2510.11689

Phys2Real: Fusing VLM Priors with Interactive Online Adaptation for Uncertainty-Aware Sim-to-Real Manipulation
Learning robotic manipulation policies directly in the real world can be expensive and time-consuming. While reinforcement learning (RL) policies trained in simulation present a scalable alternative, effective sim-to-real transfer remains challenging, particularly for tasks that require precise dynamics. To address this, we propose Phys2Real, a real-to-sim-to-real RL pipeline that combines vision-language model (VLM)-inferred physical parameter estimates with interactive adaptation through unce…

TASO: Task-Aligned Sparse Optimization for Parameter-Efficient Model Adaptation
Daiye Miao, Yufang Liu, Jie Wang, Changzhi Sun, Yunke Zhang, Demei Yan, Shaokang Dong, Qi Zhang, Yuanbin Wu
https://arxiv.org/abs/2509.17688

TASO: Task-Aligned Sparse Optimization for Parameter-Efficient Model Adaptation
LoRA has become one of the most widely used parameter-efficient fine-tuning methods due to its simplicity and effectiveness. However, numerous studies have shown that LoRA often introduces substantial parameter redundancy, which not only increases the number of trainable parameters but also hinders the effectiveness of fine-tuning. Since identifying redundant parameters in LoRA is inherently difficult, how to eliminate them efficiently and accurately remains a challenging problem. In this paper…

Mistral launches Devstral 2, a coding model with 123B parameters requiring at least four H100 GPUs, and a 24B parameter Devstral Small for local deployment (Anna Heim/TechCrunch)
https://techcrunch.com/2025/12/09/mistral-ai-surfs-vibe-coding-t…

Mistral AI surfs vibe-coding tailwinds with new coding models | TechCrunch
French AI startup Mistral today launched Devstral 2, a new generation of its AI model designed for coding, as the company seeks to catch up to bigger AI labs like Anthropic and other coding-focused LLMs.

Automated Evolutionary Optimization for Resource-Efficient Neural Network Training
Ilia Revin, Leon Strelkov, Vadim A. Potemkin, Ivan Kireev, Andrey Savchenko
https://arxiv.org/abs/2510.09566

Automated Evolutionary Optimization for Resource-Efficient Neural Network Training
There are many critical challenges in optimizing neural network models, including distributed computing, compression techniques, and efficient training, regardless of their application to specific tasks. Solving such problems is crucial because the need for scalable and resource-efficient models is increasing. To address these challenges, we have developed a new automated machine learning (AutoML) framework, Parameter Efficient Training with Robust Automation (PETRA). It applies evolutionary op…

Algorithmic Temperature Induced by Adopted Regular Universal Turing Machine
Kentaro Imafuku
https://arxiv.org/abs/2510.11737 https://arxiv.org/pdf/2510.117…

Algorithmic Temperature Induced by Adopted Regular Universal Turing Machine
We prove that an effective temperature naturally emerges from the algorithmic structure of a regular universal Turing machine (UTM), without introducing any external physical parameter. In particular, the redundancy growth of the machine's wrapper language induces a Boltzmann--like exponential weighting over program lengths, yielding a canonical ensemble interpretation of algorithmic probability. This establishes a formal bridge between algorithmic information theory and statistical mechanics, …

Cosmology Likelihood for Observables in \Euclid (CLOE). 1. Theoretical recipe
Collaboration, Cardone, Joudaki, Blot, Bonici, Camera, Ca\~nas-Herrera, Carrilho, Casas, Davini, Di Domizio, Farrens, Goh, Beauchamps, Ili\'c, Keil, Le Brun, Martinelli, Moretti, Pettorino, Pezzotta, S\'anchez, Sakr, Sciotti, Tanidis, Tutusaus, Ajani, Crocce, Giocoli, Legrand, Lembo, Lesci, Girones, Nouri-Zonoz, Pamuk, Tsedrik, Bel, Carbone, Duncan, Kilbinger, Lacasa, Lattanzi, Sapone, Sellentin, Tayl…

Cosmology Likelihood for Observables in \Euclid (CLOE). 1. Theoretical recipe
As the statistical precision of cosmological measurements increases, the accuracy of the theoretical description of these measurements needs to increase correspondingly in order to infer the underlying cosmology that governs the Universe. To this end, we have created the Cosmology Likelihood for Observables in Euclid (CLOE), which is a novel cosmological parameter inference pipeline developed within the Euclid Consortium to translate measurements and covariances into cosmological parameter cons…

Nonlinear Heisenberg Limit via Uncertainty Principle in Quantum Metrology
Binke Xia, Jingzheng Huang, Yuxiang Yang, Guihua Zeng
https://arxiv.org/abs/2510.09216 https://

Nonlinear Heisenberg Limit via Uncertainty Principle in Quantum Metrology
The Heisenberg limit is acknowledged as the ultimate precision limit in quantum metrology, traditionally implying that root mean square errors of parameter estimation decrease linearly with the time T of evolution and the number N of quantum gates or probes. However, this conventional perspective fails to interpret recent studies of "super-Heisenberg" scaling, where precision improves faster than linearly with T and N. In this work, we revisit the Heisenberg scaling by leveraging the position-m…

Biased parameter inference of eccentric, spin-precessing binary black holes
Divyajyoti, Isobel M. Romero-Shaw, Vaishak Prasad, Kaushik Paul, Chandra Kant Mishra, Prayush Kumar, Akash Maurya, Michael Boyle, Lawrence E. Kidder, Harald P. Pfeiffer, Mark A. Scheel
https://arxiv.org/abs/2510.04332

Biased parameter inference of eccentric, spin-precessing binary black holes
While the majority of gravitational wave (GW) events observed by the LIGO and Virgo detectors are consistent with mergers of binary black holes (BBHs) on quasi-circular orbits, some events are also consistent with non-zero orbital eccentricity, indicating that the binaries could have formed via dynamical interactions. Moreover, there may be GW events which show support for spin-precession, eccentricity, or both. In this work, we study the interplay of spins and eccentricity on the parameter est…

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[1/4]:
- Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model Services
Yansong Li, Zhixing Tan, Paula Branco, Yang Liu

Variational Inference for Count Response Semiparametric Regression: A Convex Solution
Virginia Murru, Matt P. Wand
https://arxiv.org/abs/2510.12356 https://

Variational Inference for Count Response Semiparametric Regression: A Convex Solution
We develop a version of variational inference for Bayesian count response regression-type models that possesses attractive attributes such as convexity and closed form updates. The convex solution aspect entails numerically stable fitting algorithms, whilst the closed form aspect makes the methodology fast and easy to implement. The essence of the approach is the use of Pólya-Gamma augmentation of a Negative Binomial likelihood, a finite-valued prior on the shape parameter and the structured m…

Prime-powered images and irreducible polynomials in dynamical semigroups
Aristaa Bhardwaj, Adrian Boyer-Paulet, Wade Hindes, Emma Qiu, Alexander Sun
https://arxiv.org/abs/2510.10310

Prime-powered images and irreducible polynomials in dynamical semigroups
Let $G=\langle x^d+c_1,\dots,x^d+c_s\rangle$ be a semigroup generated under composition for some $c_1,\dots,c_s\in\mathbb{Z}$ and some $d\geq2$. Then we prove that, outside of an exceptional one-parameter family, $G$ contains a large and explicit subset of irreducible polynomials if and only if it contains at least one irreducible polynomial. In particular, this conclusion holds when $G$ is generated by at least $s\geq3$ polynomials when $d$ is odd and at least $s\geq5$ polynomials when $d$ is …

A Pseudo-Hermitian Hybrid Model at Finite Temperature: The Role of the Exceptional Points
Ignacio Fushimi (IFLP-UNLP, Argentina), Marta Reboiro (IFLP-UNLP, Argentina)
https://arxiv.org/abs/2510.08773

A Pseudo-Hermitian Hybrid Model at Finite Temperature: The Role of the Exceptional Points
We study a hybrid system formed by an ensemble of colour nitrogen-vacancy centres in diamond interacting with a superconducting flux-qubit at finite temperature. The presence of impurities in the system is modelled through pseudo-hermitian Hamiltonian, by introducing an asymmetry parameter in the interaction between the superconducting flux qubit and the ensemble of colour nitrogen-vacancy centres in diamond. We construct the exact grand partition function of the system, and from it we derive t…

Essential AI, whose CEO co-wrote Google's Attention Is All You Need paper, unveils Rnj-1, an 8B-parameter open model with SWE-bench performance close to GPT-4o (Ashish Vaswani/Essential AI)
https://essential.ai/research/rnj-1

KORMo: Korean Open Reasoning Model for Everyone
Minjun Kim, Hyeonseok Lim, Hangyeol Yoo, Inho Won, Seungwoo Song, Minkyung Cho, Junhun Yuk, Changsu Choi, Dongjae Shin, Huige Lee, Hoyun Song, Alice Oh, Kyungtae Lim
https://arxiv.org/abs/2510.09426

KORMo: Korean Open Reasoning Model for Everyone
This work presents the first large-scale investigation into constructing a fully open bilingual large language model (LLM) for a non-English language, specifically Korean, trained predominantly on synthetic data. We introduce KORMo-10B, a 10.8B-parameter model trained from scratch on a Korean-English corpus in which 68.74% of the Korean portion is synthetic. Through systematic experimentation, we demonstrate that synthetic data, when carefully curated with balanced linguistic coverage and diver…

Information paradox and island of covariant black holes in LQG
Yongbin Du, Jia-Rui Sun, Xiangdong Zhang
https://arxiv.org/abs/2510.11921 https://arxiv.org/…

Information paradox and island of covariant black holes in LQG
We study information paradox of four dimensional covariant black holes inspired by loop quantum gravity (LQG) with two well motivated solutions. We first prepare the spacetime in the Hartle-Hawking state, compute the radiation entropy and recover a linear growth at late time. When considering the mass loss and incorporating greybody factors, we show that for Solution~1 the LQG parameter $ζ$ leaves temperature and Planckian factor of the spectrum unchanged but enhances the near-horizon barrier,…

Non-linear causal bulk viscosity in Unified Dark Matter Cosmologies
Guillermo Palma, Gabriel Gomez
https://arxiv.org/abs/2510.11900 https://arxiv.org/pdf/2…

Non-linear causal bulk viscosity in Unified Dark Matter Cosmologies
We propose a bulk viscous unified dark matter scenario based on a nonlinear extension of the full causal Israel-Stewart theory. This framework allows the viscous fluid to remain far from equilibrium, an essential feature for a physically consistent description of viscosity-driven accelerated expansion. We adopt the standard parametrization for the bulk viscosity, $ξ= ξ_{0} ρ_{m}^{s}$, treating $s$ as a free parameter, and study the model in a spatially flat Friedmann-Robertson-Walker backgro…

MaP: A Unified Framework for Reliable Evaluation of Pre-training Dynamics
Jiapeng Wang, Changxin Tian, Kunlong Chen, Ziqi Liu, Jiaxin Mao, Wayne Xin Zhao, Zhiqiang Zhang, Jun Zhou
https://arxiv.org/abs/2510.09295

MaP: A Unified Framework for Reliable Evaluation of Pre-training Dynamics
Reliable evaluation is fundamental to the progress of Large Language Models (LLMs), yet the evaluation process during pre-training is plagued by significant instability that obscures true learning dynamics. In this work, we systematically diagnose this instability, attributing it to two distinct sources: \textit{Parameter Instability} from training stochasticity and \textit{Evaluation Instability} from noisy measurement protocols. To counteract both sources of noise, we introduce \textbf{MaP}, …