Tootfinder

Optimized methods for composite optimization: a reduction perspective
Jinho Bok, Jason M. Altschuler
https://arxiv.org/abs/2506.23756 https://

Optimized methods for composite optimization: a reduction perspective
Recent advances in convex optimization have leveraged computer-assisted proofs to develop optimized first-order methods that improve over classical algorithms. However, each optimized method is specially tailored for a particular problem setting, and it is a well-documented challenge to extend optimized methods to other settings due to their highly bespoke design and analysis. We provide a general framework that derives optimized methods for composite optimization directly from those for uncons…

A Class of Stochastic Runge-Kutta Methods for Stochastic Differential Equations Converging with Order 1 in $L^p$-Norm
Andreas R\"o{\ss}ler
https://arxiv.org/abs/2506.22657

A Class of Stochastic Runge-Kutta Methods for Stochastic Differential Equations Converging with Order 1 in $L^p$-Norm
For the approximation of solutions for Itô and Stratonovich stochastic differential equations (SDEs)a new class of efficient stochastic Runge-Kutta (SRK) methods is developed. As the main novelty only two stages are necessary for the proposed SRK methods of order 1 that can be applied to SDEs with non-commutative or with commutative noise. In addition, a variant of the SRK method for SDEs with additive noise is presented. All proposed SRK methods cover also the case of drift-implicit schemes a…

Impact of Fine-Tuning Methods on Memorization in Large Language Models
Jie Hou, Chuxiong Wu, Lannan Luo, Qiang Zeng
https://arxiv.org/abs/2507.00258 https:…

Impact of Fine-Tuning Methods on Memorization in Large Language Models
As the capabilities of pre-trained large language models (LLMs) continue to advance, the "pre-train and fine-tune" paradigm has become increasingly mainstream, leading to the development of various fine-tuning methods. However, the privacy risks arising from memorization during fine-tuning have received relatively little attention. To address this gap, we categorize popular fine-tuning approaches and assess their impact on memorization through the lens of membership inference attacks (MIAs). Ou…

Hybrid Approach for Electricity Price Forecasting using AlexNet and LSTM
Bosubabu Sambana, Kotamsetty Geethika Devi, Bandi Rajeswara Reddy, Galeti Mohammad Hussain, Gownivalla Siddartha
https://arxiv.org/abs/2506.23504

Hybrid Approach for Electricity Price Forecasting using AlexNet and LSTM
The recent development of advanced machine learning methods for hybrid models has greatly addressed the need for the correct prediction of electrical prices. This method combines AlexNet and LSTM algorithms, which are used to introduce a new model with higher accuracy in price forecasting. Despite RNN and ANN being effective, they often fail to deal with forex time sequence data. The traditional methods do not accurately forecast the prices. These traditional methods only focus on demand and pr…

Access InContext: Futuring Accessible Prototyping Tools and Methods
Patricia Piedade, Peter A Hayton, Cynthia Bennett, Anna R L Carter, Clara Crivellaro, Alan Dix, Jess McGowan, Katta Spiel, Miriam Sturdee, Garreth W. Tigwell, Hugo Nicolau
https://arxiv.org/abs/2506.24057

Access InContext: Futuring Accessible Prototyping Tools and Methods
The popularity of accessibility research has grown recently, improving digital inclusion for people with disabilities. However, researchers, including those who have disabilities, have attempted to include people with disabilities in all aspects of design, and they have identified a myriad of practical accessibility barriers posed by tools and methods leveraged by human-computer interaction (HCI) researchers during prototyping. To build a more inclusive technological landscape, we must question…

Convergence of Stochastic Gradient Methods for Wide Two-Layer Physics-Informed Neural Networks
Bangti Jin, Longjun Wu
https://arxiv.org/abs/2508.21571 https://

Convergence of Stochastic Gradient Methods for Wide Two-Layer Physics-Informed Neural Networks
Physics informed neural networks (PINNs) represent a very popular class of neural solvers for partial differential equations. In practice, one often employs stochastic gradient descent type algorithms to train the neural network. Therefore, the convergence guarantee of stochastic gradient descent is of fundamental importance. In this work, we establish the linear convergence of stochastic gradient descent / flow in training over-parameterized two layer PINNs for a general class of activation fu…

Lower bounds for trace estimation via Block Krylov and other methods
Shi Jie Yu
https://arxiv.org/abs/2506.22701 https://arxiv.org/pd…

Lower bounds for trace estimation via Block Krylov and other methods
This paper studies theoretical lower bounds for estimating the trace of a matrix function, $\text{tr}(f(A))$, focusing on methods that use Hutchinson's method along with Block Krylov techniques. These methods work by approximating matrix-vector products like $f(A)V$ using a Block Krylov subspace. This is closely related to approximating functions with polynomials. We derive theoretical upper bounds on how many Krylov steps are needed for functions such as $A^{-1/2}$ and $A^{-1}$ by analyzing th…

Bridging Classical and Learning-based Iterative Registration through Deep Equilibrium Models
Yi Zhang, Yidong Zhao, Qian Tao
https://arxiv.org/abs/2507.00582

Bridging Classical and Learning-based Iterative Registration through Deep Equilibrium Models
Deformable medical image registration is traditionally formulated as an optimization problem. While classical methods solve this problem iteratively, recent learning-based approaches use recurrent neural networks (RNNs) to mimic this process by unrolling the prediction of deformation fields in a fixed number of steps. However, classical methods typically converge after sufficient iterations, but learning-based unrolling methods lack a theoretical convergence guarantee and show instability empir…

Hybrid methods for missing categorical covariates in Cox model
Abdoulaye Dioni, Lynne Moore, Aida Eslami
https://arxiv.org/abs/2507.00151 https://

Hybrid methods for missing categorical covariates in Cox model
Survival analysis aims to explore the relationship between covariates and the time until the occurrence of an event. The Cox proportional hazards model is commonly used for right-censored data, but it is not strictly limited to this type of data. However, the presence of missing values among the covariates, particularly categorical ones, can compromise the validity of the estimates. To address this issue, various classical methods for handling missing data have been proposed within the Cox mode…

Diffusion-based Multi-modal Synergy Interest Network for Click-through Rate Prediction
Xiaoxi Cui, Weihai Lu, Yu Tong, Yiheng Li, Zhejun Zhao
https://arxiv.org/abs/2508.21460 ht…

Diffusion-based Multi-modal Synergy Interest Network for Click-through Rate Prediction
In click-through rate prediction, click-through rate prediction is used to model users' interests. However, most of the existing CTR prediction methods are mainly based on the ID modality. As a result, they are unable to comprehensively model users' multi-modal preferences. Therefore, it is necessary to introduce multi-modal CTR prediction. Although it seems appealing to directly apply the existing multi-modal fusion methods to click-through rate prediction models, these methods (1) fail to eff…

Unsupervised Incremental Learning Using Confidence-Based Pseudo-Labels
Lucas Rakotoarivony
https://arxiv.org/abs/2508.21424 https://arxiv.org/pdf/2508.2142…

Unsupervised Incremental Learning Using Confidence-Based Pseudo-Labels
Deep learning models have achieved state-of-the-art performance in many computer vision tasks. However, in real-world scenarios, novel classes that were unseen during training often emerge, requiring models to acquire new knowledge incrementally. Class-Incremental Learning (CIL) methods enable a model to learn novel classes while retaining knowledge of previous classes. However, these methods make the strong assumption that the incremental dataset is fully labeled, which is unrealistic in pract…

OptMark: Robust Multi-bit Diffusion Watermarking via Inference Time Optimization
Jiazheng Xing, Hai Ci, Hongbin Xu, Hangjie Yuan, Yong Liu, Mike Zheng Shou
https://arxiv.org/abs/2508.21727

OptMark: Robust Multi-bit Diffusion Watermarking via Inference Time Optimization
Watermarking diffusion-generated images is crucial for copyright protection and user tracking. However, current diffusion watermarking methods face significant limitations: zero-bit watermarking systems lack the capacity for large-scale user tracking, while multi-bit methods are highly sensitive to certain image transformations or generative attacks, resulting in a lack of comprehensive robustness. In this paper, we propose OptMark, an optimization-based approach that embeds a robust multi-bit …

Optimization by VarQITE on Adaptive Variational Quantum Kolmogorov-Arnold Network
Hikaru Wakaura, Rahmat Mulyawan, Andriyan B. Suksmono
https://arxiv.org/abs/2506.22801

Optimization by VarQITE on Adaptive Variational Quantum Kolmogorov-Arnold Network
Quantum imaginary time evolution (QITE) is a powerful method to derive the ground states of the systems. Only the damping of quantum states leads it; hence, reaching the ground state is guaranteed by nature without any external manipulation. Numerous QITE methods by many groups are used to improve speed and accuracy, derive excited states, and solve combined optimization problems. However, the QITE methods have not been used for quantum machine learning to predict the ideal values for multiple …

PI-WAN: A Physics-Informed Wind-Adaptive Network for Quadrotor Dynamics Prediction in Unknown Environments
Mengyun Wang, Bo Wang, Yifeng Niu, Chang Wang
https://arxiv.org/abs/2507.00816

PI-WAN: A Physics-Informed Wind-Adaptive Network for Quadrotor Dynamics Prediction in Unknown Environments
Accurate dynamics modeling is essential for quadrotors to achieve precise trajectory tracking in various applications. Traditional physical knowledge-driven modeling methods face substantial limitations in unknown environments characterized by variable payloads, wind disturbances, and external perturbations. On the other hand, data-driven modeling methods suffer from poor generalization when handling out-of-distribution (OoD) data, restricting their effectiveness in unknown scenarios. To addres…

Quantum-inspired probability metrics define a complete, universal space for statistical learning
Logan S. McCarty
https://arxiv.org/abs/2508.21086 https://…

Quantum-inspired probability metrics define a complete, universal space for statistical learning
Comparing probability distributions is a core challenge across the natural, social, and computational sciences. Existing methods, such as Maximum Mean Discrepancy (MMD), struggle in high-dimensional and non-compact domains. Here we introduce quantum probability metrics (QPMs), derived by embedding probability measures in the space of quantum states: positive, unit-trace operators on a Hilbert space. This construction extends kernel-based methods and overcomes the incompleteness of MMD on non-co…

Investigating Stochastic Methods for Prosody Modeling in Speech Synthesis
Paul Mayer, Florian Lux, Alejandro P\'erez-Gonz\'alez-de-Martos, Angelina Elizarova, Lindsey Vanderlyn, Dirk V\"ath, Ngoc Thang Vu
https://arxiv.org/abs/2507.00227

Investigating Stochastic Methods for Prosody Modeling in Speech Synthesis
While generative methods have progressed rapidly in recent years, generating expressive prosody for an utterance remains a challenging task in text-to-speech synthesis. This is particularly true for systems that model prosody explicitly through parameters such as pitch, energy, and duration, which is commonly done for the sake of interpretability and controllability. In this work, we investigate the effectiveness of stochastic methods for this task, including Normalizing Flows, Conditional Flow…

DNN-based Methods of Jointly Sensing Number and Directions of Targets via a Green Massive H2AD MIMO Receiver
Bin Deng, Jiatong Bai, Feilong Zhao, Zuming Xie, Maolin Li, Yan Wang, Feng Shu
https://arxiv.org/abs/2507.22906

DNN-based Methods of Jointly Sensing Number and Directions of Targets via a Green Massive H2AD MIMO Receiver
As a green MIMO structure, the heterogeneous hybrid analog-digital H2AD MIMO architecture has been shown to own a great potential to replace the massive or extremely large-scale fully-digital MIMO in the future wireless networks to address the three challenging problems faced by the latter: high energy consumption, high circuit cost, and high complexity. However, how to intelligently sense the number and direction of multi-emitters via such a structure is still an open hard problem. To address …

Research on Comprehensive Classroom Evaluation System Based on Multiple AI Models
Cong Xie, Li Yang, Daben Wang, Jing Xiao
https://arxiv.org/abs/2506.23079

Research on Comprehensive Classroom Evaluation System Based on Multiple AI Models
The promotion of the national education digitalization strategy has facilitated the development of teaching quality evaluation towards all-round, process-oriented, precise, and intelligent directions, inspiring explorations into new methods and technologies for educational quality assurance. Classroom teaching evaluation methods dominated by teaching supervision and student teaching evaluation suffer from issues such as low efficiency, strong subjectivity, and limited evaluation dimensions. How…

AutoLyap: A Python package for computer-assisted Lyapunov analyses for first-order methods
Manu Upadhyaya, Adrien B. Taylor, Sebastian Banert, Pontus Giselsson
https://arxiv.org/abs/2506.24076

AutoLyap: A Python package for computer-assisted Lyapunov analyses for first-order methods
We introduce AutoLyap, a Python package designed to automate Lyapunov analyses for a wide class of first-order methods for solving structured optimization and inclusion problems. Lyapunov analyses are structured proof patterns, with historical roots in the study of dynamical systems, commonly used to establish convergence results for first-order methods. Building on previous works, the core idea behind AutoLyap is to recast the verification of the existence of a Lyapunov analysis as a semidefin…

"New Coral Reef Protection Technology to Transform Global Conservation"
#Coral #CoralReef #Environment

New Coral Reef Protection Technology to Transform Global Conservation | Happy Eco News
New coral reef protection technology will transform coral reef protection as an international partnership expands to cover 90% of the world's reefs. Saudi Arabia will direct the International Coral Reef Initiative and implementing advanced coral reef protection technology alongside proven conservation methods to safeguard these vital ocean ecosystems.

Anchoring Stellar Age Indicators: A Cross-Calibration of [C/N] and Gyrochronology Ages via the Age-Velocity-Dispersion Relation
Yuxi Lu, Marc H. Pinsonneault, Yuan-Sen Ting, Phil R. Van-Lane, John D Roberts, Jamie Tayar, Alexander Stone-Martinez
https://arxiv.org/abs/2506.24010

Anchoring Stellar Age Indicators: A Cross-Calibration of [C/N] and Gyrochronology Ages via the Age-Velocity-Dispersion Relation
Determining stellar ages is challenging, as it depends on other stellar parameters in a non-linear way and often relies on stellar evolution models to infer the underlying relation between these parameters and age. This complexity increases when comparing different age-dating methods, as they rely on distinct indicators and are often applicable to non-overlapping regions of the color-magnitude diagram. Moreover, many empirical calibration methods rely on pre-determined ages, often from open clu…

🧢 Modeling the World in 280 Characters
#graphics

Modeling the World in 280 Characters | Codrops
An exploration of the mindset, methods, and motivations behind crafting tiny, expressive shaders that combine code, art, and constraint.

Barycentric subspace analysis of network-valued data
Elodie Maignant (UniCA, EPIONE, CB, ZIB), Xavier Pennec (UniCA, EPIONE), Alain Trouv\'e (CB), Anna Calissano (UniCA, EPIONE, UCL)
https://arxiv.org/abs/2507.23559

Barycentric subspace analysis of network-valued data
Certain data are naturally modeled by networks or weighted graphs, be they arterial networks or mobility networks. When there is no canonical labeling of the nodes across the dataset, we talk about unlabeled networks. In this paper, we focus on the question of dimensionality reduction for this type of data. More specifically, we address the issue of interpreting the feature subspace constructed by dimensionality reduction methods. Most existing methods for network-valued data are derived from p…

Scalable Solution Methods for Dec-POMDPs with Deterministic Dynamics
Yang You, Alex Schutz, Zhikun Li, Bruno Lacerda, Robert Skilton, Nick Hawes
https://arxiv.org/abs/2508.21595

Scalable Solution Methods for Dec-POMDPs with Deterministic Dynamics
Many high-level multi-agent planning problems, including multi-robot navigation and path planning, can be effectively modeled using deterministic actions and observations. In this work, we focus on such domains and introduce the class of Deterministic Decentralized POMDPs (Det-Dec-POMDPs). This is a subclass of Dec-POMDPs characterized by deterministic transitions and observations conditioned on the state and joint actions. We then propose a practical solver called Iterative Deterministic P…

On the convergence of the no-response test for the heat equation
Shiwei Sun, Gen Nakamura, Haibing Wang
https://arxiv.org/abs/2506.23948 https://

On the convergence of the no-response test for the heat equation
Domain sampling methods called the range test (RT) and no-response test (NRT), and their duality are known for several inverse scattering problems and an inverse boundary value problem for the Laplace operator (see Section 1 for more details). In our previous work [21], we established the duality between the NRT and RT, and demonstrated the convergence of the RT for the heat equation. We also provided numerical studies for both methods. However, we did not address the convergence for the NRT. A…

A simplified unified wave-particle method for diatomic gases with rotational and vibrational non-equilibrium
Sirui Yang, Chengwen Zhong, Ningchao Ding, Junzhe Cao, He Zhang, Congshan Zhuo, Sha Liu
https://arxiv.org/abs/2507.00720

A simplified unified wave-particle method for diatomic gases with rotational and vibrational non-equilibrium
The hypersonic flow around near-space vehicles constitutes a multi-scale flow problem. Due to insufficient molecular collisions to achieve equilibrium, rarefied gas effects are present in the flow field. Thus, numerical methods capable of accurately resolving multi-scale flows are required. Furthermore, high-temperature gas effects in hypersonic flows mean vibrational excitation of polyatomic molecules. Consequently, numerical methods accounting for non-equilibrium in rotational and vibrational…

Analysis of User Experience Evaluation Methods for Deaf users: A Case Study on a mobile App
A. E. Fuentes-Cort\'azar, A. Rivera-Hern\'andez, J. R. Rojano-C\'aceres
https://arxiv.org/abs/2507.22455

Analysis of User Experience Evaluation Methods for Deaf users: A Case Study on a mobile App
User Experience (UX) evaluation methods that are commonly used with hearing users may not be functional or effective for Deaf users. This is because these methods are primarily designed for users with hearing abilities, which can create limitations in the interaction, perception, and understanding of the methods for Deaf individuals. Furthermore, traditional UX evaluation approaches often fail to address the unique accessibility needs of Deaf users, resulting in an incomplete or biased assessme…

It's a small thing, the syntactic sugar of using `/` to concatenate paths and strings is reason enough to use pathlib. And then you find out about all the built in methods...
https://mastodon.social/@treyhunner/114778741547764668

Trey Hunner 🐍 (@treyhunner@mastodon.social)
Attached: 1 image Working with file paths in Python? (splitting, joining, navigating, etc.) Check out #Python's pathlib module. It's great for splitting/joining paths, finding files by filename patterns, renaming files, and more. https://pym.dev/pathlib-module

Fast Methods For Multisite Charge Transfer Processes II: Analytic Nuclear Gradients and Nonadiabatic Dynamics For cCASSCF(1,M) and cCASSCF(2M-1,M) Wavefunctions
Tian Qiu, Joseph E. Subotnik
https://arxiv.org/abs/2508.21139

Fast Methods For Multisite Charge Transfer Processes II: Analytic Nuclear Gradients and Nonadiabatic Dynamics For cCASSCF(1,M) and cCASSCF(2M-1,M) Wavefunctions
We derive and implement analytic nuclear gradients and derivative couplings for a constrained Complete Active Space Self-Consistent Field with a small active space designed to model electron or hole transfer. Using a Lagrangian formalism, we are able to differentiate both the CASSCF energy and the constraint (which is required for globally smooth surfaces), and the resulting efficient algorithm can be immediately applied to nonadiabatic dynamics simulations of charge transfer processes. Here, w…

Computing excited eigenstates using inexact Lanczos methods and tree tensor network states
Madhumita Rano, Henrik R. Larsson
https://arxiv.org/abs/2506.22574

Computing excited eigenstates using inexact Lanczos methods and tree tensor network states
Excited eigenstates are crucial to understand the dynamics of quantum many-body systems. Tensor network states are one of the workhorses to compute ground states of many-body systems, yet the accurate computation of excited eigenstates is still challenging. Here, we develop a combination of the inexact Lanczos method, which aims at efficiently computing excited states, to tree tensor network states (TTNSs). We demonstrate our approach by computing excited vibrational states for three challengin…

Discretization of Continuous Frames by Quasi-Monte Carlo Methods
Jan Zimmermann, Andreas Klotz, Nicki Holighaus
https://arxiv.org/abs/2507.00618 https://…

Discretization of Continuous Frames by Quasi-Monte Carlo Methods
We introduce a discretization scheme for continuous localized frames using quasi-Monte Carlo integration and discrepancy theory. By generalizing classical concepts, we define a discrepancy measure on the entire phase space $\mathbb{R}^2$ and establish a corresponding Koksma-Hlawka inequality. This approach enables control over the density of the discretized frame and ensures the universality of the sampling set, relying only on the discrepancy of the sampling set and on the Sobolev-type seminor…

Today I took the time to have another look at #ActualBudget
#firefly_iii is great, but my mind just doesn't work well with traditional budgeting methods and my overall balance went down in 2025.
This might just be a coincidence (it went up in 2024 after all) but I just…

Deep Learning for Optical Misalignment Diagnostics in Multi-Lens Imaging Systems
Tomer Slor, Dean Oren, Shira Baneth, Tom Coen, Haim Suchowski
https://arxiv.org/abs/2506.23173

Deep Learning for Optical Misalignment Diagnostics in Multi-Lens Imaging Systems
In the rapidly evolving field of optical engineering, precise alignment of multi-lens imaging systems is critical yet challenging, as even minor misalignments can significantly degrade performance. Traditional alignment methods rely on specialized equipment and are time-consuming processes, highlighting the need for automated and scalable solutions. We present two complementary deep learning-based inverse-design methods for diagnosing misalignments in multi-element lens systems using only optic…

Modeling Data Diversity for Joint Instance and Verbalizer Selection in Cold-Start Scenarios
Mohna Chakraborty, Adithya Kulkarni, Qi Li
https://arxiv.org/abs/2507.00330

Modeling Data Diversity for Joint Instance and Verbalizer Selection in Cold-Start Scenarios
Prompt-based methods leverage the knowledge of pre-trained language models (PLMs) trained with a masked language modeling (MLM) objective; however, these methods are sensitive to template, verbalizer, and few-shot instance selection, particularly in cold-start settings with no labeled data. Existing studies overlook the dependency between instances and verbalizers, where instance-label probabilities depend on verbalizer token proximity in the embedding space. To address this, we propose COLDSEL…

A Dilation-based Seamless Multiscale Method For Elliptic Problems
Ziheng Chen, Bj\"orn Engquist
https://arxiv.org/abs/2506.22912 https://

A Dilation-based Seamless Multiscale Method For Elliptic Problems
Many numerical methods for multiscale differential equations require a scale separation between the larger and the smaller scales to achieve accuracy and computational efficiency. In the area of multiscale dynamical systems, so-called, seamless methods have been introduced to reduce the requirement of scale separation. We will translate these methods to numerical homogenization problems and extend the technique to multiple dimensions. The initial step is to prove that a one-dimensional \sepia{s…

Generalized Encrypted Traffic Classification Using Inter-Flow Signals
Federica Bianchi, Edoardo Di Paolo, Angelo Spognardi
https://arxiv.org/abs/2508.21558 https://

Generalized Encrypted Traffic Classification Using Inter-Flow Signals
In this paper, we present a novel encrypted traffic classification model that operates directly on raw PCAP data without requiring prior assumptions about traffic type. Unlike existing methods, it is generalizable across multiple classification tasks and leverages inter-flow signals - an innovative representation that captures temporal correlations and packet volume distributions across flows. Experimental results show that our model outperforms well-established methods in nearly every classifi…

Principled Curriculum Learning using Parameter Continuation Methods
Harsh Nilesh Pathak, Randy Paffenroth
https://arxiv.org/abs/2507.22089 https://arxiv.or…

Principled Curriculum Learning using Parameter Continuation Methods
In this work, we propose a parameter continuation method for the optimization of neural networks. There is a close connection between parameter continuation, homotopies, and curriculum learning. The methods we propose here are theoretically justified and practically effective for several problems in deep neural networks. In particular, we demonstrate better generalization performance than state-of-the-art optimization techniques such as ADAM for supervised and unsupervised learning tasks.

Image-Guided Shape-from-Template Using Mesh Inextensibility Constraints
Thuy Tran, Ruochen Chen, Shaifali Parashar
https://arxiv.org/abs/2507.22699 https://

Image-Guided Shape-from-Template Using Mesh Inextensibility Constraints
Shape-from-Template (SfT) refers to the class of methods that reconstruct the 3D shape of a deforming object from images/videos using a 3D template. Traditional SfT methods require point correspondences between images and the texture of the 3D template in order to reconstruct 3D shapes from images/videos in real time. Their performance severely degrades when encountered with severe occlusions in the images because of the unavailability of correspondences. In contrast, modern SfT methods use a c…

Bridging Ethical Principles and Algorithmic Methods: An Alternative Approach for Assessing Trustworthiness in AI Systems
Michael Papademas, Xenia Ziouvelou, Antonis Troumpoukis, Vangelis Karkaletsis
https://arxiv.org/abs/2506.22774

Bridging Ethical Principles and Algorithmic Methods: An Alternative Approach for Assessing Trustworthiness in AI Systems
Artificial Intelligence (AI) technology epitomizes the complex challenges posed by human-made artifacts, particularly those widely integrated into society and exert significant influence, highlighting potential benefits and their negative consequences. While other technologies may also pose substantial risks, AI's pervasive reach makes its societal effects especially profound. The complexity of AI systems, coupled with their remarkable capabilities, can lead to a reliance on technologies that o…

From Drone Imagery to Livability Mapping: AI-powered Environment Perception in Rural China
Weihuan Deng, Yaofu Huang, Luan Chen, Xun Li, Yao Yao
https://arxiv.org/abs/2508.21738

From Drone Imagery to Livability Mapping: AI-powered Environment Perception in Rural China
With the deepening of poverty alleviation and rural revitalization strategies, improving the rural living environment and enhancing the quality of life have become key priorities. Rural livability is a key indicator for measuring the effectiveness of these efforts. Current measurement approaches face significant limitations, as questionnaire-based methods are difficult to scale, while urban-oriented visual perception methods are poorly suited for rural contexts. In this paper, a rural-specific …

Accurate and Efficient Fetal Birth Weight Estimation from 3D Ultrasound
Jian Wang, Qiongying Ni, Hongkui Yu, Ruixuan Yao, Jinqiao Ying, Bin Zhang, Xingyi Yang, Jin Peng, Jiongquan Chen, Junxuan Yu, Wenlong Shi, Chaoyu Chen, Zhongnuo Yan, Mingyuan Luo, Gaocheng Cai, Dong Ni, Jing Lu, Xin Yang
https://arxiv.org/abs/2507.00398

Accurate and Efficient Fetal Birth Weight Estimation from 3D Ultrasound
Accurate fetal birth weight (FBW) estimation is essential for optimizing delivery decisions and reducing perinatal mortality. However, clinical methods for FBW estimation are inefficient, operator-dependent, and challenging to apply in cases of complex fetal anatomy. Existing deep learning methods are based on 2D standard ultrasound (US) images or videos that lack spatial information, limiting their prediction accuracy. In this study, we propose the first method for directly estimating FBW from…

Analysis of A Mixed Finite Element Method for Poisson's Equation with Rough Boundary Data
Huadong Gao, Yuhui Huang, Wen Xie
https://arxiv.org/abs/2507.00697

Analysis of A Mixed Finite Element Method for Poisson's Equation with Rough Boundary Data
This paper is concerned with finite element methods for Poisson's equation with rough boundary data. Conventional methods require that the boundary data $g$ of the problem belongs to $H^{1/2} (\partial Ω)$. However, in many applications one has to consider the case when $g$ is in $L^2(\partial Ω)$ only. To this end, very weak solutions are considered to establish the well-posedness of the problem. Most previously proposed numerical methods use regularizations of the boundary data. The main pu…

An empirical comparison of some outlier detection methods with longitudinal data
Marcello D'Orazio
https://arxiv.org/abs/2507.21203 https://arxiv.org/p…

An empirical comparison of some outlier detection methods with longitudinal data
This note investigates the problem of detecting outliers in longitudinal data. It compares well-known methods used in official statistics with proposals from the fields of data mining and machine learning that are based on the distance between observations or binary partitioning trees. This is achieved by applying the methods to panel survey data related to different types of statistical units. Traditional methods are quite simple, enabling the direct identification of potential outliers, but t…

🔆 From SDR to ‘Fake HDR’: Mario Kart World on Switch 2 Undermines Modern Display Potential
https://www.alexandermejia.com/from-sdr-to-fake-hdr-mario-kart-world-on-switch-2-undermines-modern-display-potential/

From SDR to ‘Fake HDR’: Mario Kart World on Switch 2 Undermines Modern Display Potential
Nintendo's Switch 2, launched with Mario Kart World, suffers from inadequate HDR implementation despite industry standards. The game qualifies "fake HDR," using SDR-first methods that limit color and dynamic range. Developers must prioritize HDR from the outset to truly leverage its potential and enhance visual quality, avoiding static tone mapping pitfalls.

Fast Methods For Multisite Charge Transfer Processes I: Constrained, State Averaged CASSCF(1,M) and CASSCF(2M-1,M) Simulations
Tian Qiu, Joseph E. Subotnik
https://arxiv.org/abs/2508.21136

Fast Methods For Multisite Charge Transfer Processes I: Constrained, State Averaged CASSCF(1,M) and CASSCF(2M-1,M) Simulations
We design a dynamically-weighted state-averaged constrained CASSCF to treat \ul{e}lectrons or \ul{h}oles moving between $n$ molecular fragments (where $n$ can be larger than 2). Within such a so-called eDSCn/hDSCn approach, we consider configurations that are mutually single excitations of each other, and we apply a generalized set of constraints to tailor the method for studying charge transfer problems. The constrained optimization problem is efficiently solved using a DIIS-SQP algorithm, thu…

Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods
Yasong Feng, Yifan Jiang, Tianyu Wang, Zhiliang Ying
https://arxiv.org/abs/2506.23335

Breaking a Logarithmic Barrier in the Stopping Time Convergence Rate of Stochastic First-order Methods
This work provides a novel convergence analysis for stochastic optimization in terms of stopping times, addressing the practical reality that algorithms are often terminated adaptively based on observed progress. Unlike prior approaches, our analysis: 1. Directly characterizes convergence in terms of stopping times adapted to the underlying stochastic process. 2. Breaks a logarithmic barrier in existing results. Key to our results is the development of a Grönwall-type argument tailored to such…

"Microplastics are everywhere—but our methods to track them are all over the place"
#Microplastics #Plastic #Plastics

Microplastics are everywhere—but our methods to track them are all over the place
A new study from the University of Portsmouth has highlighted the growing role of citizen science in tackling one of the planet's most pervasive pollution problems: microplastics and mesoplastics. While researchers often warn that a lack of standardized protocols risks muddying the waters, this research shows that public involvement could be key to plugging the data gaps and that comparability rather than conformity is key.

ODE Methods for Computing One-Dimensional Self-Motion Manifolds
Dominic Guri, George Kantor
https://arxiv.org/abs/2507.21957 https://arxiv.org/pdf/2507.219…

ODE Methods for Computing One-Dimensional Self-Motion Manifolds
Redundant manipulators are well understood to offer infinite joint configurations for achieving a desired end-effector pose. The multiplicity of inverse kinematics (IK) solutions allows for the simultaneous solving of auxiliary tasks like avoiding joint limits or obstacles. However, the most widely used IK solvers are numerical gradient-based iterative methods that inherently return a locally optimal solution. In this work, we explore the computation of self-motion manifolds (SMMs), which repre…

MedSAM-CA: A CNN-Augmented ViT with Attention-Enhanced Multi-Scale Fusion for Medical Image Segmentation
Peiting Tian, Xi Chen, Haixia Bi, Fan Li
https://arxiv.org/abs/2506.23700 …

MedSAM-CA: A CNN-Augmented ViT with Attention-Enhanced Multi-Scale Fusion for Medical Image Segmentation
Medical image segmentation plays a crucial role in clinical diagnosis and treatment planning, where accurate boundary delineation is essential for precise lesion localization, organ identification, and quantitative assessment. In recent years, deep learning-based methods have significantly advanced segmentation accuracy. However, two major challenges remain. First, the performance of these methods heavily relies on large-scale annotated datasets, which are often difficult to obtain in medical s…

SAEL: Leveraging Large Language Models with Adaptive Mixture-of-Experts for Smart Contract Vulnerability Detection
Lei Yu, Shiqi Cheng, Zhirong Huang, Jingyuan Zhang, Chenjie Shen, Junyi Lu, Li Yang, Fengjun Zhang, Jiajia Ma
https://arxiv.org/abs/2507.22371

SAEL: Leveraging Large Language Models with Adaptive Mixture-of-Experts for Smart Contract Vulnerability Detection
With the increasing security issues in blockchain, smart contract vulnerability detection has become a research focus. Existing vulnerability detection methods have their limitations: 1) Static analysis methods struggle with complex scenarios. 2) Methods based on specialized pre-trained models perform well on specific datasets but have limited generalization capabilities. In contrast, general-purpose Large Language Models (LLMs) demonstrate impressive ability in adapting to new vulnerability pa…

Iterative Methods for the Projected Solutions of Quasi-equilibrium Problems
Didier Aussel, Jauny, Asrifa Sultana, Shivani Valecha
https://arxiv.org/abs/2506.22080

Iterative Methods for the Projected Solutions of Quasi-equilibrium Problems
Aussel et al. (J Optim Theory Appl 170 818-837 2016) introduced the concept of projected solutions for the quasi-variational inequalities with a non-self constraint map, that is, the case where the constraint map may take values outside the feasible set. This paper presents two iterative methods to determine the projected solutions for quasi-equilibrium problems (QEP). We prove the convergence of the sequence generated by iterative methods to a projected solution of the QEP under some suitable …

Introduction to the Analysis of Probabilistic Decision-Making Algorithms
Agustinus Kristiadi
https://arxiv.org/abs/2508.21620 https://arxiv.org/pdf/2508.21…

Introduction to the Analysis of Probabilistic Decision-Making Algorithms
Decision theories offer principled methods for making choices under various types of uncertainty. Algorithms that implement these theories have been successfully applied to a wide range of real-world problems, including materials and drug discovery. Indeed, they are desirable since they can adaptively gather information to make better decisions in the future, resulting in data-efficient workflows. In scientific discovery, where experiments are costly, these algorithms can thus significantly red…

Accelerating MPGP-type Methods Through Preconditioning
Jakub Kru\v{z}\'ik, David Hor\'ak
https://arxiv.org/abs/2507.00617 https://

Accelerating MPGP-type Methods Through Preconditioning
This work investigates the acceleration of MPGP-type algorithms using preconditioning for the solution of quadratic programming problems. The preconditioning needs to be done only on the free set so as not to change the constraints. A variant of preconditioning restricted to the free set is the preconditioning in face. The inner preconditioner in preconditioning in face needs to be recomputed or updated every time the free set changes. Here, we investigate an approximate variant of precondition…

Multi-Method Ensemble for Out-of-Distribution Detection
Lucas Rakotoarivony
https://arxiv.org/abs/2508.21463 https://arxiv.org/pdf/2508.21463

Multi-Method Ensemble for Out-of-Distribution Detection
Detecting out-of-distribution (OOD) samples is essential for neural networks operating in open-world settings, particularly in safety-critical applications. Existing methods have improved OOD detection by leveraging two main techniques: feature truncation, which increases the separation between in-distribution (ID) and OOD samples, and scoring functions, which assign scores to distinguish between ID and OOD data. However, most approaches either focus on a single family of techniques or evaluate…

BLUEX Revisited: Enhancing Benchmark Coverage with Automatic Captioning
Jo\~ao Guilherme Alves Santos, Giovana Kerche Bon\'as, Thales Sales Almeida
https://arxiv.org/abs/2508.21294

BLUEX Revisited: Enhancing Benchmark Coverage with Automatic Captioning
With the growing capabilities of Large Language Models (LLMs), there is an increasing need for robust evaluation methods, especially in multilingual and non-English contexts. We present an updated version of the BLUEX dataset, now including 2024-2025 exams and automatically generated image captions using state-of-the-art models, enhancing its relevance for data contamination studies in LLM pretraining. Captioning strategies increase accessibility to text-only models by more than 40%, producing …

Swarm-based optimization with jumps: a kinetic BGK framework and convergence analysis
Giacomo Borghi, Hyesung Im, Lorenzo Pareschi
https://arxiv.org/abs/2507.00871

Swarm-based optimization with jumps: a kinetic BGK framework and convergence analysis
Metaheuristic algorithms are powerful tools for global optimization, particularly for non-convex and non-differentiable problems where exact methods are often impractical. Particle-based optimization methods, inspired by swarm intelligence principles, have shown effectiveness due to their ability to balance exploration and exploitation within the search space. In this work, we introduce a novel particle-based optimization algorithm where velocities are updated via random jumps, a strategy commo…

Explanations are a means to an end
Jessica Hullman, Ziyang Guo, Berk Ustun
https://arxiv.org/abs/2506.22740 https://arxiv.org/pdf/250…

Explanations are a means to an end
Modern methods for explainable machine learning are designed to describe how models map inputs to outputs--without deep consideration of how these explanations will be used in practice. This paper argues that explanations should be designed and evaluated with a specific end in mind. We describe how to formalize this end in a framework based in statistical decision theory. We show how this functionally-grounded approach can be applied across diverse use cases, such as clinical decision support, …

A new family of a posteriori error estimates for non-conforming finite element methods leading to stabilization-free error bounds
T. Chaumont-Frelet
https://arxiv.org/abs/2506.23381

A new family of a posteriori error estimates for non-conforming finite element methods leading to stabilization-free error bounds
We propose new a posteriori error estimators for non-conforming finite element discretizations of second-order elliptic PDE problems. These estimators are based on novel reformulations of the standard Prager-Synge identity, and enable to prove efficiency estimates without extra stabilization terms in the error measure for a large class of discretization schemes. We propose a residual-based estimator for which the efficiency constant scales optimally in polynomial degree, as well as two equilibr…

Activation Subspaces for Out-of-Distribution Detection
Bar{\i}\c{s} Z\"ong\"ur, Robin Hesse, Stefan Roth
https://arxiv.org/abs/2508.21695 https://

Activation Subspaces for Out-of-Distribution Detection
To ensure the reliability of deep models in real-world applications, out-of-distribution (OOD) detection methods aim to distinguish samples close to the training distribution (in-distribution, ID) from those farther away (OOD). In this work, we propose a novel OOD detection method that utilizes singular value decomposition of the weight matrix of the classification head to decompose the model's activations into decisive and insignificant components, which contribute maximally, respectively mini…

Moment Sampling in Video LLMs for Long-Form Video QA
Mustafa Chasmai, Gauri Jagatap, Gouthaman KV, Grant Van Horn, Subhransu Maji, Andrea Fanelli
https://arxiv.org/abs/2507.00033 …

Moment Sampling in Video LLMs for Long-Form Video QA
Recent advancements in video large language models (Video LLMs) have significantly advanced the field of video question answering (VideoQA). While existing methods perform well on short videos, they often struggle with long-range reasoning in longer videos. To scale Video LLMs for longer video content, frame sub-sampling (selecting frames at regular intervals) is commonly used. However, this approach is suboptimal, often leading to the loss of crucial frames or the inclusion of redundant inform…

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. …

A Structured Proximal Stochastic Variance Reduced Zeroth-order Algorithm
Marco Rando, Cheik Traor\'e, Cesare Molinari, Lorenzo Rosasco, Silvia Villa
https://arxiv.org/abs/2506.23758

A Structured Proximal Stochastic Variance Reduced Zeroth-order Algorithm
Minimizing finite sums of functions is a central problem in optimization, arising in numerous practical applications. Such problems are commonly addressed using first-order optimization methods. However, these procedures cannot be used in settings where gradient information is unavailable. Finite-difference methods provide an alternative by approximating gradients through function evaluations along a set of directions. For finite-sum minimization problems, it was shown that incorporating varian…

DLGAN : Time Series Synthesis Based on Dual-Layer Generative Adversarial Networks
Xuan Hou, Shuhan Liu, Zhaohui Peng, Yaohui Chu, Yue Zhang, Yining Wang
https://arxiv.org/abs/2508.21340

DLGAN : Time Series Synthesis Based on Dual-Layer Generative Adversarial Networks
Time series synthesis is an effective approach to ensuring the secure circulation of time series data. Existing time series synthesis methods typically perform temporal modeling based on random sequences to generate target sequences, which often struggle to ensure the temporal dependencies in the generated time series. Additionally, directly modeling temporal features on random sequences makes it challenging to accurately capture the feature information of the original time series. To address t…

SeqAffordSplat: Scene-level Sequential Affordance Reasoning on 3D Gaussian Splatting
Di Li, Jie Feng, Jiahao Chen, Weisheng Dong, Guanbin Li, Yuhui Zheng, Mingtao Feng, Guangming Shi
https://arxiv.org/abs/2507.23772

SeqAffordSplat: Scene-level Sequential Affordance Reasoning on 3D Gaussian Splatting
3D affordance reasoning, the task of associating human instructions with the functional regions of 3D objects, is a critical capability for embodied agents. Current methods based on 3D Gaussian Splatting (3DGS) are fundamentally limited to single-object, single-step interactions, a paradigm that falls short of addressing the long-horizon, multi-object tasks required for complex real-world applications. To bridge this gap, we introduce the novel task of Sequential 3D Gaussian Affordance Reasonin…

HASD: Hierarchical Adaption for pathology Slide-level Domain-shift
Jingsong Liu, Han Li, Chen Yang, Michael Deutges, Ario Sadafi, Xin You, Katharina Breininger, Nassir Navab, Peter J. Sch\"uffler
https://arxiv.org/abs/2506.23673

HASD: Hierarchical Adaption for pathology Slide-level Domain-shift
Domain shift is a critical problem for pathology AI as pathology data is heavily influenced by center-specific conditions. Current pathology domain adaptation methods focus on image patches rather than WSI, thus failing to capture global WSI features required in typical clinical scenarios. In this work, we address the challenges of slide-level domain shift by proposing a Hierarchical Adaptation framework for Slide-level Domain-shift (HASD). HASD achieves multi-scale feature consistency and comp…

Automatic discovery of optimal meta-solvers for time-dependent nonlinear PDEs
Youngkyu Lee, Shanqing Liu, Jerome Darbon, George Em Karniadakis
https://arxiv.org/abs/2507.00278

Automatic discovery of optimal meta-solvers for time-dependent nonlinear PDEs
We present a general and scalable framework for the automated discovery of optimal meta-solvers for the solution of time-dependent nonlinear partial differential equations after appropriate discretization. By integrating classical numerical methods (e.g., Krylov-based methods) with modern deep learning components, such as neural operators, our approach enables flexible, on-demand solver design tailored to specific problem classes and objectives. The fast solvers tackle the large linear system r…

Improving Aviation Safety Analysis: Automated HFACS Classification Using Reinforcement Learning with Group Relative Policy Optimization
Arash Ahmadi, Sarah Sharif, Yaser Banad
https://arxiv.org/abs/2508.21201

Improving Aviation Safety Analysis: Automated HFACS Classification Using Reinforcement Learning with Group Relative Policy Optimization
Analyzing the human factors behind aviation accidents is crucial for preventing future incidents, yet traditional methods using the Human Factors Analysis and Classification System (HFACS) are limited by scalability and consistency. To address this, we introduce an automated HFACS classification framework for aviation safety analysis that utilizes Reinforcement Learning with Group Relative Policy Optimization (GRPO) to fine-tune a Llama-3.1 8B language model. Our approach incorporates a multi-c…

Second-order methods for provably escaping strict saddle points in composite nonconvex and nonsmooth optimization
Alexander Bodard, Masoud Ahookhosh, Panagiotis Patrinos
https://arxiv.org/abs/2506.22332

Second-order methods for provably escaping strict saddle points in composite nonconvex and nonsmooth optimization
This study introduces two second-order methods designed to provably avoid saddle points in composite nonconvex optimization problems: (i) a nonsmooth trust-region method and (ii) a curvilinear linesearch method. These developments are grounded in the forward-backward envelope (FBE), for which we analyze the local second-order differentiability around critical points and establish a novel equivalence between its second-order stationary points and those of the original objective. We show that the…

Genuinely multi-dimensional stationarity preserving global flux Finite Volume formulation for nonlinear hyperbolic PDEs
Wasilij Barsukow, Mirco Ciallella, Mario Ricchiuto, Davide Torlo
https://arxiv.org/abs/2506.21700

Genuinely multi-dimensional stationarity preserving global flux Finite Volume formulation for nonlinear hyperbolic PDEs
Classical Finite Volume methods for multi-dimensional problems include stabilization (e.g. via a Riemann solver), that is derived by considering several one-dimensional problems in different directions. Such methods therefore ignore a possibly existing balance of contributions coming from different directions, such as the one characterizing multi-dimensional stationary states. Instead being preserved, they are usually diffused away by such methods. Stationarity preserving methods use a better s…

Physics-Informed Spectral Modeling for Hyperspectral Imaging
Zuzanna Gawrysiak, Krzysztof Krawiec
https://arxiv.org/abs/2508.21618 https://arxiv.org/pdf/25…

Physics-Informed Spectral Modeling for Hyperspectral Imaging
We present PhISM, a physics-informed deep learning architecture that learns without supervision to explicitly disentangle hyperspectral observations and model them with continuous basis functions. \mname outperforms prior methods on several classification and regression benchmarks, requires limited labeled data, and provides additional insights thanks to interpretable latent representation.

TMUAD: Enhancing Logical Capabilities in Unified Anomaly Detection Models with a Text Memory Bank
Jiawei Liu, Jiahe Hou, Wei Wang, Jinsong Du, Yang Cong, Huijie Fan
https://arxiv.org/abs/2508.21795

TMUAD: Enhancing Logical Capabilities in Unified Anomaly Detection Models with a Text Memory Bank
Anomaly detection, which aims to identify anomalies deviating from normal patterns, is challenging due to the limited amount of normal data available. Unlike most existing unified methods that rely on carefully designed image feature extractors and memory banks to capture logical relationships between objects, we introduce a text memory bank to enhance the detection of logical anomalies. Specifically, we propose a Three-Memory framework for Unified structural and logical Anomaly Detection (TMUA…

CooT: Learning to Coordinate In-Context with Coordination Transformers
Huai-Chih Wang, Hsiang-Chun Chuang, Hsi-Chun Cheng, Dai-Jie Wu, Shao-Hua Sun
https://arxiv.org/abs/2506.23549

CooT: Learning to Coordinate In-Context with Coordination Transformers
Effective coordination among artificial agents in dynamic and uncertain environments remains a significant challenge in multi-agent systems. Existing approaches, such as self-play and population-based methods, either generalize poorly to unseen partners or require extensive training. To overcome these limitations, we propose Coordination Transformers (CooT), a novel in-context coordination framework that uses recent interaction histories to adapt to unseen partners rapidly. Unlike previous appr…

Decoding Memories: An Efficient Pipeline for Self-Consistency Hallucination Detection
Weizhi Gao, Xiaorui Liu, Feiyi Wang, Dan Lu, Junqi Yin
https://arxiv.org/abs/2508.21228 htt…

Decoding Memories: An Efficient Pipeline for Self-Consistency Hallucination Detection
Large language models (LLMs) have demonstrated impressive performance in both research and real-world applications, but they still struggle with hallucination. Existing hallucination detection methods often perform poorly on sentence-level generation or rely heavily on domain-specific knowledge. While self-consistency approaches help address these limitations, they incur high computational costs due to repeated generation. In this paper, we conduct the first study on identifying redundancy in s…

Parallel block coordinate descent methods with identification strategies
Rolando Lopes, Sandra A. Santos, Paulo J. S. Silva
https://arxiv.org/abs/2507.22277 https://

Parallel block coordinate descent methods with identification strategies
This work presents a parallel variant of the algorithm introduced in [Acceleration of block coordinate descent methods with identification strategies Comput. Optim. Appl. 72(3):609--640, 2019] to minimize the sum of a partially separable smooth convex function and a possibly non-smooth block-separable convex function under simple constraints. It achieves better efficiency by using a strategy to identify the nonzero coordinates that allows the computational effort to be focused on using a nonuni…

Learning from Silence and Noise for Visual Sound Source Localization
Xavier Juanola, Giovana Morais, Magdalena Fuentes, Gloria Haro
https://arxiv.org/abs/2508.21761 https://

Learning from Silence and Noise for Visual Sound Source Localization
Visual sound source localization is a fundamental perception task that aims to detect the location of sounding sources in a video given its audio. Despite recent progress, we identify two shortcomings in current methods: 1) most approaches perform poorly in cases with low audio-visual semantic correspondence such as silence, noise, and offscreen sounds, i.e. in the presence of negative audio; and 2) most prior evaluations are limited to positive cases, where both datasets and metrics convey sce…

Failure Prediction Is a Better Performance Proxy for Early-Exit Networks Than Calibration
Piotr Kubaty, Filip Szatkowski, Metod Jazbec, Bartosz W\'ojcik
https://arxiv.org/abs/2508.21495

Failure Prediction Is a Better Performance Proxy for Early-Exit Networks Than Calibration
Early-exit models speed up inference by attaching internal classifiers to intermediate layers of the model and allowing computation to stop once a prediction satisfies an exit criterion. Most early-exit methods rely on confidence-based exit strategies, which motivated some works to calibrate intermediate classifiers to improve the performance of the entire model. In this paper, we show that calibration measures can be misleading indicators of the performance of multi-exit models: a well-calibra…

Role-Aware Language Models for Secure and Contextualized Access Control in Organizations
Saeed Almheiri, Yerulan Kongrat, Adrian Santosh, Ruslan Tasmukhanov, Josemaria Vera, Muhammad Dehan Al Kautsar, Fajri Koto
https://arxiv.org/abs/2507.23465

Role-Aware Language Models for Secure and Contextualized Access Control in Organizations
As large language models (LLMs) are increasingly deployed in enterprise settings, controlling model behavior based on user roles becomes an essential requirement. Existing safety methods typically assume uniform access and focus on preventing harmful or toxic outputs, without addressing role-specific access constraints. In this work, we investigate whether LLMs can be fine-tuned to generate responses that reflect the access privileges associated with different organizational roles. We explore t…

Augmented Lagrangian methods for infeasible convex optimization problems and diverging proximal-point algorithms
Roland Andrews, Justin Carpentier, Adrien Taylor
https://arxiv.org/abs/2506.22428

Augmented Lagrangian methods for infeasible convex optimization problems and diverging proximal-point algorithms
This work investigates the convergence behavior of augmented Lagrangian methods (ALMs) when applied to convex optimization problems that may be infeasible. ALMs are a popular class of algorithms for solving constrained optimization problems. We establish progressively stronger convergence results, ranging from basic sequence convergence to precise convergence rates, under a hierarchy of assumptions. In particular, we demonstrate that, under mild assumptions, the sequences of iterates generated …

Benchmarking GPT-5 in Radiation Oncology: Measurable Gains, but Persistent Need for Expert Oversight
Ugur Dinc, Jibak Sarkar, Philipp Schubert, Sabine Semrau, Thomas Weissmann, Andre Karius, Johann Brand, Bernd-Niklas Axer, Ahmed Gomaa, Pluvio Stephan, Ishita Sheth, Sogand Beirami, Annette Schwarz, Udo Gaipl, Benjamin Frey, Christoph Bert, Stefanie Corradini, Rainer Fietkau, Florian Putz

Benchmarking GPT-5 in Radiation Oncology: Measurable Gains, but Persistent Need for Expert Oversight
Introduction: Large language models (LLM) have shown great potential in clinical decision support. GPT-5 is a novel LLM system that has been specifically marketed towards oncology use. Methods: Performance was assessed using two complementary benchmarks: (i) the ACR Radiation Oncology In-Training Examination (TXIT, 2021), comprising 300 multiple-choice items, and (ii) a curated set of 60 authentic radiation oncologic vignettes representing diverse disease sites and treatment indications. For …

Hypernetworks for Model-Heterogeneous Personalized Federated Learning
Chen Zhang, Husheng Li, Xiang Liu, Linshan Jiang, Danxin Wang
https://arxiv.org/abs/2507.22330 https://

Hypernetworks for Model-Heterogeneous Personalized Federated Learning
Recent advances in personalized federated learning have focused on addressing client model heterogeneity. However, most existing methods still require external data, rely on model decoupling, or adopt partial learning strategies, which can limit their practicality and scalability. In this paper, we revisit hypernetwork-based methods and leverage their strong generalization capabilities to design a simple yet effective framework for heterogeneous personalized federated learning. Specifically, we…

Helmholtz boundary integral methods and the pollution effect
Jeffrey Galkowski, Manas Rachh, Euan A. Spence
https://arxiv.org/abs/2507.22797 https://arxiv.…

Helmholtz boundary integral methods and the pollution effect
This paper is concerned with solving the Helmholtz exterior Dirichlet and Neumann problems with large wavenumber $k$ and smooth obstacles using the standard second-kind boundary integral equations (BIEs) for these problems. We consider Galerkin and collocation methods - with subspaces consisting of $\textit{either}$ piecewise polynomials (in 2-d for collocation, in any dimension for Galerkin) $\textit{or}$ trigonometric polynomials (in 2-d) - as well as a fully discrete quadrature (a.k.a., Nyst…

Regularized Extragradient Methods for Solving Equilibrium Problems on Hadamard Manifolds
Shikher Sharmaa, Pankaj Gautam, Simeon Reich
https://arxiv.org/abs/2506.22391

Regularized Extragradient Methods for Solving Equilibrium Problems on Hadamard Manifolds
Employing two distinct types of regularization terms, we propose two regularized extragradient methods for solving equilibrium problems on Hadamard manifolds. The sequences generated by these extragradient algorithms converge to a solution of the equilibrium problem without requiring the Lipschitz continuity of the bifunction or imposing additional conditions on the parameters. We establish convergence results for both algorithms and derive global error bounds along with $R$-linear convergence …

LitBench: A Benchmark and Dataset for Reliable Evaluation of Creative Writing
Daniel Fein, Sebastian Russo, Violet Xiang, Kabir Jolly, Rafael Rafailov, Nick Haber
https://arxiv.org/abs/2507.00769

LitBench: A Benchmark and Dataset for Reliable Evaluation of Creative Writing
Evaluating creative writing generated by large language models (LLMs) remains challenging because open-ended narratives lack ground truths. Without performant automated evaluation methods, off-the-shelf (OTS) language models are employed as zero-shot judges, yet their reliability is unclear in this context. In pursuit of robust evaluation for creative writing, we introduce LitBench, the first standardized benchmark and paired dataset for creative writing verification, comprising a held-out test…

Towards Interactive Lesion Segmentation in Whole-Body PET/CT with Promptable Models
Maximilian Rokuss, Yannick Kirchhoff, Fabian Isensee, Klaus H. Maier-Hein
https://arxiv.org/abs/2508.21680

Towards Interactive Lesion Segmentation in Whole-Body PET/CT with Promptable Models
Whole-body PET/CT is a cornerstone of oncological imaging, yet accurate lesion segmentation remains challenging due to tracer heterogeneity, physiological uptake, and multi-center variability. While fully automated methods have advanced substantially, clinical practice benefits from approaches that keep humans in the loop to efficiently refine predicted masks. The autoPET/CT IV challenge addresses this need by introducing interactive segmentation tasks based on simulated user prompts. In this w…

Limitations of Physics-Informed Neural Networks: a Study on Smart Grid Surrogation
Julen Cestero, Carmine Delle Femine, Kenji S. Muro, Marco Quartulli, Marcello Restelli
https://arxiv.org/abs/2508.21559

Limitations of Physics-Informed Neural Networks: a Study on Smart Grid Surrogation
Physics-Informed Neural Networks (PINNs) present a transformative approach for smart grid modeling by integrating physical laws directly into learning frameworks, addressing critical challenges of data scarcity and physical consistency in conventional data-driven methods. This paper evaluates PINNs' capabilities as surrogate models for smart grid dynamics, comparing their performance against XGBoost, Random Forest, and Linear Regression across three key experiments: interpolation, cross-validat…

Computational Detection of Intertextual Parallels in Biblical Hebrew: A Benchmark Study Using Transformer-Based Language Models
David M. Smiley
https://arxiv.org/abs/2506.24117

Computational Detection of Intertextual Parallels in Biblical Hebrew: A Benchmark Study Using Transformer-Based Language Models
Identifying parallel passages in biblical Hebrew is foundational in biblical scholarship for uncovering intertextual relationships. Traditional methods rely on manual comparison, which is labor-intensive and prone to human error. This study evaluates the potential of pre-trained transformer-based language models, including E5, AlephBERT, MPNet, and LaBSE, for detecting textual parallels in the Hebrew Bible. Focusing on known parallels between the books of Samuel/Kings and Chronicles, I assessed…

Temporal Flow Matching for Learning Spatio-Temporal Trajectories in 4D Longitudinal Medical Imaging
Nico Albert Disch, Yannick Kirchhoff, Robin Peretzke, Maximilian Rokuss, Saikat Roy, Constantin Ulrich, David Zimmerer, Klaus Maier-Hein
https://arxiv.org/abs/2508.21580

Temporal Flow Matching for Learning Spatio-Temporal Trajectories in 4D Longitudinal Medical Imaging
Understanding temporal dynamics in medical imaging is crucial for applications such as disease progression modeling, treatment planning and anatomical development tracking. However, most deep learning methods either consider only single temporal contexts, or focus on tasks like classification or regression, limiting their ability for fine-grained spatial predictions. While some approaches have been explored, they are often limited to single timepoints, specific diseases or have other technical …

Multi-Hazard Early Warning Systems for Agriculture with Featural-Temporal Explanations
Boyuan Zheng, Victor W. Chu
https://arxiv.org/abs/2507.22962 https://

Multi-Hazard Early Warning Systems for Agriculture with Featural-Temporal Explanations
Climate extremes present escalating risks to agriculture intensifying the need for reliable multi-hazard early warning systems (EWS). The situation is evolving due to climate change and hence such systems should have the intelligent to continue to learn from recent climate behaviours. However, traditional single-hazard forecasting methods fall short in capturing complex interactions among concurrent climatic events. To address this deficiency, in this paper, we combine sequential deep learning …

AllSummedUp: un framework open-source pour comparer les metriques d'evaluation de resume
Tanguy Herserant, Vincent Guigue
https://arxiv.org/abs/2508.21389 https://

AllSummedUp: un framework open-source pour comparer les metriques d'evaluation de resume
This paper investigates reproducibility challenges in automatic text summarization evaluation. Based on experiments conducted across six representative metrics ranging from classical approaches like ROUGE to recent LLM-based methods (G-Eval, SEval-Ex), we highlight significant discrepancies between reported performances in the literature and those observed in our experimental setting. We introduce a unified, open-source framework, applied to the SummEval dataset and designed to support fair and…

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[8/9]:
- Benchmarking Spiking Neural Network Learning Methods with Varying Locality
Jiaqi Lin, Sen Lu, Malyaban Bal, Abhronil Sengupta

Learning Unified Representations from Heterogeneous Data for Robust Heart Rate Modeling
Peng Yang, Zhengdong Huang, Zicheng Xie, Wentao Tian, Jingyu Liu, Lunhong Dong
https://arxiv.org/abs/2508.21785

Learning Unified Representations from Heterogeneous Data for Robust Heart Rate Modeling
Heart rate prediction is vital for personalized health monitoring and fitness, while it frequently faces a critical challenge when deploying in real-world: data heterogeneity. We classify it in two key dimensions: source heterogeneity from fragmented device markets with varying feature sets, and user heterogeneity reflecting distinct physiological patterns across individuals and activities. Existing methods either discard device-specific information, or fail to model user-specific differences, …

Adversarial Patch Attack for Ship Detection via Localized Augmentation
Chun Liu, Panpan Ding, Zheng Zheng, Hailong Wang, Bingqian Zhu, Tao Xu, Zhigang Han, Jiayao Wang
https://arxiv.org/abs/2508.21472 …

Adversarial Patch Attack for Ship Detection via Localized Augmentation
Current ship detection techniques based on remote sensing imagery primarily rely on the object detection capabilities of deep neural networks (DNNs). However, DNNs are vulnerable to adversarial patch attacks, which can lead to misclassification by the detection model or complete evasion of the targets. Numerous studies have demonstrated that data transformation-based methods can improve the transferability of adversarial examples. However, excessive augmentation of image backgrounds or irreleva…

Hierarchical Adversarially-Resilient Multi-Agent Reinforcement Learning for Cyber-Physical Systems Security
Saad Alqithami
https://arxiv.org/abs/2506.22445

Hierarchical Adversarially-Resilient Multi-Agent Reinforcement Learning for Cyber-Physical Systems Security
Cyber-Physical Systems play a critical role in the infrastructure of various sectors, including manufacturing, energy distribution, and autonomous transportation systems. However, their increasing connectivity renders them highly vulnerable to sophisticated cyber threats, such as adaptive and zero-day attacks, against which traditional security methods like rule-based intrusion detection and single-agent reinforcement learning prove insufficient. To overcome these challenges, this paper introdu…

Mapping like a Skeptic: Probabilistic BEV Projection for Online HD Mapping
Fatih Erdo\u{g}an, Merve Rabia Bar{\i}n, Fatma G\"uney
https://arxiv.org/abs/2508.21689 https://

Mapping like a Skeptic: Probabilistic BEV Projection for Online HD Mapping
Constructing high-definition (HD) maps from sensory input requires accurately mapping the road elements in image space to the Bird's Eye View (BEV) space. The precision of this mapping directly impacts the quality of the final vectorized HD map. Existing HD mapping approaches outsource the projection to standard mapping techniques, such as attention-based ones. However, these methods struggle with accuracy due to generalization problems, often hallucinating non-existent road elements. Our key i…

Quantum enhanced ensemble GANs for anomaly detection in continuous biomanufacturing
Rajiv Kailasanathan, William R. Clements, Mohammad Reza Boskabadi, Shawn M. Gibford, Emmanouil Papadakis, Christopher J. Savoie, Seyed Soheil Mansouri
https://arxiv.org/abs/2508.21438

Quantum enhanced ensemble GANs for anomaly detection in continuous biomanufacturing
The development of continuous biomanufacturing processes requires robust and early anomaly detection, since even minor deviations can compromise yield and stability, leading to disruptions in scheduling, reduced weekly production, and diminished economic performance. These processes are inherently complex and exhibit non-linear dynamics with intricate relationships between process variables, thus making advanced methods for anomaly detection essential for efficient operation. In this work, we p…

Entropy-Based Non-Invasive Reliability Monitoring of Convolutional Neural Networks
Amirhossein Nazeri, Wael Hafez
https://arxiv.org/abs/2508.21715 https://…

Entropy-Based Non-Invasive Reliability Monitoring of Convolutional Neural Networks
Convolutional Neural Networks (CNNs) have become the foundation of modern computer vision, achieving unprecedented accuracy across diverse image recognition tasks. While these networks excel on in-distribution data, they remain vulnerable to adversarial perturbations imperceptible input modifications that cause misclassification with high confidence. However, existing detection methods either require expensive retraining, modify network architecture, or degrade performance on clean inputs. Here…

Latent Factorization of Tensors with Threshold Distance Weighted Loss for Traffic Data Estimation
Lei Yang
https://arxiv.org/abs/2506.22441 https://…

Latent Factorization of Tensors with Threshold Distance Weighted Loss for Traffic Data Estimation
Intelligent transportation systems (ITS) rely heavily on complete and high-quality spatiotemporal traffic data to achieve optimal performance. Nevertheless, in real-word traffic data collection processes, issues such as communication failures and sensor malfunctions often lead to incomplete or corrupted datasets, thereby posing significant challenges to the advancement of ITS. Among various methods for imputing missing spatiotemporal traffic data, the latent factorization of tensors (LFT) model…

HCCM: Hierarchical Cross-Granularity Contrastive and Matching Learning for Natural Language-Guided Drones
Hao Ruan, Jinliang Lin, Yingxin Lai, Zhiming Luo, Shaozi Li
https://arxiv.org/abs/2508.21539

HCCM: Hierarchical Cross-Granularity Contrastive and Matching Learning for Natural Language-Guided Drones
Natural Language-Guided Drones (NLGD) provide a novel paradigm for tasks such as target matching and navigation. However, the wide field of view and complex compositional semantics in drone scenarios pose challenges for vision-language understanding. Mainstream Vision-Language Models (VLMs) emphasize global alignment while lacking fine-grained semantics, and existing hierarchical methods depend on precise entity partitioning and strict containment, limiting effectiveness in dynamic environments…

Modality-Aware Feature Matching: A Comprehensive Review of Single- and Cross-Modality Techniques
Weide Liu, Wei Zhou, Jun Liu, Ping Hu, Jun Cheng, Jungong Han, Weisi Lin
https://arxiv.org/abs/2507.22791

Modality-Aware Feature Matching: A Comprehensive Review of Single- and Cross-Modality Techniques
Feature matching is a cornerstone task in computer vision, essential for applications such as image retrieval, stereo matching, 3D reconstruction, and SLAM. This survey comprehensively reviews modality-based feature matching, exploring traditional handcrafted methods and emphasizing contemporary deep learning approaches across various modalities, including RGB images, depth images, 3D point clouds, LiDAR scans, medical images, and vision-language interactions. Traditional methods, leveraging de…

Complete Gaussian Splats from a Single Image with Denoising Diffusion Models
Ziwei Liao, Mohamed Sayed, Steven L. Waslander, Sara Vicente, Daniyar Turmukhambetov, Michael Firman
https://arxiv.org/abs/2508.21542

Complete Gaussian Splats from a Single Image with Denoising Diffusion Models
Gaussian splatting typically requires dense observations of the scene and can fail to reconstruct occluded and unobserved areas. We propose a latent diffusion model to reconstruct a complete 3D scene with Gaussian splats, including the occluded parts, from only a single image during inference. Completing the unobserved surfaces of a scene is challenging due to the ambiguity of the plausible surfaces. Conventional methods use a regression-based formulation to predict a single "mode" for occluded…