Tootfinder

Throttling Web Agents Using Reasoning Gates
Abhinav Kumar, Jaechul Roh, Ali Naseh, Amir Houmansadr, Eugene Bagdasarian
https://arxiv.org/abs/2509.01619 https://

Throttling Web Agents Using Reasoning Gates
AI web agents use Internet resources at far greater speed, scale, and complexity -- changing how users and services interact. Deployed maliciously or erroneously, these agents could overload content providers. At the same time, web agents can bypass CAPTCHAs and other defenses by mimicking user behavior or flood authentication systems with fake accounts. Yet providers must protect their services and content from denial-of-service attacks and scraping by web agents. In this paper, we design a fr…

Taking a SEAT: Predicting Value Interpretations from Sentiment, Emotion, Argument, and Topic Annotations
Adina Nicola Dobrinoiu, Ana Cristiana Marcu, Amir Homayounirad, Luciano Cavalcante Siebert, Enrico Liscio
https://arxiv.org/abs/2510.01976

Taking a SEAT: Predicting Value Interpretations from Sentiment, Emotion, Argument, and Topic Annotations
Our interpretation of value concepts is shaped by our sociocultural background and lived experiences, and is thus subjective. Recognizing individual value interpretations is important for developing AI systems that can align with diverse human perspectives and avoid bias toward majority viewpoints. To this end, we investigate whether a language model can predict individual value interpretations by leveraging multi-dimensional subjective annotations as a proxy for their interpretive lens. That i…

A LYM Inequality For Product Measures
Gal Yehuda, Amir Yehudayoff
https://arxiv.org/abs/2509.01160 https://arxiv.org/pdf/2509.01160

A LYM Inequality For Product Measures
This note proves a version of Lubell-Yamamoto-Meshalkin inequality for general product measures.

Fragility Analysis of Data-Driven Feedback Gains
Yongzhang Li, Amir Shakouri, M. Kanat Camlibel
https://arxiv.org/abs/2510.00717 https://arxiv.org/pdf/2510…

Fragility Analysis of Data-Driven Feedback Gains
For linear time-invariant systems, input-state data collected during an open-loop experiment can remedy the lack of knowledge of system parameters. However, such data do not contain information about other system uncertainties such as feedback perturbations. In this paper, we study the effect of additive perturbations on control parameters in a data-based setting. To this end, we parameterize the set of quadratically stabilizing feedback gains obtained from noisy input-state data. We study the …

Hierarchical Maximum Entropy via the Renormalization Group
Amir R. Asadi
https://arxiv.org/abs/2509.01424 https://arxiv.org/pdf/2509.01424

Hierarchical Maximum Entropy via the Renormalization Group
Hierarchical structures, which include multiple levels, are prevalent in statistical and machine-learning models as well as physical systems. Extending the foundational result that the maximum entropy distribution under mean constraints is given by the exponential Gibbs-Boltzmann form, we introduce the framework of "hierarchical maximum entropy" to address these multilevel models. We demonstrate that Pareto optimal distributions, which maximize entropies across all levels of hierarchical transf…

Bounds on SMEFT affecting multi gauge and Higgs-gauge couplings using two and three body spin correlations in $e^-e^ \to 3l2j\slashed{E}$ process
Amir Subba, Ritesh K. Singh
https://arxiv.org/abs/2509.01452

Bounds on SMEFT affecting multi gauge and Higgs-gauge couplings using two and three body spin correlations in $e^-e^+\to 3l2j\slashed{E}$ process
The upcoming electron-positron collider provides an ideal place to probe deviation from the Standard Model predictions with its clean environment, beam polarization and significant luminosity. We studied anomalous quartic gauge boson couplings~($VVW^-W^+, V\in\{γ,Z\}$), triple gauge couplings~($W^-W^+γ/Z)$, and Higgs-gauge couplings $(HVV, V\in\{W^\pm,Z,γ\}$) induced by $SU(2)_L \times U(1)_Y$ gauge invariant dimension-6 operators in $3l2j\slashed{E}$ final events with initial beam polarizat…

Robustness of classical nucleation theory to chemical heterogeneity of crystal nucleating substrates
Fernanda Sulantay Vargas, Sarwar Hussain, Amir Haji-Akbari
https://arxiv.org/abs/2510.01420

Robustness of classical nucleation theory to chemical heterogeneity of crystal nucleating substrates
Heterogeneous nucleation is a process wherein extrinsic impurities facilitate freezing by lowering nucleation barriers and constitutes the dominant mechanism for crystallization in most systems. Classical nucleation theory (\textsc{Cnt}) has been remarkably successful in predicting the kinetics of heterogeneous nucleation, even on chemically and topographically non-uniform surfaces, despite its reliance on several restrictive assumptions, such as the idealized spherical-cap geometry of the crys…

Crosslisted article(s) found for cond-mat.stat-mech. https://arxiv.org/list/cond-mat.stat-mech/new
[1/1]:
- Robustness of classical nucleation theory to chemical heterogeneity of crystal nucleating substrates
Fernanda Sulantay Vargas, Sarwar Hussain, Amir Haji-Akbari

Crosslisted article(s) found for physics.flu-dyn. https://arxiv.org/list/physics.flu-dyn/new
[1/1]:
- RheOFormer: A generative transformer model for simulation of complex fluids and flows
Maedeh Saberi, Amir Barati Farimani, Safa Jamali

Replaced article(s) found for astro-ph.IM. https://arxiv.org/list/astro-ph.IM/new
[1/1]:
- Toward a Robust R2D2 Paradigm for Radio-interferometric Imaging: Revisiting Deep Neural Network T...
Amir Aghabiglou, Chung San Chu, Chao Tang, Arwa Dabbech, Yves Wiaux

Mamba Outpaces Reformer in Stock Prediction with Sentiments from Top Ten LLMs
Lokesh Antony Kadiyala, Amir Mirzaeinia
https://arxiv.org/abs/2510.01203 https://

Mamba Outpaces Reformer in Stock Prediction with Sentiments from Top Ten LLMs
The stock market is extremely difficult to predict in the short term due to high market volatility, changes caused by news, and the non-linear nature of the financial time series. This research proposes a novel framework for improving minute-level prediction accuracy using semantic sentiment scores from top ten different large language models (LLMs) combined with minute interval intraday stock price data. We systematically constructed a time-aligned dataset of AAPL news articles and 1-minute Ap…

SHERPA: A Model-Driven Framework for Large Language Model Execution
Boqi Chen, Kua Chen, Jos\'e Antonio Hern\'andez L\'opez, Gunter Mussbacher, D\'aniel Varr\'o, Amir Feizpour
https://arxiv.org/abs/2509.00272

SHERPA: A Model-Driven Framework for Large Language Model Execution
Recently, large language models (LLMs) have achieved widespread application across various fields. Despite their impressive capabilities, LLMs suffer from a lack of structured reasoning ability, particularly for complex tasks requiring domain-specific best practices, which are often unavailable in the training data. Although multi-step prompting methods incorporating human best practices, such as chain-of-thought and tree-of-thought, have gained popularity, they lack a general mechanism to cont…

Insights into the Structure and Dynamics of Water at Co$_3$O$_4$(001) Using a High-Dimensional Neural Network Potential
Amir Omranpour, J\"org Behler
https://arxiv.org/abs/2509.00322

Insights into the Structure and Dynamics of Water at Co$_3$O$_4$(001) Using a High-Dimensional Neural Network Potential
Co$_3$O$_4$ is an important catalyst for the oxidation of organic molecules in the liquid phase. Still, understanding the atomistic details of Co$_3$O$_4$-water interfaces under operando conditions remains extremely challenging. While ab initio molecular dynamics have become an essential tool for investigating these dynamic interfaces in silico, they are limited to only a few picoseconds and a few hundred atoms. In this work, we overcome these limitations by training a high-dimensional neural n…

Contest vs. Competition in Cournot Duopoly: Schaffer's Paradox
Rabah Amir, Igor V. Evstigneev, Mikhail V. Zhitlukhin
https://arxiv.org/abs/2509.00960 https://

Contest vs. Competition in Cournot Duopoly: Schaffer's Paradox
The paper compares two types of industrial organization in the Cournot duopoly: (a) the classical one, where the market players maximize profits and the outcome of the game is a Cournot-Nash equilibrium; (b) a contest in which players strive to win a fixed prize/bonus employing unbeatable strategies. Passing from (a) to (b) leads to a perfect competition with zero profits of the players (Schaffer's paradox). Transition from (b) to (a) results in a substantial decline in the production output, w…

Replaced article(s) found for math.FA. https://arxiv.org/list/math.FA/new
[1/1]:
- Refined general weighted $L^{p}$-Hardy and Caffarelli-Kohn-Nirenberg type inequalities and identi...
Nurgissa Yessirkegenov, Amir Zhangirbayev

Replaced article(s) found for cs.PL. https://arxiv.org/list/cs.PL/new
[1/1]:
- Ranking Functions for Linear-Constraint Loops
Amir M. Ben-Amram, Samir Genaim
https:…

Low-power integrated optical parametric amplification via second-harmonic resonance
Devin J. Dean, Taewon Park, Hubert S. Stokowski, Luke Qi, Sam Robison, Alexander Y. Hwang, Jason Herrmann, Martin M. Fejer, Amir H. Safavi-Naeini
https://arxiv.org/abs/2509.26425

Low-power integrated optical parametric amplification via second-harmonic resonance
Optical amplifiers are fundamental to modern photonics, enabling long-distance communications, precision sensing, and quantum information processing. Erbium-doped amplifiers dominate telecommunications but are restricted to specific wavelength bands, while semiconductor amplifiers offer broader coverage but suffer from high noise and nonlinear distortions. Optical parametric amplifiers (OPAs) promise broadband, quantum-limited amplification across arbitrary wavelengths. However, their miniaturi…

Tidal disruption of a magnetized star
Pavel Abolmasov, Omer Bromberg, Amir Levinson, Ehud Nakar
https://arxiv.org/abs/2509.23894 https://arxiv.org/pdf/2509…

Tidal disruption of a magnetized star
Tidal disruptions of stars by supermassive black holes in galactic centers (TDEs) are now being actively studied both theoretically and observationally. They are observed throughout the electromagnetic spectrum, from radio to gamma-rays. It is still unclear how the emission is produced and, in particular, what is the role of the magnetic field of the disrupted star. There are many ways how magnetic fields might affect the dynamics of a TDE. They are likely responsible for the angular momentum t…

Replaced article(s) found for cs.AR. https://arxiv.org/list/cs.AR/new
[1/1]:
- OptGM: An Optimized Gate Merging Method to Mitigate NBTI in Digital Circuits
Maryam Ghane, Amir M. Hajisadeghi, Hamid R. Zarandi

Domain Boundaries in a Metallic Distortive Polar Metal
Adrian Savovici, Barak Ratzker, Xuyang Zhou, Stefan Zaefferer, Martina Ruffino, Iliya Radulov, Patricia Jovi\v{c}evi\'c-Klug, Shyam Katnagallu, Amir Hamzehei, Philipp Watermeyer, Alexandra Vogel, J\"org Neugebauer, Christoph Freysoldt, Dierk Raabe
https://arxiv.org/abs/2509.23…

Domain Boundaries in a Metallic Distortive Polar Metal
Polar metals are an underexplored material class combining two properties that are typically incompatible, namely a polar crystal structure and reasonable electrical conductivity. While intriguing given that metals favor centrosymmetry, these materials also exhibit potential functional properties relevant to memory, optoelectronic, catalytic, and other applications. The distortive polar metal (DPM) subclass forms through a centrosymmetry-lifting phase transformation into a polar crystal structu…

Symmetry enforces entanglement at high temperatures
Amir-Reza Negari, Leonardo A. Lessa, Subhayan Sahu
https://arxiv.org/abs/2508.20166 https://arxiv.org/p…

Symmetry enforces entanglement at high temperatures
Many-body quantum systems with local interactions undergo "sudden death of entanglement" at high temperatures, whereby thermal states become classical mixtures of product states. We investigate whether symmetry constraints can prevent this phenomenon. We prove that strongly symmetric thermal states (canonical ensemble) of generic Hamiltonians with on-site Abelian symmetries remain entangled with non-zero entanglement negativity at arbitrarily high temperatures, under mild conditions on the symm…

Network-Level Prompt and Trait Leakage in Local Research Agents
Hyejun Jeong, Mohammadreze Teymoorianfard, Abhinav Kumar, Amir Houmansadr, Eugene Badasarian
https://arxiv.org/abs/2508.20282

Network-Level Prompt and Trait Leakage in Local Research Agents
We show that Web and Research Agents (WRAs) -- language model-based systems that investigate complex topics on the Internet -- are vulnerable to inference attacks by passive network adversaries such as ISPs. These agents could be deployed \emph{locally} by organizations and individuals for privacy, legal, or financial purposes. Unlike sporadic web browsing by humans, WRAs visit $70{-}140$ domains with distinguishable timing correlations, enabling unique fingerprinting attacks. Specifically, w…

Stable coresets: Unleashing the power of uniform sampling
Amir Carmel, Robert Krauthgamer
https://arxiv.org/abs/2509.22189 https://arxiv.org/pdf/2509.22189…

Stable coresets: Unleashing the power of uniform sampling
Uniform sampling is a highly efficient method for data summarization. However, its effectiveness in producing coresets for clustering problems is not yet well understood, primarily because it generally does not yield a strong coreset, which is the prevailing notion in the literature. We formulate \emph{stable coresets}, a notion that is intermediate between the standard notions of weak and strong coresets, and effectively combines the broad applicability of strong coresets with highly efficient…

Circuit Distillation
Somin Wadhwa, Silvio Amir, Byron C. Wallace
https://arxiv.org/abs/2509.25002 https://arxiv.org/pdf/2509.25002

Circuit Distillation
Model distillation typically focuses on behavioral mimicry, where a student model is trained to replicate a teacher's output while treating its internal computations as a black box. In this work we propose an alternative approach: Distilling the underlying computational mechanisms implemented by a teacher model. Specifically, we propose circuit distillation, which introduces an objective to align internal representations between analogous circuit components in teacher and student models. We pro…

Crosslisted article(s) found for astro-ph.GA. https://arxiv.org/list/astro-ph.GA/new
[1/1]:
- Tidal disruption of a magnetized star
Pavel Abolmasov, Omer Bromberg, Amir Levinson, Ehud Nakar

OffTopicEval: When Large Language Models Enter the Wrong Chat, Almost Always!
Jingdi Lei, Varun Gumma, Rishabh Bhardwaj, Seok Min Lim, Chuan Li, Amir Zadeh, Soujanya Poria
https://arxiv.org/abs/2509.26495

OffTopicEval: When Large Language Models Enter the Wrong Chat, Almost Always!
Large Language Model (LLM) safety is one of the most pressing challenges for enabling wide-scale deployment. While most studies and global discussions focus on generic harms, such as models assisting users in harming themselves or others, enterprises face a more fundamental concern: whether LLM-based agents are safe for their intended use case. To address this, we introduce operational safety, defined as an LLM's ability to appropriately accept or refuse user queries when tasked with a specific…

Semi-Supervised Radiomics for Glioblastoma IDH Mutation: Limited Labels, Data Sensitivity, and SHAP Interpretation
Amir Hossein Pouria, Sajad Jabarzadeh Ghandilu, Shahram Taeb, Somayeh Sadat Mehrnia, Mehrdad Oveisi, Arman Rahmim, Mohammad R. Salmanpour
https://arxiv.org/abs/2509.25641

Semi-Supervised Radiomics for Glioblastoma IDH Mutation: Limited Labels, Data Sensitivity, and SHAP Interpretation
Glioblastoma (GBM) is an aggressive brain tumor in which IDH mutation status is a key prognostic biomarker, but traditional testing requires invasive biopsies, emphasizing the need for non-invasive approaches. In this multi-center study, we analyzed MRI sequences (T1, T2-weighted, contrast-enhanced T1, and FLAIR) from 1,329 patients across eight centers, with IDH labels available for 1,061 cases. A total of 1,223 radiomic features per case were extracted using PyRadiomics with Laplacian of Gaus…

Non-Gaussian statistics of concentration fluctuations in free liquid diffusion
Marco Bussoletti, Mirko Gallo, Amir Jafari, Gregory L. Eyink
https://arxiv.org/abs/2509.25511 http…

Non-Gaussian statistics of concentration fluctuations in free liquid diffusion
We show that the three-point skewness of concentration fluctuations is non-vanishing in free liquid diffusion, even in the limit of vanishingly small mean concentration gradients. We exploit a high-Schmidt reduction of nonlinear Landau-Lifshitz hydrodynamics for a binary fluid, both analytically and by a massively parallel Lagrangian Monte Carlo simulation. Non-Gaussian statistics result from nonlinear coupling of concentration fluctuations to thermal velocity fluctuations, analogous to the tur…

Domain-Informed Genetic Superposition Programming: A Case Study on SFRC Beams
Mohammad Sadegh Khorshidi, Navid Yazdanjue, Hassan Gharoun, Mohammad Reza Nikoo, Fang Chen, Amir H. Gandomi
https://arxiv.org/abs/2509.21355

Domain-Informed Genetic Superposition Programming: A Case Study on SFRC Beams
This study presents domain-informed genetic superposition programming (DIGSP), a symbolic regression framework tailored for engineering systems governed by separable physical mechanisms. DIGSP partitions the input space into domain-specific feature subsets and evolves independent genetic programming (GP) populations to model material-specific effects. Early evolution occurs in isolation, while ensemble fitness promotes inter-population cooperation. To enable symbolic superposition, an adaptive …

Evaluating the Evaluators: Metrics for Compositional Text-to-Image Generation
Seyed Amir Kasaei, Ali Aghayari, Arash Marioriyad, Niki Sepasian, MohammadAmin Fazli, Mahdieh Soleymani Baghshah, Mohammad Hossein Rohban
https://arxiv.org/abs/2509.21227

Evaluating the Evaluators: Metrics for Compositional Text-to-Image Generation
Text-image generation has advanced rapidly, but assessing whether outputs truly capture the objects, attributes, and relations described in prompts remains a central challenge. Evaluation in this space relies heavily on automated metrics, yet these are often adopted by convention or popularity rather than validated against human judgment. Because evaluation and reported progress in the field depend directly on these metrics, it is critical to understand how well they reflect human preferences. …

Mike Johnson, Israeli Speaker to rally for Trump getting 2026 Nobel Peace Prize (Kate Santaliz/Axios)
https://www.axios.com/2025/10/14/mike-johnson-israeli-speaker-amir-ohanna-trump-nobel-prize-gaza
http://www.memeorandum.com/251014/p70#a251014p70

Quantifying (non-)weak compactness of operators on $AL$- and $C(K)$-spaces
Antonio Acuaviva, Amir Bahman Nasseri
https://arxiv.org/abs/2508.21543 https://a…

Quantifying (non-)weak compactness of operators on $AL$- and $C(K)$-spaces
We study the representation of non-weakly compact operators between $AL$-spaces. In this setting, we show that every operator admits a best approximant in the ideal of weakly compact operators. Using duality arguments, we extend this result to operators between $C(L)$-spaces where $L$ is extremally disconnected. We also characterize the weak essential norm for operators between $AL$-spaces in terms of factorizations of the identity on $\ell_1$. As a consequence, we deduce that the weak Calkin a…

Benchmarking Web API Integration Code Generation
Daniel Maninger, Leon Chemnitz, Amir Molzam Sharifloo, Jannis Brugger, Mira Mezini
https://arxiv.org/abs/2509.20172 https://

Benchmarking Web API Integration Code Generation
API integration is a cornerstone of our digital infrastructure, enabling software systems to connect and interact. However, as shown by many studies, writing or generating correct code to invoke APIs, particularly web APIs, is challenging. Although large language models~(LLMs) have become popular in software development, their effectiveness in automating the generation of web API integration code remains unexplored. In order to address this, we present a dataset and evaluation pipeline designed…

LLM Trainer: Automated Robotic Data Generating via Demonstration Augmentation using LLMs
Abraham George, Amir Barati Farimani
https://arxiv.org/abs/2509.20070 https://

LLM Trainer: Automated Robotic Data Generating via Demonstration Augmentation using LLMs
We present LLM Trainer, a fully automated pipeline that leverages the world knowledge of Large Language Models (LLMs) to transform a small number of human demonstrations (as few as one) into a large robot dataset for imitation learning. Our approach decomposes demonstration generation into two steps: (1) offline demonstration annotation that extracts keyframes, salient objects, and pose-object relations; and (2) online keypose retargeting that adapts those keyframes to a new scene, given an ini…

Engaging and Educating Eclipse Observers Through Workshops, Media, Planetarium shows and Citizen Science
Patricia H. Reiff, Carolyn T. Sumners, Charles H. Gardner, Amir Caspi, Sarah Kovac
https://arxiv.org/abs/2509.22348

Engaging and Educating Eclipse Observers Through Workshops, Media, Planetarium shows and Citizen Science
The Heliophysics Big Year was an extended year where major solar events engaged the public. It included two eclipses (annular on October 14, 2023 and total on April 8, 2024), plus solar max and the Parker Solar Probe perihelion December 24, 2024. After the eclipse of 2017, many millions more Americans planned to view the solar corona. We expanded our eclipse website with activities, citizen science projects, resources, training videos, equipment, and external links. We were the Southwest Region…

AI Reasoning Models for Problem Solving in Physics
Amir Bralin, N. Sanjay Rebello
https://arxiv.org/abs/2508.20941 https://arxiv.org/pdf/2508.20941

AI Reasoning Models for Problem Solving in Physics
Reasoning models are the new generation of Large Language Models (LLMs) capable of complex problem solving. Their reliability in solving introductory physics problems was tested by evaluating a sample of n = 5 solutions generated by one such model -- OpenAI's o3-mini -- per each problem from 20 chapters of a standard undergraduate textbook. In total, N = 408 problems were given to the model and N x n = 2,040 generated solutions examined. The model successfully solved 94% of the problems posed, …

An enhanced statistical feature fusion approach using an improved distance evaluation algorithm and weighted K-nearest neighbor for bearing fault diagnosis
Amir Eshaghi Chaleshtori, Abdollah Aghaie
https://arxiv.org/abs/2509.21219

An enhanced statistical feature fusion approach using an improved distance evaluation algorithm and weighted K-nearest neighbor for bearing fault diagnosis
Bearings are among the most failure-prone components in rotating machinery, and their condition directly impacts overall performance. Therefore, accurately diagnosing bearing faults is essential for ensuring system stability. However, detecting such malfunctions in noisy environments, where data is collected from multiple sensors, necessitates the extraction and selection of informative features. This paper proposes an improved distance evaluation algorithm combined with a weighted K-nearest ne…

Replaced article(s) found for q-bio.TO. https://arxiv.org/list/q-bio.TO/new
[1/1]:
- MAE-SAM2: Mask Autoencoder-Enhanced SAM2 for Clinical Retinal Vascular Leakage Segmentation
Xin Xing, Irmak Karaca, Amir Akhavanrezayat, Samira Badrloo, Quan Dong Nguyen, Mahadevan Subramaniam

Differentially-Private Decentralized Learning in Heterogeneous Multicast Networks
Amir Ziaeddini, Yauhen Yakimenka, J\"org Kliewer
https://arxiv.org/abs/2509.21688 https://…

Differentially-Private Decentralized Learning in Heterogeneous Multicast Networks
We propose a power-controlled differentially private decentralized learning algorithm designed for a set of clients aiming to collaboratively train a common learning model. The network is characterized by a row-stochastic adjacency matrix, which reflects different channel gains between the clients. In our privacy-preserving approach, both the transmit power for model updates and the level of injected Gaussian noise are jointly controlled to satisfy a given privacy and energy budget. We show tha…

Communication Efficient LLM Pre-training with SparseLoCo
Amir Sarfi, Benjamin Th\'erien, Joel Lidin, Eugene Belilovsky
https://arxiv.org/abs/2508.15706 https://

Communication Efficient LLM Pre-training with SparseLoCo
Communication-efficient distributed training algorithms have received considerable interest recently due to their benefits for training Large Language Models (LLMs) in bandwidth-constrained settings, such as across data centers and over the internet. Despite reducing communication frequency, these methods still typically require communicating a full copy of the model's gradients-resulting in a communication bottleneck even for cross-datacenter links. Furthermore, they can slightly degrade perfo…

Convergence rate of $\ell^p$-energy minimization on graphs: sharp polynomial bounds and a phase transition at $p=3$
Gideon Amir, Fedor Nazarov, Yuval Peres
https://arxiv.org/abs/2508.19411

Convergence rate of $\ell^p$-energy minimization on graphs: sharp polynomial bounds and a phase transition at $p=3$
We consider the following dynamics on a connected graph $(V,E)$ with $n$ vertices. Given $p>1$ and an initial opinion profile $f_0:V \to [0,1]$, at each integer step $t \ge 1$ a uniformly random vertex $v=v_t$ is selected, and the opinion there is updated to the value $f_{t}(v)$ that minimizes the sum $\sum_{w \sim v} |f_t(v)-f_{t-1}(w)|^p$ over neighbours $w$ of $v$. The case $p=2$ yields linear averaging dynamics, but for all $p \ne 2$ the dynamics are nonlinear. In the limiting cas…

New Algorithmic Directions in Optimal Transport and Applications for Product Spaces
Salman Beigi, Omid Etesami, Mohammad Mahmoody, Amir Najafi
https://arxiv.org/abs/2509.21502 h…

New Algorithmic Directions in Optimal Transport and Applications for Product Spaces
We study optimal transport between two high-dimensional distributions $μ,ν$ in $R^n$ from an algorithmic perspective: given $x \sim μ$, find a close $y \sim ν$ in $poly(n)$ time, where $n$ is the dimension of $x,y$. Thus, running time depends on the dimension rather than the full representation size of $μ,ν$. Our main result is a general algorithm for transporting any product distribution $μ$ to any $ν$ with cost $Δ+ δ$ under $\ell_p^p$, where $Δ$ is the Knothe-Rosenblatt transport c…

From Embeddings to Equations: Genetic-Programming Surrogates for Interpretable Transformer Classification
Mohammad Sadegh Khorshidi, Navid Yazdanjue, Hassan Gharoun, Mohammad Reza Nikoo, Fang Chen, Amir H. Gandomi
https://arxiv.org/abs/2509.21341

From Embeddings to Equations: Genetic-Programming Surrogates for Interpretable Transformer Classification
We study symbolic surrogate modeling of frozen Transformer embeddings to obtain compact, auditable classifiers with calibrated probabilities. For five benchmarks (SST2G, 20NG, MNIST, CIFAR10, MSC17), embeddings from ModernBERT, DINOv2, and SigLIP are partitioned on the training set into disjoint, information-preserving views via semantic-preserving feature partitioning (SPFP). A cooperative multi-population genetic program (MEGP) then learns additive, closed-form logit programs over these views…

Hallucination as an Upper Bound: A New Perspective on Text-to-Image Evaluation
Seyed Amir Kasaei, Mohammad Hossein Rohban
https://arxiv.org/abs/2509.21257 https://

Hallucination as an Upper Bound: A New Perspective on Text-to-Image Evaluation
In language and vision-language models, hallucination is broadly understood as content generated from a model's prior knowledge or biases rather than from the given input. While this phenomenon has been studied in those domains, it has not been clearly framed for text-to-image (T2I) generative models. Existing evaluations mainly focus on alignment, checking whether prompt-specified elements appear, but overlook what the model generates beyond the prompt. We argue for defining hallucination in T…

How the Raiders' Early-Season Struggles Vindicate 1 Veteran https://www.si.com/nfl/raiders/las-vegas-zamir-white-jackson-powers-johnson-pete-carroll

Extendibility of Fermionic Gaussian States
Amir-Reza Negari, Farzin Salek
https://arxiv.org/abs/2508.18532 https://arxiv.org/pdf/2508.18532

Extendibility of Fermionic Gaussian States
We investigate $(k_1,k_2)$-extendibility of fermionic Gaussian states, a property central to quantum correlations and approximations of separability. We show that these states are $(k_1,k_2)$-extendible if and only if they admit a fermionic Gaussian extension, yielding a complete covariance-matrix characterization and a simple semidefinite program (SDP) whose size scales linearly with the number of modes. This provides necessary conditions for arbitrary fermionic states and is sufficient within…

Can You Trust Your Copilot? A Privacy Scorecard for AI Coding Assistants
Amir AL-Maamari
https://arxiv.org/abs/2509.20388 https://arxiv.org/pdf/2509.20388

Can You Trust Your Copilot? A Privacy Scorecard for AI Coding Assistants
The rapid integration of AI-powered coding assistants into developer workflows has raised significant privacy and trust concerns. As developers entrust proprietary code to services like OpenAI's GPT, Google's Gemini, and GitHub Copilot, the unclear data handling practices of these tools create security and compliance risks. This paper addresses this challenge by introducing and applying a novel, expert-validated privacy scorecard. The methodology involves a detailed analysis of four document ty…

How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on $\tau$-bench
Venkatesh Mishra, Amir Saeidi, Satyam Raj, Mutsumi Nakamura, Jayanth Srinivasa, Gaowen Liu, Ali Payani, Chitta Baral
https://arxiv.org/abs/2508.20931

How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on $τ$-bench
Recent advances in reasoning and planning capabilities of large language models (LLMs) have enabled their potential as autonomous agents capable of tool use in dynamic environments. However, in multi-turn conversational environments like $τ$-bench, these agents often struggle with consistent reasoning, adherence to domain-specific policies, and extracting correct information over a long horizon of tool-calls and conversation. To capture and mitigate these failures, we conduct a comprehensive m…

Collaborative Filtering using Variational Quantum Hopfield Associative Memory
Amir Kermanshahani, Ebrahim Ardeshir-Larijani, Rakesh Saini, Saif Al-Kuwari
https://arxiv.org/abs/2508.14906

Collaborative Filtering using Variational Quantum Hopfield Associative Memory
Quantum computing, with its ability to do exponentially faster computation compared to classical systems, has found novel applications in various fields such as machine learning and recommendation systems. Quantum Machine Learning (QML), which integrates quantum computing with machine learning techniques, presents powerful new tools for data processing and pattern recognition. This paper proposes a hybrid recommendation system that combines Quantum Hopfield Associative Memory (QHAM) with deep n…

Audio-Visual Feature Synchronization for Robust Speech Enhancement in Hearing Aids
Nasir Saleem, Mandar Gogate, Kia Dashtipour, Adeel Hussain, Usman Anwar, Adewale Adetomi, Tughrul Arslan, Amir Hussain
https://arxiv.org/abs/2508.19483

Audio-Visual Feature Synchronization for Robust Speech Enhancement in Hearing Aids
Audio-visual feature synchronization for real-time speech enhancement in hearing aids represents a progressive approach to improving speech intelligibility and user experience, particularly in strong noisy backgrounds. This approach integrates auditory signals with visual cues, utilizing the complementary description of these modalities to improve speech intelligibility. Audio-visual feature synchronization for real-time SE in hearing aids can be further optimized using an efficient feature ali…

All-Electric Heavy-Duty Robotic Manipulator: Actuator Configuration Optimization and Sensorless Control
Mohammad Bahari, Amir Hossein Barjini, Pauli Mustalahti, Jouni Mattila
https://arxiv.org/abs/2509.15778

All-Electric Heavy-Duty Robotic Manipulator: Actuator Configuration Optimization and Sensorless Control
This paper presents a unified framework that integrates modeling, optimization, and sensorless control of an all-electric heavy-duty robotic manipulator (HDRM) driven by electromechanical linear actuators (EMLAs). An EMLA model is formulated to capture motor electromechanics and direction-dependent transmission efficiencies, while a mathematical model of the HDRM, incorporating both kinematics and dynamics, is established to generate joint-space motion profiles for prescribed TCP trajectories. …

Towards an AI-Augmented Textbook
LearnLM Team, Google, :, Amy Wang, Anna Iurchenko, Anisha Choudhury, Alicia Mart\'in, Amir Globerson, Avinatan Hassidim, Ay\c{c}a \c{C}akmakli, Ayelet Shasha Evron, Charlie Yang, Courtney Heldreth, Diana Akrong, Gal Elidan, Hairong Mu, Ian Li, Ido Cohen, Katherine Chou, Komal Singh, Lev Borovoi, Lidan Hackmon, Lior Belinsky, Michael Fink, Niv Efron, Preeti Singh, Rena Levitt, Shashank Agarwal, Shay Sharon, Tracey Lee-Joe, Xiaohong Hao, Yael Gold-Z…

Towards an AI-Augmented Textbook
Textbooks are a cornerstone of education, but they have a fundamental limitation: they are a one-size-fits-all medium. Any new material or alternative representation requires arduous human effort, so that textbooks cannot be adapted in a scalable manner. We present an approach for transforming and augmenting textbooks using generative AI, adding layers of multiple representations and personalization while maintaining content integrity and quality. We refer to the system built with this approach…

State of Abdominal CT Datasets: A Critical Review of Bias, Clinical Relevance, and Real-world Applicability
Saeide Danaei, Zahra Dehghanian, Elahe Meftah, Nariman Naderi, Seyed Amir Ahmad Safavi-Naini, Faeze Khorasanizade, Hamid R. Rabiee
https://arxiv.org/abs/2508.13626

State of Abdominal CT Datasets: A Critical Review of Bias, Clinical Relevance, and Real-world Applicability
This systematic review critically evaluates publicly available abdominal CT datasets and their suitability for artificial intelligence (AI) applications in clinical settings. We examined 46 publicly available abdominal CT datasets (50,256 studies). Across all 46 datasets, we found substantial redundancy (59.1\% case reuse) and a Western/geographic skew (75.3\% from North America and Europe). A bias assessment was performed on the 19 datasets with >=100 cases; within this subset, the most preval…

Unveiling Excitonic Insulator Signatures in Ta$_\mathrm{2}$NiSe$_\mathrm{5}$
Nour Maraytta, Peter Nagel, Fatemeh Ghorbani, Amir Ghiami, Santanu Pakhira, Mai Ye, Bjoern Wehinger, Federico Abbruciati, Gaston Garbarino, Matthieu Le Tacon, Stefan Schuppler, Amir-Abbas Haghighirad, Michael Merz
https://arxiv.org/abs/2509.15771

Unveiling Excitonic Insulator Signatures in Ta$_\mathrm{2}$NiSe$_\mathrm{5}$
The high-temperature phase of Ta$_\mathrm{2}$NiSe$_\mathrm{5}$, a near-zero-gap semiconductor ($E_G$ = 0), is a promising candidate for an excitonic insulator. Given the dome-like evolution expected for an excitonic insulator around $E_G$, we investigated Ta$_\mathrm{2}$NiSe$_\mathrm{5}$, the more semi-metallic Ta$_\mathrm{2}$(Ni,Co)Se$_\mathrm{5}$, and semiconducting Ta$_\mathrm{2}$NiS$_\mathrm{5}$ using high-resolution single-crystal x-ray diffraction and near-edge x-ray absorption fine struc…

Number Fields With Large P\'olya Groups
Amir Akbary, Abbas Maarefparvar
https://arxiv.org/abs/2508.11125 https://arxiv.org/pdf/2508.11125

Number Fields With Large Pólya Groups
The Pólya group ${\rm Po}(K)$ of a number field $K$ is the subgroup of the ideal class group ${\rm Cl}(K)$ of $K$ generated by the classes of all the products of the prime ideals of $K$ with the same norm. Motivated by the classical "one class in each genus problem", we prove general finiteness theorems for the number fields $K$ with a fixed Pólya index $\left[{\rm Cl}(K):{\rm Po}(K)\right]$ in the families of Galois number fields, solvable CM-fields, and real quadratic fields of extended R-D…

Bridging Minds and Machines: Toward an Integration of AI and Cognitive Science
Rui Mao, Qian Liu, Xiao Li, Erik Cambria, Amir Hussain
https://arxiv.org/abs/2508.20674 https://…

Bridging Minds and Machines: Toward an Integration of AI and Cognitive Science
Cognitive Science has profoundly shaped disciplines such as Artificial Intelligence (AI), Philosophy, Psychology, Neuroscience, Linguistics, and Culture. Many breakthroughs in AI trace their roots to cognitive theories, while AI itself has become an indispensable tool for advancing cognitive research. This reciprocal relationship motivates a comprehensive review of the intersections between AI and Cognitive Science. By synthesizing key contributions from both perspectives, we observe that AI pr…

Form factors of composite branch-point twist operators in the sinh-Gordon model on a multi-sheeted Riemann surface: semiclassical limit
Michael Lashkevich, Amir Nesturov
https://arxiv.org/abs/2508.12878

Form factors of composite branch-point twist operators in the sinh-Gordon model on a multi-sheeted Riemann surface: semiclassical limit
Quantum sinh-Gordon model in 1+1 dimensions is one of the simplest and best-studied massive integrable relativistic quantum field theories. We consider this theory on a multi-sheeted Riemann surfaces with a flat metric, which can be seen as a pile of planes connected to each other along cut lines. The cut lines end at branch points, which are represented by a twist operator ${\cal T}_n.$ Operators of such kind are interesting in the framework of the problem of computing von Neumann and Renyi en…

Measuring the Mean Plane of the Distant Kuiper Belt
Amir Siraj, Christopher F. Chyba, Scott Tremaine
https://arxiv.org/abs/2508.14156 https://arxiv.org/pdf…

Measuring the Mean Plane of the Distant Kuiper Belt
In the absence of any unseen planetary-mass bodies in the outer solar system, the mean plane of the distant Kuiper belt should be the same as the plane orthogonal to the angular momentum vector of the solar system -- the invariable plane. Here, we measure the mean plane of the non-resonant Kuiper belt across semimajor axes 50 - 400 AU. We introduce a new method to measure the mean plane that we demonstrate to be independent of observational bias. In particular, our results are not biased by sur…

Energy-Efficient Routing Algorithm for Wireless Sensor Networks: A Multi-Agent Reinforcement Learning Approach
Parham Soltani, Mehrshad Eskandarpour, Amir Ahmadizad, Hossein Soleimani
https://arxiv.org/abs/2508.14679

Energy-Efficient Routing Algorithm for Wireless Sensor Networks: A Multi-Agent Reinforcement Learning Approach
Efficient energy management is essential in Wireless Sensor Networks (WSNs) to extend network lifetime and ensure reliable data transmission. This paper presents a novel method using reinforcement learning-based cluster-head selection and a hybrid multi-hop routing algorithm, which leverages Q-learning within a multi-agent system to dynamically adapt transmission paths based on the energy distribution across sensor nodes. Each sensor node is modeled as an autonomous agent that observes local st…

Crosslisted article(s) found for physics.atom-ph. https://arxiv.org/list/physics.atom-ph/new
[1/1]:
- Robust Control and Entanglement of Qudits in Neutral Atom Arrays
Amir Burshtein, Shachar Fraenkel, Moshe Goldstein, Ran Finkelstein

Crosslisted article(s) found for q-bio.NC. https://arxiv.org/list/q-bio.NC/new
[1/1]:
- Goals and the Structure of Experience
Nadav Amir, Stas Tiomkin, Angela Langdon

Polarimeter to Unify the Corona and Heliosphere (PUNCH)
Craig DeForest, Sarah Gibson, Ronnie Killough, Nick Waltham, Matt Beasley, Robin Colaninno, Glenn Laurent, Daniel Seaton, Marcus Hughes, Madhulika Guhathakurta, Nicholeen Viall, Raphael Attie, Dipankar Banerjee, Luke Barnar, Doug Biesecker, Mario Bisi, Volker Bothmer, Antonina Brody, Joan Burkepile, Iver Cairns, Jennifer Campbell, david Cheney, Traci Case, Amir Caspi, Rohit Chhiber, Matthew Clapp, Steven Cranmer, Jackie Davies, Cu…

Polarimeter to Unify the Corona and Heliosphere (PUNCH)
The Polarimeter to Unify the Corona and Heliosphere (PUNCH) mission is a NASA Small Explorer to determine the cross-scale processes that unify the solar corona and heliosphere. PUNCH has two science objectives: (1) understand how coronal structures become the ambient solar wind, and (2) understand the dynamic evolution of transient structures, such as coronal mass ejections, in the young solar wind. To address these objectives, PUNCH uses a constellation of four small spacecraft in Sun-synchron…

A Lightweight Pipeline for Noisy Speech Voice Cloning and Accurate Lip Sync Synthesis
Javeria Amir, Farwa Attaria, Mah Jabeen, Umara Noor, Zahid Rashid
https://arxiv.org/abs/2509.12831

A Lightweight Pipeline for Noisy Speech Voice Cloning and Accurate Lip Sync Synthesis
Recent developments in voice cloning and talking head generation demonstrate impressive capabilities in synthesizing natural speech and realistic lip synchronization. Current methods typically require and are trained on large scale datasets and computationally intensive processes using clean studio recorded inputs that is infeasible in noisy or low resource environments. In this paper, we introduce a new modular pipeline comprising Tortoise text to speech. It is a transformer based latent diffu…

Near-Field Integrated Imaging and Communication in Distributed MIMO Networks
Kangda Zhi, Tianyu Yang, Shuangyang Li, Yi Song, Amir Rezaei, Giuseppe Caire
https://arxiv.org/abs/2508.17526

Near-Field Integrated Imaging and Communication in Distributed MIMO Networks
In this work, we propose a general framework for wireless imaging in distributed MIMO wideband communication systems, considering multi-view non-isotropic targets and near-field propagation effects. For indoor scenarios where the objective is to image small-scale objects with high resolution, we propose a range migration algorithm (RMA)-based scheme using three kinds of array architectures: the full array, boundary array, and distributed boundary array. With non-isotropic near-field channels, w…

Replaced article(s) found for cs.RO. https://arxiv.org/list/cs.RO/new
[1/3]:
- Sample-Efficient Reinforcement Learning with Symmetry-Guided Demonstrations for Robotic Manipulation
Amir M. Soufi Enayati, Zengjie Zhang, Kashish Gupta, Homayoun Najjaran

In-Context Decision Making for Optimizing Complex AutoML Pipelines
Amir Rezaei Balef, Katharina Eggensperger
https://arxiv.org/abs/2508.13657 https://arxiv…

In-Context Decision Making for Optimizing Complex AutoML Pipelines
Combined Algorithm Selection and Hyperparameter Optimization (CASH) has been fundamental to traditional AutoML systems. However, with the advancements of pre-trained models, modern ML workflows go beyond hyperparameter optimization and often require fine-tuning, ensembling, and other adaptation techniques. While the core challenge of identifying the best-performing model for a downstream task remains, the increasing heterogeneity of ML pipelines demands novel AutoML approaches. This work extend…

Strengthening the Bridge Between Chiral Lagrangians and QCD Sum-Rules
J. Ho, Amir H. Fariborz, T. G. Steele
https://arxiv.org/abs/2509.16380 https://arxiv.…

Strengthening the Bridge Between Chiral Lagrangians and QCD Sum-Rules
Previous work has shown that mesonic fields in chiral Lagrangians can be systematically connected to quark-level operators in QCD sum rules through chiral-symmetry constrained and energy-independent scale factor matrices. This framework yields universal scale factors associated with each chiral nonet, whether composed of quark-antiquark ($q\bar{q}$) or four-quark ($qq\bar{q}\bar{q}$) operators. Building on the demonstrated scale-factor universality for the $K_0^*$ isodoublet and $a_0$ isotriple…

Robust Control and Entanglement of Qudits in Neutral Atom Arrays
Amir Burshtein, Shachar Fraenkel, Moshe Goldstein, Ran Finkelstein
https://arxiv.org/abs/2508.16294 https://

Robust Control and Entanglement of Qudits in Neutral Atom Arrays
Quantum devices comprised of elementary components with more than two stable levels - so-called qudits - enrich the accessible Hilbert space, enabling applications ranging from fault-tolerant quantum computing to simulating complex many-body models. While several quantum platforms are built from local elements that are equipped with a rich spectrum of stable energy levels, schemes for the efficient control and entanglement of qudits are scarce. Importantly, no experimental demonstration of mult…

Linkage Attacks Expose Identity Risks in Public ECG Data Sharing
Ziyu Wang, Elahe Khatibi, Farshad Firouzi, Sanaz Rahimi Mousavi, Krishnendu Chakrabarty, Amir M. Rahmani
https://arxiv.org/abs/2508.15850

Linkage Attacks Expose Identity Risks in Public ECG Data Sharing
The increasing availability of publicly shared electrocardiogram (ECG) data raises critical privacy concerns, as its biometric properties make individuals vulnerable to linkage attacks. Unlike prior studies that assume idealized adversarial capabilities, we evaluate ECG privacy risks under realistic conditions where attackers operate with partial knowledge. Using data from 109 participants across diverse real-world datasets, our approach achieves 85% accuracy in re-identifying individuals in pu…

Accelerating GenAI Workloads by Enabling RISC-V Microkernel Support in IREE
Adeel Ahmad, Ahmad Tameem Kamal, Nouman Amir, Bilal Zafar, Saad Bin Nasir
https://arxiv.org/abs/2508.14899

Accelerating GenAI Workloads by Enabling RISC-V Microkernel Support in IREE
This project enables RISC-V microkernel support in IREE, an MLIR-based machine learning compiler and runtime. The approach begins by enabling the lowering of MLIR linalg dialect contraction ops to linalg.mmt4d op for the RISC-V64 target within the IREE pass pipeline, followed by the development of optimized microkernels for RISC-V. The performance gains are compared with upstream IREE and Llama.cpp for the Llama-3.2-1B-Instruct model.

What makes an entity salient in discourse?
Amir Zeldes, Jessica Lin
https://arxiv.org/abs/2508.16464 https://arxiv.org/pdf/2508.16464

What makes an entity salient in discourse?
Entities in discourse vary broadly in salience: main participants, objects and locations are noticeable and memorable, while tangential ones are less important and quickly forgotten, raising questions about how humans signal and infer relative salience. Using a graded operationalization of salience based on summary-worthiness in multiple summaries of a discourse, this paper explores data from 24 spoken and written genres of English to extract a multifactorial complex of overt and implicit lingu…

FM OFDM Unifying High Mobility Communications and Sensing
Amir Bouziane, Huseyin Arslan
https://arxiv.org/abs/2508.16107 https://arxiv.org/pdf/2508.16107…

FM OFDM Unifying High Mobility Communications and Sensing
Integrated Sensing and Communication (ISAC) is foundational to future sixth generation (6G) systems, demanding waveform co-design that supports both high throughput data transmission and accurate environmental perception. While Orthogonal Frequency Division Multiplexing (OFDM) offers flexibility and backward compatibility, its high Peak to Average Power Ratio (PAPR) poses significant challenges at higher frequency bands. To address this, we investigate Frequency Modulated Orthogonal Frequency D…

Physically-Based Inverse Rendering Framework for PET Image Reconstruction
Yixin Li, Soroush Shabani Sichani, Zipai Wang, Wanbin Tan, Baptiste Nicolet, Xiuyuan Wang, David A. Muller, Gloria C. Chiang, Wenzel Jakob, Amir H. Goldan
https://arxiv.org/abs/2508.19956

Physically-Based Inverse Rendering Framework for PET Image Reconstruction
Differentiable rendering has been widely adopted in computer graphics as a powerful approach to inverse problems, enabling efficient gradient-based optimization by differentiating the image formation process with respect to millions of scene parameters. Inspired by this paradigm, we propose a physically-based inverse rendering (IR) framework, the first ever platform for PET image reconstruction using Dr.Jit, for PET image reconstruction. Our method integrates Monte Carlo sampling with an analyt…

Quickest Change Detection in Continuous-Time in Presence of a Covert Adversary
Amir Reza Ramtin, Philippe Nain, Don Towsley
https://arxiv.org/abs/2509.17778 https://

Quickest Change Detection in Continuous-Time in Presence of a Covert Adversary
We investigate the problem of covert quickest change detection in a continuous-time setting, where a Brownian motion experiences a drift change at an unknown time. Unlike classical formulations, we consider a covert adversary who adjusts the post-change drift $μ= μ(γ)$ as a function of the false alarm constraint parameter $γ$, with the goal of remaining undetected for as long as possible. Leveraging the exact expressions for the average detection delay (ADD) and average time to false alarm …

Multi-population Ensemble Genetic Programming via Cooperative Coevolution and Multi-view Learning for Classification
Mohammad Sadegh Khorshidi, Navid Yazdanjue, Hassan Gharoun, Mohammad Reza Nikoo, Fang Chen, Amir H. Gandomi
https://arxiv.org/abs/2509.19339

Multi-population Ensemble Genetic Programming via Cooperative Coevolution and Multi-view Learning for Classification
This paper introduces Multi-population Ensemble Genetic Programming (MEGP), a computational intelligence framework that integrates cooperative coevolution and the multiview learning paradigm to address classification challenges in high-dimensional and heterogeneous feature spaces. MEGP decomposes the input space into conditionally independent feature subsets, enabling multiple subpopulations to evolve in parallel while interacting through a dynamic ensemble-based fitness mechanism. Each individ…

AI-Driven Adaptive Air Transit Network with Modular Aerial Pods
Amir Shafiee, Alireza Yazdiani, Hanieh Rastegar, Rui Li, Rayan Karim, Aolei Cao, Ziyang Li, Xieqing Yu, Charlle Sy, Zhaoyao Bao, Xi Cheng, H. Oliver Gao
https://arxiv.org/abs/2509.12644

AI-Driven Adaptive Air Transit Network with Modular Aerial Pods
This paper presents an adaptive air transit network leveraging modular aerial pods and artificial intelligence (AI) to address urban mobility challenges. Passenger demand, forecasted from AI models, serves as input parameters for a Mixed-Integer Nonlinear Programming (MINLP) optimization model that dynamically adjusts pod dispatch schedules and train lengths in response to demand variations. The results reveal a complex interplay of factors, including demand levels, headway bounds, train config…

Cin\'{e}aste: A Fine-grained Contextual Movie Question Answering Benchmark
Nisarg A. Shah, Amir Ziai, Chaitanya Ekanadham, Vishal M. Patel
https://arxiv.org/abs/2509.14227 h…

Cinéaste: A Fine-grained Contextual Movie Question Answering Benchmark
While recent advancements in vision-language models have improved video understanding, diagnosing their capacity for deep, narrative comprehension remains a challenge. Existing benchmarks often test short-clip recognition or use template-based questions, leaving a critical gap in evaluating fine-grained reasoning over long-form narrative content. To address these gaps, we introduce $\mathsf{Cin\acute{e}aste}$, a comprehensive benchmark for long-form movie understanding. Our dataset comprises 3,…

The 1 Thing Raiders Rookie RB Ashton Jeanty Needs https://www.si.com/nfl/raiders/las-vegas-zamir-white-ashton-jeanty-washington-commanders-pete-carroll

Revealing the Influence of Dopants on the Properties of Fluorite Structure Ferroelectrics
Shouzhuo Yang, David Lehninger, Markus Neuber, Amir Pourjafar, Ayse S\"unb\"ul, Anant Rastogi, Peter Reinig, Konrad Seidel, Maximilian Lederer
https://arxiv.org/abs/2508.16477

Revealing the Influence of Dopants on the Properties of Fluorite Structure Ferroelectrics
Fluorite structure ferroelectrics, especially hafnium oxide, are widely investigated for their application in non-volatile memories, sensors, actuators, RF devices and energy harvesters. Due to the metastable nature of the ferroelectric phase in these materials, dopants and process parameters need to be optimized for its stabilization. Here, we present clear evidence of how dopants affect the properties in this material system and solutions to achieve improved reliability, desired crystallizati…

On Spectral Properties of Gradient-based Explanation Methods
Amir Mehrpanah, Erik Englesson, Hossein Azizpour
https://arxiv.org/abs/2508.10595 https://arxi…

On Spectral Properties of Gradient-based Explanation Methods
Understanding the behavior of deep networks is crucial to increase our confidence in their results. Despite an extensive body of work for explaining their predictions, researchers have faced reliability issues, which can be attributed to insufficient formalism. In our research, we adopt novel probabilistic and spectral perspectives to formally analyze explanation methods. Our study reveals a pervasive spectral bias stemming from the use of gradient, and sheds light on some common design choices…

Quantum Co-Magnetometer Using Diamond Nitrogen-Vacancy Centers and Rubidium Cells
Ittai Shalev, Kfir Levi, Rotem Malkinson, Amir Hen, Liron Stern, Nir Bar-Gill
https://arxiv.org/abs/2508.15638

Quantum Co-Magnetometer Using Diamond Nitrogen-Vacancy Centers and Rubidium Cells
Recent advances in chip scale magnetic quantum sensing have produced platforms that pair unprecedented sensitivity with extreme miniaturization. Here, we demonstrate a hybrid quantum sensor by combining Nitrogen-Vacancy (NV) centers in diamond with a rubidium (Rb) vapor cell, designed for precise magnetic field measurements and quantum exploration. The hybrid comagnetometer leverages the high resolution vector magnetic sensing of NV centers along with the high scalar field sensitivity of the Rb…

NavMoE: Hybrid Model- and Learning-based Traversability Estimation for Local Navigation via Mixture of Experts
Botao He, Amir Hossein Shahidzadeh, Yu Chen, Jiayi Wu, Tianrui Guan, Guofei Chen, Howie Choset, Dinesh Manocha, Glen Chou, Cornelia Fermuller, Yiannis Aloimonos
https://arxiv.org/abs/2509.12747

NavMoE: Hybrid Model- and Learning-based Traversability Estimation for Local Navigation via Mixture of Experts
This paper explores traversability estimation for robot navigation. A key bottleneck in traversability estimation lies in efficiently achieving reliable and robust predictions while accurately encoding both geometric and semantic information across diverse environments. We introduce Navigation via Mixture of Experts (NAVMOE), a hierarchical and modular approach for traversability estimation and local navigation. NAVMOE combines multiple specialized models for specific terrain types, each of whi…

BEFT: Bias-Efficient Fine-Tuning of Language Models
Baichuan Huang, Ananth Balashankar, Amir Aminifar
https://arxiv.org/abs/2509.15974 https://arxiv.org/pd…

BEFT: Bias-Efficient Fine-Tuning of Language Models
Fine-tuning all-bias-terms stands out among various parameter-efficient fine-tuning (PEFT) techniques, owing to its out-of-the-box usability and competitive performance, especially in low-data regimes. Bias-only fine-tuning has the potential for unprecedented parameter efficiency. However, the link between fine-tuning different bias terms (i.e., bias terms in the query, key, or value projections) and downstream performance remains unclear. The existing approaches, e.g., based on the magnitude o…

An Optimization Framework for the Time-Dependent Electric Vehicle Routing Problem with Shared Mobility: A Step Toward Smart Cities
Alireza Yazdiani, Shayan Bafandkar, Amir Elmi, Yousef Shafahi
https://arxiv.org/abs/2509.12623

An Optimization Framework for the Time-Dependent Electric Vehicle Routing Problem with Shared Mobility: A Step Toward Smart Cities
This paper aims to introduce a mathematical model to solve the time-dependent electric vehicles routing problem in shared travels. Shared mobility has gained significance recently due to its contribution to the alleviation of traffic congestion and air pollution. In this study, a MIP model has been developed and solved for a toy problem using the CPLEX solver to indicate the efficiency of shared mobility compared to private mode. We have considered practical constraints, such as considering the…

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[3/10]:
- Context-aware Biases for Length Extrapolation
Ali Veisi, Hamidreza Amirzadeh, Amir Mansourian

Detecting Text Manipulation in Images using Vision Language Models
Vidit Vidit, Pavel Korshunov, Amir Mohammadi, Christophe Ecabert, Ketan Kotwal, S\'ebastien Marcel
https://arxiv.org/abs/2509.10278

Detecting Text Manipulation in Images using Vision Language Models
Recent works have shown the effectiveness of Large Vision Language Models (VLMs or LVLMs) in image manipulation detection. However, text manipulation detection is largely missing in these studies. We bridge this knowledge gap by analyzing closed- and open-source VLMs on different text manipulation datasets. Our results suggest that open-source models are getting closer, but still behind closed-source ones like GPT- 4o. Additionally, we benchmark image manipulation detection-specific VLMs for te…

Scaling Hybrid Quantum-HPC Applications with the Quantum Framework
Srikar Chundury, Amir Shehata, Seongmin Kim, Muralikrishnan Gopalakrishnan Meena, Chao Lu, Kalyana Gottiparthi, Eduardo Antonio Coello Perez, Frank Mueller, In-Saeng Suh
https://arxiv.org/abs/2509.14470

Scaling Hybrid Quantum-HPC Applications with the Quantum Framework
Hybrid quantum-high performance computing (Q-HPC) workflows are emerging as a key strategy for running quantum applications at scale in current noisy intermediate-scale quantum (NISQ) devices. These workflows must operate seamlessly across diverse simulators and hardware backends since no single simulator offers the best performance for every circuit type. Simulation efficiency depends strongly on circuit structure, entanglement, and depth, making a flexible and backend-agnostic execution model…

From Individual to Multi-Agent Algorithmic Recourse: Minimizing the Welfare Gap via Capacitated Bipartite Matching
Zahra Khotanlou, Kate Larson, Amir-Hossein Karimi
https://arxiv.org/abs/2508.11070

From Individual to Multi-Agent Algorithmic Recourse: Minimizing the Welfare Gap via Capacitated Bipartite Matching
Decision makers are increasingly relying on machine learning in sensitive situations. In such settings, algorithmic recourse aims to provide individuals with actionable and minimally costly steps to reverse unfavorable AI-driven decisions. While existing research predominantly focuses on single-individual (i.e., seeker) and single-model (i.e., provider) scenarios, real-world applications often involve multiple interacting stakeholders. Optimizing outcomes for seekers under an individual welfare…

Crosslisted article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[1/7]:
- Domain-Specific Constitutional AI: Enhancing Safety in LLM-Powered Mental Health Chatbots
Chenhan Lyu, Yutong Song, Pengfei Zhang, Amir M. Rahmani

Two-point Random Gradient-free Methods for Model-free Feedback Optimization
Amir Mehrnoosh, Gianluca Bianchin
https://arxiv.org/abs/2509.11666 https://arxi…

Two-point Random Gradient-free Methods for Model-free Feedback Optimization
Feedback optimization has emerged as a promising approach for optimizing the steady-state operation of dynamical systems while requiring minimal modeling efforts. Unfortunately, most existing feedback optimization methods rely on knowledge of the plant dynamics, which may be difficult to obtain or estimate in practice. In this paper, we introduce a novel randomized two-point gradient-free feedback optimization method, inspired by zeroth-order optimization techniques. Our method relies on functi…

January Food Benchmark (JFB): A Public Benchmark Dataset and Evaluation Suite for Multimodal Food Analysis
Amir Hosseinian, Ashkan Dehghani Zahedani, Umer Mansoor, Noosheen Hashemi, Mark Woodward
https://arxiv.org/abs/2508.09966

January Food Benchmark (JFB): A Public Benchmark Dataset and Evaluation Suite for Multimodal Food Analysis
Progress in AI for automated nutritional analysis is critically hampered by the lack of standardized evaluation methodologies and high-quality, real-world benchmark datasets. To address this, we introduce three primary contributions. First, we present the January Food Benchmark (JFB), a publicly available collection of 1,000 food images with human-validated annotations. Second, we detail a comprehensive benchmarking framework, including robust metrics and a novel, application-oriented overall s…

Cross-Platform Scaling of Vision-Language-Action Models from Edge to Cloud GPUs
Amir Taherin, Juyi Lin, Arash Akbari, Arman Akbari, Pu Zhao, Weiwei Chen, David Kaeli, Yanzhi Wang
https://arxiv.org/abs/2509.11480

Cross-Platform Scaling of Vision-Language-Action Models from Edge to Cloud GPUs
Vision-Language-Action (VLA) models have emerged as powerful generalist policies for robotic control, yet their performance scaling across model architectures and hardware platforms, as well as their associated power budgets, remain poorly understood. This work presents an evaluation of five representative VLA models -- spanning state-of-the-art baselines and two newly proposed architectures -- targeting edge and datacenter GPU platforms. Using the LIBERO benchmark, we measure accuracy alongsid…

Who Gets the Mic? Investigating Gender Bias in the Speaker Assignment of a Speech-LLM
Dariia Puhach, Amir H. Payberah, \'Eva Sz\'ekely
https://arxiv.org/abs/2508.13603 h…

Who Gets the Mic? Investigating Gender Bias in the Speaker Assignment of a Speech-LLM
Similar to text-based Large Language Models (LLMs), Speech-LLMs exhibit emergent abilities and context awareness. However, whether these similarities extend to gender bias remains an open question. This study proposes a methodology leveraging speaker assignment as an analytic tool for bias investigation. Unlike text-based models, which encode gendered associations implicitly, Speech-LLMs must produce a gendered voice, making speaker selection an explicit bias cue. We evaluate Bark, a Text-to-Sp…

Beyond Rebalancing: Benchmarking Binary Classifiers Under Class Imbalance Without Rebalancing Techniques
Ali Nawaz, Amir Ahmad, Shehroz S. Khan
https://arxiv.org/abs/2509.07605 …

Beyond Rebalancing: Benchmarking Binary Classifiers Under Class Imbalance Without Rebalancing Techniques
Class imbalance poses a significant challenge to supervised classification, particularly in critical domains like medical diagnostics and anomaly detection where minority class instances are rare. While numerous studies have explored rebalancing techniques to address this issue, less attention has been given to evaluating the performance of binary classifiers under imbalance when no such techniques are applied. Therefore, the goal of this study is to assess the performance of binary classifiers…

CS-FLEURS: A Massively Multilingual and Code-Switched Speech Dataset
Brian Yan, Injy Hamed, Shuichiro Shimizu, Vasista Lodagala, William Chen, Olga Iakovenko, Bashar Talafha, Amir Hussein, Alexander Polok, Kalvin Chang, Dominik Klement, Sara Althubaiti, Puyuan Peng, Matthew Wiesner, Thamar Solorio, Ahmed Ali, Sanjeev Khudanpur, Shinji Watanabe, Chih-Chen Chen, Zhen Wu, Karim Benharrak, Anuj Diwan, Samuele Cornell, Eunjung Yeo, Kwanghee Choi, Carlos Carvalho, Karen Rosero

CS-FLEURS: A Massively Multilingual and Code-Switched Speech Dataset
We present CS-FLEURS, a new dataset for developing and evaluating code-switched speech recognition and translation systems beyond high-resourced languages. CS-FLEURS consists of 4 test sets which cover in total 113 unique code-switched language pairs across 52 languages: 1) a 14 X-English language pair set with real voices reading synthetically generated code-switched sentences, 2) a 16 X-English language pair set with generative text-to-speech 3) a 60 {Arabic, Mandarin, Hindi, Spanish}-X langu…

BcQLM: Efficient Vision-Language Understanding with Distilled Q-Gated Cross-Modal Fusion
Sike Xiang, Shuang Chen, Amir Atapour-Abarghouei
https://arxiv.org/abs/2509.08715 https:…

BcQLM: Efficient Vision-Language Understanding with Distilled Q-Gated Cross-Modal Fusion
As multimodal large language models (MLLMs) advance, their large-scale architectures pose challenges for deployment in resource-constrained environments. In the age of large models, where energy efficiency, computational scalability and environmental sustainability are paramount, the development of lightweight and high-performance models is critical for real-world applications. As such, we propose a lightweight MLLM framework for end-to-end visual question answering. Our proposed approach centr…

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…

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[2/5]:
- Beyond I'm Sorry, I Can't: Dissecting Large Language Model Refusal
Nirmalendu Prakash, Yeo Wei Jie, Amir Abdullah, Ranjan Satapathy, Erik Cambria, Roy Ka Wei Lee

FATHOMS-RAG: A Framework for the Assessment of Thinking and Observation in Multimodal Systems that use Retrieval Augmented Generation
Samuel Hildebrand (Louisiana State University), Curtis Taylor (Oak Ridge National Lab), Sean Oesch (Oak Ridge National Lab), James M Ghawaly Jr (Louisiana State University), Amir Sadovnik (Oak Ridge National Lab), Ryan Shivers (Oak Ridge National Lab), Brandon Schreiber (Oak Ridge National Lab), Kevin Kurian (University of Florida)

FATHOMS-RAG: A Framework for the Assessment of Thinking and Observation in Multimodal Systems that use Retrieval Augmented Generation
Retrieval-augmented generation (RAG) has emerged as a promising paradigm for improving factual accuracy in large language models (LLMs). We introduce a benchmark designed to evaluate RAG pipelines as a whole, evaluating a pipeline's ability to ingest, retrieve, and reason about several modalities of information, differentiating it from existing benchmarks that focus on particular aspects such as retrieval. We present (1) a small, human-created dataset of 93 questions designed to evaluate a pipe…

RefGrader: Automated Grading of Mathematical Competition Proofs using Agentic Workflows
Hamed Mahdavi (Pennsylvania State University), Pouria Mahdavinia (Pennsylvania State University), Samira Malek (Pennsylvania State University), Pegah Mohammadipour (Pennsylvania State University), Alireza Hashemi (City University of New York), Majid Daliri (New York University), Alireza Farhadi (Amirkabir University of Technology), Amir Khasahmadi (Autodesk), Niloofar Mireshghallah (Carnegie Mellon …

RefGrader: Automated Grading of Mathematical Competition Proofs using Agentic Workflows
State-of-the-art (SOTA) LLMs have progressed from struggling on proof-based Olympiad problems to solving most of the IMO 2025 problems, with leading systems reportedly handling 5 of 6 problems. Given this progress, we assess how well these models can grade proofs: detecting errors, judging their severity, and assigning fair scores beyond binary correctness. We study proof-analysis capabilities using a corpus of 90 Gemini 2.5 Pro-generated solutions that we grade on a 1-4 scale with detailed err…