Tootfinder

If you are a US citizen holding a #HamRadio license, please add your name to #AmateurRadio antennas with bills in both the house and senate,…

Deconstructing Intraocular Pressure: A Non-invasive Multi-Stage Probabilistic Inverse Framework
Md Rezwan Jaher, Abul Mukid Mohammad Mukaddes, A. B. M. Abdul Malek
https://arxiv.org/abs/2509.14167

Deconstructing Intraocular Pressure: A Non-invasive Multi-Stage Probabilistic Inverse Framework
Many critical healthcare decisions are challenged by the inability to measure key underlying parameters. Glaucoma, a leading cause of irreversible blindness driven by elevated intraocular pressure (IOP), provides a stark example. The primary determinant of IOP, a tissue property called trabecular meshwork permeability, cannot be measured in vivo, forcing clinicians to depend on indirect surrogates. This clinical challenge is compounded by a broader computational one: developing predictive model…

DSCC-HS: A Dynamic Self-Reinforcing Framework for Hallucination Suppression in Large Language Models
Xiao Zheng
https://arxiv.org/abs/2509.13702 https://ar…

DSCC-HS: A Dynamic Self-Reinforcing Framework for Hallucination Suppression in Large Language Models
Large Language Model (LLM) hallucination is a significant barrier to their reliable deployment. Current methods like Retrieval-Augmented Generation (RAG) are often reactive. We introduce **Dynamic Self-reinforcing Calibration for Hallucination Suppression (DSCC-HS)**, a novel, proactive framework that intervenes during autoregressive decoding. Inspired by dual-process cognitive theory, DSCC-HS uses a compact proxy model, trained in adversarial roles as a Factual Alignment Proxy (FAP) and a Hall…

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,…

Interesting 👀 https://social.zarchbox.fr/notes/agclhhyre66bnqz3
Extension from @… :

Catalpa: GC for a Low-Variance Software Stack
Anthony Arnold, Mark Marron
https://arxiv.org/abs/2509.13429 https://arxiv.org/pdf/2509.13429

Catalpa: GC for a Low-Variance Software Stack
The performance of an application/runtime is usually conceptualized as a continuous function where, the lower the amount of memory/time used on a given workload, then the better the compiler/runtime is. However, in practice, good performance of an application is viewed as more of a binary function - either the application responds in under, say 100 ms, and is fast enough for a user to barely notice, or it takes a noticeable amount of time, leaving the user waiting and potentially abandoning the…

A numerical scheme for a fully nonlinear free boundary problem
Edgard A. Pimentel, Erc\'ilia Sousa
https://arxiv.org/abs/2509.14150 https://arxiv.org/p…

A numerical scheme for a fully nonlinear free boundary problem
We propose a numerical method to approximate viscosity solutions of fully nonlinear free transmission problems. The method discretises a two-layer regularisation of a PDE, involving a functional and a vanishing parameter. The former is handled via a fixed-point argument. We then prove that the numerical method converges to a one-parameter regularisation of the free boundary problem. Regularity estimates enable us to take the vanishing limit of such a parameter and recover a viscosity solution o…

Algorithmic Perspective on Toda's Theorem
Dror Fried, Etay Segal, Gad E. Yaron
https://arxiv.org/abs/2509.13871 https://arxiv.org/pdf/2509.13871…

Algorithmic Perspective on Toda's Theorem
Toda's Theorem is a fundamental result in computational complexity theory, whose proof relies on a reduction from a QBF problem with a constant number of quantifiers to a model counting problem. While this reduction, henceforth called Toda's reduction, is of a purely theoretical nature, the recent progress of model counting tools raises the question of whether the reduction can be utilized to an efficient algorithm for solving QBF. In this work, we address this question by looking at Toda's red…

Tahoe is a whole thing today... I've had icons disappearing from my Safari Start Page, invisible App windows in Mission Control, A disappearing mouse cursor in Photoshop.
And... what is it with the window corner radii?
I mean come on!
#Tahoe #Apple #MacOS26

Agentic JWT: A Secure Delegation Protocol for Autonomous AI Agents
Abhishek Goswami
https://arxiv.org/abs/2509.13597 https://arxiv.org/pdf/2509.13597

Agentic JWT: A Secure Delegation Protocol for Autonomous AI Agents
Autonomous LLM agents can issue thousands of API calls per hour without human oversight. OAuth 2.0 assumes deterministic clients, but in agentic settings stochastic reasoning, prompt injection, or multi-agent orchestration can silently expand privileges. We introduce Agentic JWT (A-JWT), a dual-faceted intent token that binds each agent's action to verifiable user intent and, optionally, to a specific workflow step. A-JWT carries an agent's identity as a one-way checksum hash derived from its…

OpenHA: A Series of Open-Source Hierarchical Agentic Models in Minecraft
Zihao Wang, Muyao Li, Kaichen He, Xiangyu Wang, Zhancun Mu, Anji Liu, Yitao Liang
https://arxiv.org/abs/2509.13347

OpenHA: A Series of Open-Source Hierarchical Agentic Models in Minecraft
The choice of action spaces is a critical yet unresolved challenge in developing capable, end-to-end trainable agents. This paper first presents a large-scale, systematic comparison of prominent abstracted action spaces and tokenizers for Vision-Language-Action (VLA) or hierarchical agent models in the open-ended Minecraft. Our analysis reveals that no single action space is universally optimal; instead, the most effective abstraction is highly task-dependent, creating a dilemma for building ge…

Quantum ground-state cooling of two librational modes of a nanorotor
Stephan Troyer, Florian Fechtel, Lorenz Hummer, Henning Rudolph, Benjamin A. Stickler, Uro\v{s} Deli\'c, Markus Arndt
https://arxiv.org/abs/2509.13398

Quantum ground-state cooling of two librational modes of a nanorotor
Controlling the motion of nanoscale objects at the quantum limit promises new tests of quantum mechanics and advanced sensors. Rotational motion is of particular interest, as it follows nonlinear dynamics in a compact, closed configuration space, which opens up a plethora of phenomena and applications beyond the possibilities of free or trapped linear motion. A prerequisite for such experiments is the capability to trap nanorotors and initialize them in a quantum ground state of libration. Here…

Replaced article(s) found for math.OC. https://arxiv.org/list/math.OC/new
[1/1]:
- A robust BFGS algorithm for unconstrained nonlinear optimization problems
Yaguang Yang
https://arxiv.org/abs/1212.5929
- Quantum computing and the stable set problem
Alja\v{z} Krpan, Janez Povh, Dunja Pucher
https://arxiv.org/abs/2405.12845 https://mastoxiv.page/@arXiv_mathOC_bot/112483516437815686
- Mean Field Game with Reflected Jump Diffusion Dynamics: A Linear Programming Approach
Zongxia Liang, Xiang Yu, Keyu Zhang
https://arxiv.org/abs/2508.20388 https://mastoxiv.page/@arXiv_mathOC_bot/115111048711698998
- Differential Dynamic Programming for the Optimal Control Problem with an Ellipsoidal Target Set a...
Sungjun Eom, Gyunghoon Park
https://arxiv.org/abs/2509.07546 https://mastoxiv.page/@arXiv_mathOC_bot/115179281556444440
- On the Moreau envelope properties of weakly convex functions
Marien Renaud, Arthur Leclaire, Nicolas Papadakis
https://arxiv.org/abs/2509.13960 https://mastoxiv.page/@arXiv_mathOC_bot/115224514482363803
- Automated algorithm design via Nevanlinna-Pick interpolation
Ibrahim K. Ozaslan, Tryphon T. Georgiou, Mihailo R. Jovanovic
https://arxiv.org/abs/2509.21416 https://mastoxiv.page/@arXiv_mathOC_bot/115286533597711930
- Optimal Control of a Bioeconomic Crop-Energy System with Energy Reinvestment
Othman Cherkaoui Dekkaki
https://arxiv.org/abs/2510.11381 https://mastoxiv.page/@arXiv_mathOC_bot/115372322896073250
- Point Convergence Analysis of the Accelerated Gradient Method for Multiobjective Optimization: Co...
Yingdong Yin
https://arxiv.org/abs/2510.26382 https://mastoxiv.page/@arXiv_mathOC_bot/115468018035252078
- History-Aware Adaptive High-Order Tensor Regularization
Chang He, Bo Jiang, Yuntian Jiang, Chuwen Zhang, Shuzhong Zhang
https://arxiv.org/abs/2511.05788
- Equivalence of entropy solutions and gradient flows for pressureless 1D Euler systems
Jos\'e Antonio Carrillo, Sondre Tesdal Galtung
https://arxiv.org/abs/2312.04932 https://mastoxiv.page/@arXiv_mathAP_bot/111560077272113052
- Kernel Modelling of Fading Memory Systems
Yongkang Huo, Thomas Chaffey, Rodolphe Sepulchre
https://arxiv.org/abs/2403.11945 https://mastoxiv.page/@arXiv_eessSY_bot/112121123836064435
- The Maximum Theoretical Ground Speed of the Wheeled Vehicle
Altay Zhakatayev, Mukatai Nemerebayev
https://arxiv.org/abs/2502.15341 https://mastoxiv.page/@arXiv_physicsclassph_bot/114057765769441123
- Hessian stability and convergence rates for entropic and Sinkhorn potentials via semiconcavity
Giacomo Greco, Luca Tamanini
https://arxiv.org/abs/2504.11133 https://mastoxiv.page/@arXiv_mathPR_bot/114346453424694503
- Optimizing the ground state energy of the three-dimensional magnetic Dirichlet Laplacian with con...
Matthias Baur
https://arxiv.org/abs/2504.21597 https://mastoxiv.page/@arXiv_mathph_bot/114431404740241516
- A localized consensus-based sampling algorithm
Arne Bouillon, Alexander Bodard, Panagiotis Patrinos, Dirk Nuyens, Giovanni Samaey
https://arxiv.org/abs/2505.24861 https://mastoxiv.page/@arXiv_mathNA_bot/114612580684567066
- A Novel Sliced Fused Gromov-Wasserstein Distance
Moritz Piening, Robert Beinert
https://arxiv.org/abs/2508.02364 https://mastoxiv.page/@arXiv_csLG_bot/114976243138728278
- Minimal Regret Walras Equilibria for Combinatorial Markets via Duality, Integrality, and Sensitiv...
Alo\"is Duguet, Tobias Harks, Martin Schmidt, Julian Schwarz
https://arxiv.org/abs/2511.09021 https://mastoxiv.page/@arXiv_csGT_bot/115541243299714775
toXiv_bot_toot

New book on the history of McGill University - written and edited by historians, not the university's comms department. I wrote a chapter on how Indigenous dispossession and colonial politicians saved McGill when it was in danger of going broke. Others cover McGill's ties to chattel slavery, Japanese exclusion, research of various sorts, student lives, queer experiences, and more.
Check it out:

Dual-Actor Fine-Tuning of VLA Models: A Talk-and-Tweak Human-in-the-Loop Approach
Piaopiao Jin, Qi Wang, Guokang Sun, Ziwen Cai, Pinjia He, Yangwei You
https://arxiv.org/abs/2509.13774

Dual-Actor Fine-Tuning of VLA Models: A Talk-and-Tweak Human-in-the-Loop Approach
Vision-language-action (VLA) models demonstrate strong generalization in robotic manipulation but face challenges in complex, real-world tasks. While supervised fine-tuning with demonstrations is constrained by data quality, reinforcement learning (RL) offers a promising alternative. We propose a human-in-the-loop dual-actor fine-tuning framework grounded in RL. The framework integrates a primary actor for robust multi-task performance with a refinement actor for latent-space adaptation. Beyond…

Non-associative structures in extended geometry
Martin Cederwall, Jakob Palmkvist
https://arxiv.org/abs/2509.14215 https://arxiv.org/pdf/2509.14215

Non-associative structures in extended geometry
We consider a generalisation of vector fields on a vector space, where the vector space is generalised to a highest-weight module over a Kac-Moody algebra. The generalised vector field is an element in a non-associative superalgebra defined by the module and the Kac-Moody algebra. Also the Lie derivative of a vector field parameterised by another is generalised and expressed in a simple way in terms of this superalgebra. It reproduces the generalised Lie derivative in the general framework of e…

one of the coolest things about the #bcndp convention has been the use if this little ballot book for voting for elected positions within the party.
They announce the number and colour of the page, you rip out the paper and use it to make your selection.
Then the committee folks go around with ballot boxes like offerings at church 😆
Democracy is cool wherever it happens and in all its iterations.
#bcndp #democracy

A counterexample to the $S_{10}$- and the $S_{12}$-Conjecture
Isaak H. Wolf
https://arxiv.org/abs/2509.14184 https://arxiv.org/pdf/2509.14184

A counterexample to the $S_{10}$- and the $S_{12}$-Conjecture
For two graphs $G$ and $H$, a mapping $f\colon E(G) \to E(H)$ is an $H$-coloring of $G$, if it is a proper edge-coloring and for every $v \in V(G)$ there exists a vertex $u \in V(H)$ with $f(\partial_G(v))=\partial_H(u)$. Motivated by the Petersen Coloring Conjecture, Mkrtchyan [A remark on the Petersen coloring conjecture of Jaeger, \emph{Australas. J. Combin.}, 56 (2013), 145-151] and Mkrtchyan together with Hakobyan [$S_{12}$ and $P_{12}$-colorings of cubic graphs, \emph{Ars Math. Contemp.},…

“TABS [by Mozilla] pulls exactly the data you need—from HTML to Markdown to JSON—using the fastest, most efficient method for each page. It adapts to the structure and complexity of the site, staying stealthy and reliable so your [AI] agents always get what they need without friction.”
Ethical Stealthy AI Scraping (tm) by Mozilla.
#Mozilla

📰 Deine Spende macht’s möglich: Ich informiere täglich über #Klima und #Forschung auf Deutsch, damit englischdominierte #Wissenschaftsmeldungen besser zugänglich werden. Danke für das Tei…

KlimaCrew
Ich informiere über Zukunftsthemen, um Menschen vor Risiken zu warnen und Fortschritte sichtbar zu machen.

Thom-Milnor bounds for smooth manifolds
Saugata Basu, Antonio Lerario, Matteo Testa
https://arxiv.org/abs/2509.14079 https://arxiv.org/pdf/2509.14079

Thom-Milnor bounds for smooth manifolds
We prove a smooth analogue of the classical Thom-Milnor bound, showing that the Betti numbers of the zero set of a smooth map on a compact Riemannian manifold can be controlled by a condition number computed from its first jet. This extends previous results in the Euclidean setting by Lerario and Stecconi [J. Singul., 2021]. As a key step, we generalize the Thom-Milnor bound to polynomial maps on a nonsingular real algebraic variety, improving the dependence on the degree. Finally, inspired by …

Py maidr: Bridging Visual and Non-Visual Data Experiences Through a Unified Python Framework
JooYoung Seo, Saairam Venkatesh, Daksh Pokar, Sanchita Kamath, Krishna Anandan Ganesan
https://arxiv.org/abs/2509.13532

Py maidr: Bridging Visual and Non-Visual Data Experiences Through a Unified Python Framework
Although recent efforts have developed accessible data visualization tools for blind and low-vision (BLV) users, most follow a "design for them" approach that creates an unintentional divide between sighted creators and BLV consumers. This unidirectional paradigm perpetuates a power dynamic where sighted creators produce non-visual content boundaries for BLV consumers to access. This paper proposes a bidirectional approach, "design for us," where both sighted and BLV collaborators can employ th…

Is Research Software Science a Metascience?
Evan Eisinger, Michael A. Heroux
https://arxiv.org/abs/2509.13436 https://arxiv.org/pdf/2509.13436

Is Research Software Science a Metascience?
As research increasingly relies on computational methods, the reliability of scientific results depends on the quality, reproducibility, and transparency of research software. Ensuring these qualities is critical for scientific integrity and discovery. This paper asks whether Research Software Science (RSS)--the empirical study of how research software is developed and used--should be considered a form of metascience, the science of science. Classification matters because it could affect recogn…

Defining a classification system for augmentation technology in socio-technical terms
Isabel Pedersen, Ann Hill Duin
https://arxiv.org/abs/2509.13340 https://

Defining a classification system for augmentation technology in socio-technical terms
This short paper provides a means to classify augmentation technologies to reconceptualize them as sociotechnical, discursive and rhetorical phenomena, rather than only through technological classifications. It identifies a set of value systems that constitute augmentation technologies within discourses, namely, the intent to enhance, automate, and build efficiency. This short paper makes a contribution to digital literacy surrounding augmentation technology emergence, as well as the more speci…

Say No to China’s Cruel New “Monkey Business” #AnimalRights

Circuit realization and hardware linearization of monotone operator equilibrium networks
Thomas Chaffey
https://arxiv.org/abs/2509.13793 https://arxiv.org/…

Circuit realization and hardware linearization of monotone operator equilibrium networks
It is shown that the port behavior of a resistor- diode network corresponds to the solution of a ReLU monotone operator equilibrium network (a neural network in the limit of infinite depth), giving a parsimonious construction of a neural network in analog hardware. We furthermore show that the gradient of such a circuit can be computed directly in hardware, using a procedure we call hardware linearization. This allows the network to be trained in hardware, which we demonstrate with a device-lev…

Tractability Frontiers of the Shapley Value for Aggregate Conjunctive Queries
Christoph Standke, Benny Kimelfeld
https://arxiv.org/abs/2509.13565 https://a…

Tractability Frontiers of the Shapley Value for Aggregate Conjunctive Queries
In recent years, the Shapley value has emerged as a general game-theoretic measure for assessing the contribution of a tuple to the result of a database query. We study the complexity of calculating the Shapley value of a tuple for an aggregate conjunctive query, which applies an aggregation function to the result of a conjunctive query (CQ) based on a value function that assigns a number to each query answer. Prior work by Livshits, Bertossi, Kimelfeld, and Sebag (2020) established that this t…

Classification Filtering
Ilker Bayram
https://arxiv.org/abs/2509.13975 https://arxiv.org/pdf/2509.13975

Classification Filtering
We consider a streaming signal in which each sample is linked to a latent class. We assume that multiple classifiers are available, each providing class probabilities with varying degrees of accuracy. These classifiers are employed following a straightforward and fixed policy. In this setting, we consider the problem of fusing the output of the classifiers while incorporating the temporal aspect to improve classification accuracy. We propose a state-space model and develop a filter tailored for…

Modeling the Carbon Footprint of HPC: The Top 500 and EasyC
Varsha Rao, Andrew A. Chien
https://arxiv.org/abs/2509.13583 https://arxiv.org/pdf/2509.13583…

Modeling the Carbon Footprint of HPC: The Top 500 and EasyC
Climate change is a critical concern for HPC systems, but GHG protocol carbon-emission accounting methodologies are difficult for a single system, and effectively infeasible for a collection of systems. As a result, there is no HPC-wide carbon reporting, and even the largest HPC sites do not do GHG protocol reporting. We assess the carbon footprint of HPC, focusing on the Top 500 systems. The key challenge lies in modeling the carbon footprint with limited data availability. With the disclo…

Wrong.
#google #ai #slop

Local existence theory for a class of CMC gauges for the Einstein-non-linear scalar field equations
Hans Ringstr\"om
https://arxiv.org/abs/2509.14110 https://

Local existence theory for a class of CMC gauges for the Einstein-non-linear scalar field equations
The purpose of this article is to develop a local existence theory for a class of CMC gauges for the Einstein-non-linear scalar field equations. We do so in the context of closed and parallelisable initial manifolds. The assumption that the initial manifold is parallelisable is not a topological restriction in the case of closed oriented 3-manifolds, but it is a restriction in higher dimensions. The results include local existence, uniqueness, a continuation criterion and Cauchy stability. Prev…

A Compositional Kernel Model for Feature Learning
Feng Ruan, Keli Liu, Michael Jordan
https://arxiv.org/abs/2509.14158 https://arxiv.org/pdf/2509.14158

A Compositional Kernel Model for Feature Learning
We study a compositional variant of kernel ridge regression in which the predictor is applied to a coordinate-wise reweighting of the inputs. Formulated as a variational problem, this model provides a simple testbed for feature learning in compositional architectures. From the perspective of variable selection, we show how relevant variables are recovered while noise variables are eliminated. We establish guarantees showing that both global minimizers and stationary points discard noise coordin…

MOCHA: Multi-modal Objects-aware Cross-arcHitecture Alignment
Elena Camuffo, Francesco Barbato, Mete Ozay, Simone Milani, Umberto Michieli
https://arxiv.org/abs/2509.14001 https…

MOCHA: Multi-modal Objects-aware Cross-arcHitecture Alignment
We introduce MOCHA (Multi-modal Objects-aware Cross-arcHitecture Alignment), a knowledge distillation approach that transfers region-level multimodal semantics from a large vision-language teacher (e.g., LLaVa) into a lightweight vision-only object detector student (e.g., YOLO). A translation module maps student features into a joint space, where the training of the student and translator is guided by a dual-objective loss that enforces both local alignment and global relational consistency. Un…

I have a Frequently Asked Questions page!
This covers my process, payment, free stuff and pricing.
If there's a question you have about my work that isn't listed, then please let me know.
#faq #frequentlyaskedquestions

Extended Abstract: Towards a Performance Comparison of Syntax and Type-Directed NbE
Chester J. F. Gould, William J. Bowman
https://arxiv.org/abs/2509.13489 https://

Extended Abstract: Towards a Performance Comparison of Syntax and Type-Directed NbE
A key part of any dependent type-checker is the method for checking whether two types are equal. A common claim is that syntax-directed equality is more performant, although type-directed equality is more expressive. However, this claim is difficult to make precise, since implementations choose only one or the other approach, making a direct comparison impossible. We present some work-in-progress developing a realistic platform for direct, apples-to-apples, comparison of the two approaches, qua…

Gen AI in Proof-based Math Courses: A Pilot Study
Hannah Klawa, Shraddha Rajpal, Cigole Thomas
https://arxiv.org/abs/2509.13570 https://arxiv.org/pdf/2509.…

Gen AI in Proof-based Math Courses: A Pilot Study
With the rapid rise of generative AI in higher education and the unreliability of current AI detection tools, developing policies that encourage student learning and critical thinking has become increasingly important. This study examines student use and perceptions of generative AI across three proof-based undergraduate mathematics courses: a first-semester abstract algebra course, a topology course and a second-semester abstract algebra course. In each case, course policy permitted some use o…

Framing Migration: A Computational Analysis of UK Parliamentary Discourse
Vahid Ghafouri, Robert McNeil, Teodor Yankov, Madeleine Sumption, Luc Rocher, Scott A. Hale, Adam Mahdi
https://arxiv.org/abs/2509.14197

Framing Migration: A Computational Analysis of UK Parliamentary Discourse
We present a large-scale computational analysis of migration-related discourse in UK parliamentary debates spanning over 75 years and compare it with US congressional discourse. Using open-weight LLMs, we annotate each statement with high-level stances toward migrants and track the net tone toward migrants across time and political parties. For the UK, we extend this with a semi-automated framework for extracting fine-grained narrative frames to capture nuances of migration discourse. Our findi…

A Tight Quantum Algorithm for Multiple Collision Search
Xavier Bonnetain, Johanna Loyer, Andr\'e Schrottenloher, Yixin Shen
https://arxiv.org/abs/2509.13909 https://

A Tight Quantum Algorithm for Multiple Collision Search
Searching for collisions in random functions is a fundamental computational problem, with many applications in symmetric and asymmetric cryptanalysis. When one searches for a single collision, the known quantum algorithms match the query lower bound. This is not the case for the problem of finding multiple collisions, despite its regular appearance as a sub-component in sieving-type algorithms. At EUROCRYPT 2019, Liu and Zhandry gave a query lower bound $Ω(2^{m/3 + 2k/3})$ for finding $2^k$ …

GeoAware-VLA: Implicit Geometry Aware Vision-Language-Action Model
Ali Abouzeid, Malak Mansour, Zezhou Sun, Dezhen Song
https://arxiv.org/abs/2509.14117 https://

GeoAware-VLA: Implicit Geometry Aware Vision-Language-Action Model
Vision-Language-Action (VLA) models often fail to generalize to novel camera viewpoints, a limitation stemming from their difficulty in inferring robust 3D geometry from 2D images. We introduce GeoAware-VLA, a simple yet effective approach that enhances viewpoint invariance by integrating strong geometric priors into the vision backbone. Instead of training a visual encoder or relying on explicit 3D data, we leverage a frozen, pretrained geometric vision model as a feature extractor. A trainabl…

The Cybersecurity of a Humanoid Robot
V\'ictor Mayoral-Vilches
https://arxiv.org/abs/2509.14096 https://arxiv.org/pdf/2509.14096

The Cybersecurity of a Humanoid Robot
The rapid advancement of humanoid robotics presents unprecedented cybersecurity challenges that existing theoretical frameworks fail to adequately address. This report presents a comprehensive security assessment of a production humanoid robot platform, bridging the gap between abstract security models and operational vulnerabilities. Through systematic static analysis, runtime observation, and cryptographic examination, we uncovered a complex security landscape characterized by both sophistica…

An Automaton-based Characterisation of First-Order Logic over Infinite Trees
Massimo Benerecetti (Universit\`a degli Studi di Napoli "Federico II"), Dario Della Monica (Universit\`a degli Studi di Udine), Angelo Matteo (Universit\`a degli Studi di Udine), Fabio Mogavero (Universit\`a degli Studi di Napoli "Federico II"), Gabriele Puppis (Universit\`a degli Studi di Udine)

An Automaton-based Characterisation of First-Order Logic over Infinite Trees
In this paper, we study First Order Logic (FO) over (unordered) infinite trees and its connection with branching-time temporal logics. More specifically, we provide an automata-theoretic characterisation of FO interpreted over infinite trees. To this end, two different classes of hesitant tree automata are introduced and proved to capture precisely the expressive power of two branching time temporal logics, denoted polcCTLp and cCTL*[f], which are, respectively, a restricted version of counti…

When Avatars Have Personality: Effects on Engagement and Communication in Immersive Medical Training
Julia S. Dollis, Iago A. Brito, Fernanda B. F\"arber, Pedro S. F. B. Ribeiro, Rafael T. Sousa, Arlindo R. Galv\~ao Filho
https://arxiv.org/abs/2509.14132

When Avatars Have Personality: Effects on Engagement and Communication in Immersive Medical Training
While virtual reality (VR) excels at simulating physical environments, its effectiveness for training complex interpersonal skills is limited by a lack of psychologically plausible virtual humans. This is a critical gap in high-stakes domains like medical education, where communication is a core competency. This paper introduces a framework that integrates large language models (LLMs) into immersive VR to create medically coherent virtual patients with distinct, consistent personalities, built …

Prompt2DAG: A Modular Methodology for LLM-Based Data Enrichment Pipeline Generation
Abubakari Alidu, Michele Ciavotta, Flavio DePaoli
https://arxiv.org/abs/2509.13487 https://…

Prompt2DAG: A Modular Methodology for LLM-Based Data Enrichment Pipeline Generation
Developing reliable data enrichment pipelines demands significant engineering expertise. We present Prompt2DAG, a methodology that transforms natural language descriptions into executable Apache Airflow DAGs. We evaluate four generation approaches -- Direct, LLM-only, Hybrid, and Template-based -- across 260 experiments using thirteen LLMs and five case studies to identify optimal strategies for production-grade automation. Performance is measured using a penalized scoring framework that combin…

The column number for 3-modular matrices
Joseph Paat, Zach Walsh, Luze Xu
https://arxiv.org/abs/2509.13463 https://arxiv.org/pdf/2509.13463

The column number for 3-modular matrices
An integer-valued matrix $\mathbf{A}$ is $Δ$-modular if each $\text{rank}(\mathbf{A}) \times \text{rank}(\mathbf{A})$ submatrix has determinant at most $Δ$ in absolute value. The column number problem is to determine the maximum number of pairwise non-parallel columns of a rank-$r$, $Δ$-modular matrix. Exact values for the column number are only known for $r \le 2$ or $Δ\le 2$. We prove that if $r$ is sufficiently large, then the maximum number of pairwise non-parallel columns of a rank-$r$…

The Economics of Information Pollution in the Age of AI: A General Equilibrium Approach to Welfare, Measurement, and Policy
Yukun Zhang, Tianyang Zhang
https://arxiv.org/abs/2509.13729

The Economics of Information Pollution in the Age of AI: A General Equilibrium Approach to Welfare, Measurement, and Policy
The advent of Large Language Models (LLMs) represents a fundamental shock to the economics of information production. By asymmetrically collapsing the marginal cost of generating low-quality, synthetic content while leaving high-quality production costly, AI systematically incentivizes information pollution. This paper develops a general equilibrium framework to analyze this challenge. We model the strategic interactions among a monopolistic platform, profit-maximizing producers, and utility-ma…

WatchAnxiety: A Transfer Learning Approach for State Anxiety Prediction from Smartwatch Data
Md Sabbir Ahmed, Noah French, Mark Rucker, Zhiyuan Wang, Taylor Myers-Brower, Kaitlyn Petz, Mehdi Boukhechba, Bethany A. Teachman, Laura E. Barnes
https://arxiv.org/abs/2509.13725

WatchAnxiety: A Transfer Learning Approach for State Anxiety Prediction from Smartwatch Data
Social anxiety is a common mental health condition linked to significant challenges in academic, social, and occupational functioning. A core feature is elevated momentary (state) anxiety in social situations, yet little prior work has measured or predicted fluctuations in this anxiety throughout the day. Capturing these intra-day dynamics is critical for designing real-time, personalized interventions such as Just-In-Time Adaptive Interventions (JITAIs). To address this gap, we conducted a stu…

Can Current AI Models Count What We Mean, Not What They See? A Benchmark and Systematic Evaluation
Gia Khanh Nguyen, Yifeng Huang, Minh Hoai
https://arxiv.org/abs/2509.13939 htt…

Can Current AI Models Count What We Mean, Not What They See? A Benchmark and Systematic Evaluation
Visual counting is a fundamental yet challenging task, especially when users need to count objects of a specific type in complex scenes. While recent models, including class-agnostic counting models and large vision-language models (VLMs), show promise in counting tasks, their ability to perform fine-grained, intent-driven counting remains unclear. In this paper, we introduce PairTally, a benchmark dataset specifically designed to evaluate fine-grained visual counting. Each of the 681 high-reso…

Semantic Fusion with Fuzzy-Membership Features for Controllable Language Modelling
Yongchao Huang, Hassan Raza
https://arxiv.org/abs/2509.13357 https://arx…

Semantic Fusion with Fuzzy-Membership Features for Controllable Language Modelling
We propose semantic fusion, a lightweight scheme that augments a Transformer language model (LM) with a parallel, fuzzy-membership feature channel that encodes token-level semantics. Each token is represented by a vector of interpretable features (e.g. part-of-speech cues, shallow roles, boundary flags, sentiment polarity and strength) whose values are graded degrees from differentiable membership functions (e.g. power kernels). These per-token vectors form a sentence-level semantic matrix fuse…

AssoCiAm: A Benchmark for Evaluating Association Thinking while Circumventing Ambiguity
Yifan Liu, Wenkuan Zhao, Shanshan Zhong, Jinghui Qin, Mingfu Liang, Zhongzhan Huang, Wushao Wen
https://arxiv.org/abs/2509.14171

AssoCiAm: A Benchmark for Evaluating Association Thinking while Circumventing Ambiguity
Recent advancements in multimodal large language models (MLLMs) have garnered significant attention, offering a promising pathway toward artificial general intelligence (AGI). Among the essential capabilities required for AGI, creativity has emerged as a critical trait for MLLMs, with association serving as its foundation. Association reflects a model' s ability to think creatively, making it vital to evaluate and understand. While several frameworks have been proposed to assess associative abi…

Coherent Driving of a Quantum System with Modulated Free-Space Electrons
Matthias Kolb, Thomas Spielauer, Thomas Weigner, Giovanni Boero, Dennis R\"atzel, Philipp Haslinger
https://arxiv.org/abs/2509.13904

Coherent Driving of a Quantum System with Modulated Free-Space Electrons
Control of quantum systems typically relies on the interaction with electromagnetic radiation. In this study, we experimentally show that the electromagnetic near-field of a spatially modulated freespace electron beam can be used to drive spin systems, demonstrating free-electron-bound-electron resonant interaction. By periodically deflecting the electron beam of a scanning electron microscope in close proximity to a spin-active solid-state sample, and sweeping the deflection frequency across t…

Soft Regrasping Tool Inspired by Jamming Gripper
Takuya Kiyokawa, Zhengtao Hu, Weiwei Wan, Kensuke Harada
https://arxiv.org/abs/2509.13815 https://arxiv.or…

Soft Regrasping Tool Inspired by Jamming Gripper
Regrasping on fixtures is a promising approach to reduce pose uncertainty in robotic assembly, but conventional rigid fixtures lack adaptability and require dedicated designs for each part. To overcome this limitation, we propose a soft jig inspired by the jamming transition phenomenon, which can be continuously deformed to accommodate diverse object geometries. By pressing a triangular-pyramid-shaped tool into the membrane and evacuating the enclosed air, a stable cavity is formed as a placeme…

Cybersecurity AI: Humanoid Robots as Attack Vectors
V\'ictor Mayoral-Vilches
https://arxiv.org/abs/2509.14139 https://arxiv.org/pdf/2509.14139

Cybersecurity AI: Humanoid Robots as Attack Vectors
We present a systematic security assessment of the Unitree G1 humanoid showing it operates simultaneously as a covert surveillance node and can be purposed as an active cyber operations platform. Partial reverse engineering of Unitree's proprietary FMX encryption reveal a static Blowfish-ECB layer and a predictable LCG mask-enabled inspection of the system's otherwise sophisticated security architecture, the most mature we have observed in commercial robotics. Two empirical case studies expose …

On the set of fixed points for NRS($m$)
Mario DeFranco
https://arxiv.org/abs/2509.14176 https://arxiv.org/pdf/2509.14176

On the set of fixed points for NRS($m$)
Let $f(z)$ be a degree $d$ polynomial with zeros $z_i$. For arbitrary $m$ we construct explicit set of fixed points (attractors) of NRS($m$), and prove a factored formula for the Jacobian at these points. We prove that if NRS(2), when applied to $f$ with an arbitrary starting point, converges to a point $(w_0, w_1)$, then $w_0$ is of the form $z_i+z_j$ for some $i \neq j$. As a corollary, we prove a formula expressing the elementary symmetric expansion of the function \[ \prod_{1\leq i < j \leq…

Towards a Physics Foundation Model
Florian Wiesner, Matthias Wessling, Stephen Baek
https://arxiv.org/abs/2509.13805 https://arxiv.org/pdf/2509.13805

Towards a Physics Foundation Model
Foundation models have revolutionized natural language processing through a ``train once, deploy anywhere'' paradigm, where a single pre-trained model adapts to countless downstream tasks without retraining. Access to a Physics Foundation Model (PFM) would be transformative -- democratizing access to high-fidelity simulations, accelerating scientific discovery, and eliminating the need for specialized solver development. Yet current physics-aware machine learning approaches remain fundamentally…

AI as a teaching tool and learning partner
Steven Watterson, Sarah Atkinson, Elaine Murray, Andrew McDowell
https://arxiv.org/abs/2509.13899 https://arxiv.…

AI as a teaching tool and learning partner
The arrival of AI tools and in particular Large Language Models (LLMs) has had a transformative impact on teaching and learning and institutes are still trying to determine how to integrate LLMs into education in constructive ways. Here, we explore the adoption of LLM-based tools into two teaching programmes, one undergraduate and one postgraduate. We provided to our classes (1) a LLM-powered chatbot that had access to course materials by RAG and (2) AI-generated audio-only podcasts for each we…

From Next Token Prediction to (STRIPS) World Models -- Preliminary Results
Carlos N\'u\~nez-Molina, Vicen\c{c} G\'omez, Hector Geffner
https://arxiv.org/abs/2509.13389 h…

From Next Token Prediction to (STRIPS) World Models -- Preliminary Results
We consider the problem of learning propositional STRIPS world models from action traces alone, using a deep learning architecture (transformers) and gradient descent. The task is cast as a supervised next token prediction problem where the tokens are the actions, and an action $a$ may follow an action sequence if the hidden effects of the previous actions do not make an action precondition of $a$ false. We show that a suitable transformer architecture can faithfully represent propositional STR…

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…

Observation of topological Phenomena in a Weyl Exceptional Ring with Single Photons
Zhong-Sheng Chen, Wei-Xin Chen, Fan Wu, Zhong-Wei Xu, Jing Ma, Yun-Kun Jiang, Huai-Zhi Wu, Shi-Biao Zheng
https://arxiv.org/abs/2509.13708

Observation of topological Phenomena in a Weyl Exceptional Ring with Single Photons
Compared with Hermitian theory, non-Hermitian physics offers a fundamentally different mathematical framework, enabling the observation of topological phenomena that have no analogue in Hermitian systems. Among these, the exceptional point (EP) ring stands out as a quintessential topological feature unique to non-Hermitian systems. In this study, we employ single-photon interferometry to overcome the experimental challenge of precise phase control in quantum systems, thereby enabling a complete…

GenExam: A Multidisciplinary Text-to-Image Exam
Zhaokai Wang, Penghao Yin, Xiangyu Zhao, Changyao Tian, Yu Qiao, Wenhai Wang, Jifeng Dai, Gen Luo
https://arxiv.org/abs/2509.14232

GenExam: A Multidisciplinary Text-to-Image Exam
Exams are a fundamental test of expert-level intelligence and require integrated understanding, reasoning, and generation. Existing exam-style benchmarks mainly focus on understanding and reasoning tasks, and current generation benchmarks emphasize the illustration of world knowledge and visual concepts, neglecting the evaluation of rigorous drawing exams. We introduce GenExam, the first benchmark for multidisciplinary text-to-image exams, featuring 1,000 samples across 10 subjects with exam-st…

Personalization on a Budget: Minimally-Labeled Continual Learning for Resource-Efficient Seizure Detection
Amirhossein Shahbazinia, Jonathan Dan, Jose A. Miranda, Giovanni Ansaloni, David Atienza
https://arxiv.org/abs/2509.13974

Personalization on a Budget: Minimally-Labeled Continual Learning for Resource-Efficient Seizure Detection
Objective: Epilepsy, a prevalent neurological disease, demands careful diagnosis and continuous care. Seizure detection remains challenging, as current clinical practice relies on expert analysis of electroencephalography, which is a time-consuming process and requires specialized knowledge. Addressing this challenge, this paper explores automated epileptic seizure detection using deep learning, focusing on personalized continual learning models that adapt to each patient's unique electroenceph…

GLIDE: A Coordinated Aerial-Ground Framework for Search and Rescue in Unknown Environments
Seth Farrell, Chenghao Li, Hongzhan Yu, Hesam Mojtahedi, Sicun Gao, Henrik I. Christensen
https://arxiv.org/abs/2509.14210

GLIDE: A Coordinated Aerial-Ground Framework for Search and Rescue in Unknown Environments
We present a cooperative aerial-ground search-and-rescue (SAR) framework that pairs two unmanned aerial vehicles (UAVs) with an unmanned ground vehicle (UGV) to achieve rapid victim localization and obstacle-aware navigation in unknown environments. We dub this framework Guided Long-horizon Integrated Drone Escort (GLIDE), highlighting the UGV's reliance on UAV guidance for long-horizon planning. In our framework, a goal-searching UAV executes real-time onboard victim detection and georeferenci…

Differential Privacy in Federated Learning: Mitigating Inference Attacks with Randomized Response
Ozer Ozturk, Busra Buyuktanir, Gozde Karatas Baydogmus, Kazim Yildiz
https://arxiv.org/abs/2509.13987

Differential Privacy in Federated Learning: Mitigating Inference Attacks with Randomized Response
Machine learning models used for distributed architectures consisting of servers and clients require large amounts of data to achieve high accuracy. Data obtained from clients are collected on a central server for model training. However, storing data on a central server raises concerns about security and privacy. To address this issue, a federated learning architecture has been proposed. In federated learning, each client trains a local model using its own data. The trained models are periodic…

Vistoria: A Multimodal System to Support Fictional Story Writing through Instrumental Text-Image Co-Editing
Kexue Fu, Jingfei Huang, Long Ling, Sumin Hong, Yihang Zuo, Ray LC, Toby Jia-jun Li
https://arxiv.org/abs/2509.13646

Vistoria: A Multimodal System to Support Fictional Story Writing through Instrumental Text-Image Co-Editing
Humans think visually-we remember in images, dream in pictures, and use visual metaphors to communicate. Yet, most creative writing tools remain text-centric, limiting how authors plan and translate ideas. We present Vistoria, a system for synchronized text-image co-editing in fictional story writing that treats visuals and text as coequal narrative materials. A formative Wizard-of-Oz co-design study with 10 story writers revealed how sketches, images, and annotations serve as essential instrum…

Explicit Reasoning Makes Better Judges: A Systematic Study on Accuracy, Efficiency, and Robustness
Pratik Jayarao, Himanshu Gupta, Neeraj Varshney, Chaitanya Dwivedi
https://arxiv.org/abs/2509.13332

Explicit Reasoning Makes Better Judges: A Systematic Study on Accuracy, Efficiency, and Robustness
As Large Language Models (LLMs) are increasingly adopted as automated judges in benchmarking and reward modeling, ensuring their reliability, efficiency, and robustness has become critical. In this work, we present a systematic comparison of "thinking" and "non-thinking" LLMs in the LLM-as-a-judge paradigm using open-source Qwen 3 models of relatively small sizes (0.6B, 1.7B, and 4B parameters). We evaluate both accuracy and computational efficiency (FLOPs) on RewardBench tasks, and further exa…

Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale
Hasan Abed Al Kader Hammoud, Mohammad Zbeeb, Bernard Ghanem
https://arxiv.org/abs/2509.14008

Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale
We present Hala, a family of Arabic-centric instruction and translation models built with our translate-and-tune pipeline. We first compress a strong AR$\leftrightarrow$EN teacher to FP8 (yielding $\sim$2$\times$ higher throughput with no quality loss) and use it to create high-fidelity bilingual supervision. A lightweight language model LFM2-1.2B is then fine-tuned on this data and used to translate high-quality English instruction sets into Arabic, producing a million-scale corpus tailored to…

A Conformal Prediction Framework for Uncertainty Quantification in Physics-Informed Neural Networks
Yifan Yu, Cheuk Hin Ho, Yangshuai Wang
https://arxiv.org/abs/2509.13717 https…

A Conformal Prediction Framework for Uncertainty Quantification in Physics-Informed Neural Networks
Physics-Informed Neural Networks (PINNs) have emerged as a powerful framework for solving PDEs, yet existing uncertainty quantification (UQ) approaches for PINNs generally lack rigorous statistical guarantees. In this work, we bridge this gap by introducing a distribution-free conformal prediction (CP) framework for UQ in PINNs. This framework calibrates prediction intervals by constructing nonconformity scores on a calibration set, thereby yielding distribution-free uncertainty estimates with …

Morphology-optimized Multi-Scale Fusion: Combining Local Artifacts and Mesoscopic Semantics for Deepfake Detection and Localization
Chao Shuai, Gaojian Wang, Kun Pan, Tong Wu, Fanli Jin, Haohan Tan, Mengxiang Li, Zhenguang Liu, Feng Lin, Kui Ren
https://arxiv.org/abs/2509.13776

Morphology-optimized Multi-Scale Fusion: Combining Local Artifacts and Mesoscopic Semantics for Deepfake Detection and Localization
While the pursuit of higher accuracy in deepfake detection remains a central goal, there is an increasing demand for precise localization of manipulated regions. Despite the remarkable progress made in classification-based detection, accurately localizing forged areas remains a significant challenge. A common strategy is to incorporate forged region annotations during model training alongside manipulated images. However, such approaches often neglect the complementary nature of local detail and…

Quantum keystroke logging
En-Jui Chang
https://arxiv.org/abs/2509.13659 https://arxiv.org/pdf/2509.13659

Quantum keystroke logging
We propose a \textit{quantum keystroke logging} scheme in the context of GKP-based quantum communication. The central idea is that, if a communication provider controls the preparation of encoded states, it may be able to infer logical operations applied by users prior to transmission. We show that phase estimation can be adapted to this setting despite two obstacles: GKP codewords are not eigenstates of the logical operators, and realistic communication involves one-shot operations rather than…

MCGS-SLAM: A Multi-Camera SLAM Framework Using Gaussian Splatting for High-Fidelity Mapping
Zhihao Cao, Hanyu Wu, Li Wa Tang, Zizhou Luo, Zihan Zhu, Wei Zhang, Marc Pollefeys, Martin R. Oswald
https://arxiv.org/abs/2509.14191

MCGS-SLAM: A Multi-Camera SLAM Framework Using Gaussian Splatting for High-Fidelity Mapping
Recent progress in dense SLAM has primarily targeted monocular setups, often at the expense of robustness and geometric coverage. We present MCGS-SLAM, the first purely RGB-based multi-camera SLAM system built on 3D Gaussian Splatting (3DGS). Unlike prior methods relying on sparse maps or inertial data, MCGS-SLAM fuses dense RGB inputs from multiple viewpoints into a unified, continuously optimized Gaussian map. A multi-camera bundle adjustment (MCBA) jointly refines poses and depths via dense …

Deep Learning-Driven Peptide Classification in Biological Nanopores
Samuel Tovey, Julian Ho{\ss}bach, Sandro Kuppel, Tobias Ensslen, Jan C. Behrends, Christian Holm
https://arxiv.org/abs/2509.14029

Deep Learning-Driven Peptide Classification in Biological Nanopores
A device capable of performing real time classification of proteins in a clinical setting would allow for inexpensive and rapid disease diagnosis. One such candidate for this technology are nanopore devices. These devices work by measuring a current signal that arises when a protein or peptide enters a nanometer-length-scale pore. Should this current be uniquely related to the structure of the peptide and its interactions with the pore, the signals can be used to perform identification. While s…

InfraMind: A Novel Exploration-based GUI Agentic Framework for Mission-critical Industrial Management
Liangtao Lin, Zhaomeng Zhu, Tianwei Zhang, Yonggang Wen
https://arxiv.org/abs/2509.13704

InfraMind: A Novel Exploration-based GUI Agentic Framework for Mission-critical Industrial Management
Mission-critical industrial infrastructure, such as data centers, increasingly depends on complex management software. Its operations, however, pose significant challenges due to the escalating system complexity, multi-vendor integration, and a shortage of expert operators. While Robotic Process Automation (RPA) offers partial automation through handcrafted scripts, it suffers from limited flexibility and high maintenance costs. Recent advances in Large Language Model (LLM)-based graphical user…

CL$^2$GEC: A Multi-Discipline Benchmark for Continual Learning in Chinese Literature Grammatical Error Correction
Shang Qin, Jingheng Ye, Yinghui Li, Hai-Tao Zheng, Qi Li, Jinxiao Shan, Zhixing Li, Hong-Gee Kim
https://arxiv.org/abs/2509.13672

CL$^2$GEC: A Multi-Discipline Benchmark for Continual Learning in Chinese Literature Grammatical Error Correction
The growing demand for automated writing assistance in diverse academic domains highlights the need for robust Chinese Grammatical Error Correction (CGEC) systems that can adapt across disciplines. However, existing CGEC research largely lacks dedicated benchmarks for multi-disciplinary academic writing, overlooking continual learning (CL) as a promising solution to handle domain-specific linguistic variation and prevent catastrophic forgetting. To fill this crucial gap, we introduce CL$^2$GEC,…

Free mutual information and higher-point OTOCs
Shreya Vardhan, Jinzhao Wang
https://arxiv.org/abs/2509.13406 https://arxiv.org/pdf/2509.13406

Free mutual information and higher-point OTOCs
We introduce a quantity called the free mutual information (FMI), adapted from concepts in free probability theory, as a new physical measure of quantum chaos. This quantity captures the spreading of a time-evolved operator in the space of all possible operators on the Hilbert space, which is doubly exponential in the number of degrees of freedom. It thus provides a finer notion of operator spreading than the well-understood phenomenon of operator growth in physical space. We derive two central…

The Influence of Facial Features on the Perceived Trustworthiness of a Social Robot
Benedict Barrow, Roger K. Moore
https://arxiv.org/abs/2509.13948 https://

The Influence of Facial Features on the Perceived Trustworthiness of a Social Robot
Trust and the perception of trustworthiness play an important role in decision-making and our behaviour towards others, and this is true not only of human-human interactions but also of human-robot interactions. While significant advances have been made in recent years in the field of social robotics, there is still some way to go before we fully understand the factors that influence human trust in robots. This paper presents the results of a study into the first impressions created by a social…

Diving into Mitigating Hallucinations from a Vision Perspective for Large Vision-Language Models
Weihang Wang, Xinhao Li, Ziyue Wang, Yan Pang, Jielei Zhang, Peiyi Li, Qiang Zhang, Longwen Gao
https://arxiv.org/abs/2509.13836

Diving into Mitigating Hallucinations from a Vision Perspective for Large Vision-Language Models
Object hallucination in Large Vision-Language Models (LVLMs) significantly impedes their real-world applicability. As the primary component for accurately interpreting visual information, the choice of visual encoder is pivotal. We hypothesize that the diverse training paradigms employed by different visual encoders instill them with distinct inductive biases, which leads to their diverse hallucination performances. Existing benchmarks typically focus on coarse-grained hallucination detection a…

The Art of Saying "Maybe": A Conformal Lens for Uncertainty Benchmarking in VLMs
Asif Azad, Mohammad Sadat Hossain, MD Sadik Hossain Shanto, M Saifur Rahman, Md Rizwan Pervez
https://arxiv.org/abs/2509.13379

The Art of Saying "Maybe": A Conformal Lens for Uncertainty Benchmarking in VLMs
Vision-Language Models (VLMs) have achieved remarkable progress in complex visual understanding across scientific and reasoning tasks. While performance benchmarking has advanced our understanding of these capabilities, the critical dimension of uncertainty quantification has received insufficient attention. Therefore, unlike prior conformal prediction studies that focused on limited settings, we conduct a comprehensive uncertainty benchmarking study, evaluating 16 state-of-the-art VLMs (open a…

Language models' activations linearly encode training-order recency
Dmitrii Krasheninnikov, Richard E. Turner, David Krueger
https://arxiv.org/abs/2509.14223 https://…

Language models' activations linearly encode training-order recency
We show that language models' activations linearly encode when information was learned during training. Our setup involves creating a model with a known training order by sequentially fine-tuning Llama-3.2-1B on six disjoint but otherwise similar datasets about named entities. We find that the average activations of test samples for the six training datasets encode the training order: when projected into a 2D subspace, these centroids are arranged exactly in the order of training and lie on a s…

The original Wigner's-Friend scenarios
Jay Lawrence
https://arxiv.org/abs/2509.13470 https://arxiv.org/pdf/2509.13470

The original Wigner's-Friend scenarios
We describe the Wigner's-Friend scenario according to Wigner, then a similar but earlier version according to Everett. Wigner and Everett provide different resolutions of essentially the same paradox. Decoherence theory provides a third resolution. Despite different interpretations (or their absence), these three stories fit together to form a consistent picture without a paradox.

Op-Fed: Opinion, Stance, and Monetary Policy Annotations on FOMC Transcripts Using Active Learning
Alisa Kanganis, Katherine A. Keith
https://arxiv.org/abs/2509.13539 https://…

Op-Fed: Opinion, Stance, and Monetary Policy Annotations on FOMC Transcripts Using Active Learning
The U.S. Federal Open Market Committee (FOMC) regularly discusses and sets monetary policy, affecting the borrowing and spending decisions of millions of people. In this work, we release Op-Fed, a dataset of 1044 human-annotated sentences and their contexts from FOMC transcripts. We faced two major technical challenges in dataset creation: imbalanced classes -- we estimate fewer than 8% of sentences express a non-neutral stance towards monetary policy -- and inter-sentence dependence -- 65% of …

Asterisk Operator
Zixi Li
https://arxiv.org/abs/2509.13364 https://arxiv.org/pdf/2509.13364

Asterisk Operator
We propose the \textbf{Asterisk Operator} ($\ast$-operator), a novel unified framework for abstract reasoning based on Adjacency-Structured Parallel Propagation (ASPP). The operator formalizes structured reasoning tasks as local, parallel state evolution processes guided by implicit relational graphs. We prove that the $\ast$-operator maintains local computational constraints while achieving global reasoning capabilities, providing an efficient and convergent computational paradigm for abstract…

FedSSG: Expectation-Gated and History-Aware Drift Alignment for Federated Learning
Zhanting Zhou, Jinshan Lai, Fengchun Zhang, Zeqin Wu, Fengli Zhang
https://arxiv.org/abs/2509.13895

FedSSG: Expectation-Gated and History-Aware Drift Alignment for Federated Learning
Non-IID data and partial participation induce client drift and inconsistent local optima in federated learning, causing unstable convergence and accuracy loss. We present FedSSG, a stochastic sampling-guided, history-aware drift alignment method. FedSSG maintains a per-client drift memory that accumulates local model differences as a lightweight sketch of historical gradients; crucially, it gates both the memory update and the local alignment term by a smooth function of the observed/expected p…

Learning Minimal Representations of Many-Body Physics from Snapshots of a Quantum Simulator
Frederik M{\o}ller, Gabriel Fern\'andez-Fern\'andez, Thomas Schweigler, Paulin de Schoulepnikoff, J\"org Schmiedmayer, Gorka Mu\~noz-Gil
https://arxiv.org/abs/2509.13821

Learning Minimal Representations of Many-Body Physics from Snapshots of a Quantum Simulator
Analog quantum simulators provide access to many-body dynamics beyond the reach of classical computation. However, extracting physical insights from experimental data is often hindered by measurement noise, limited observables, and incomplete knowledge of the underlying microscopic model. Here, we develop a machine learning approach based on a variational autoencoder (VAE) to analyze interference measurements of tunnel-coupled one-dimensional Bose gases, which realize the sine-Gordon quantum fi…

You Are What You Train: Effects of Data Composition on Training Context-aware Machine Translation Models
Pawe{\l} M\k{a}ka, Yusuf Can Semerci, Jan Scholtes, Gerasimos Spanakis
https://arxiv.org/abs/2509.14031

You Are What You Train: Effects of Data Composition on Training Context-aware Machine Translation Models
Achieving human-level translations requires leveraging context to ensure coherence and handle complex phenomena like pronoun disambiguation. Sparsity of contextually rich examples in the standard training data has been hypothesized as the reason for the difficulty of context utilization. In this work, we systematically validate this claim in both single- and multilingual settings by constructing training datasets with a controlled proportions of contextually relevant examples. We demonstrate a …

CrowdAgent: Multi-Agent Managed Multi-Source Annotation System
Maosheng Qin, Renyu Zhu, Mingxuan Xia, Chenkai Chen, Zhen Zhu, Minmin Lin, Junbo Zhao, Lu Xu, Changjie Fan, Runze Wu, Haobo Wang
https://arxiv.org/abs/2509.14030

CrowdAgent: Multi-Agent Managed Multi-Source Annotation System
High-quality annotated data is a cornerstone of modern Natural Language Processing (NLP). While recent methods begin to leverage diverse annotation sources-including Large Language Models (LLMs), Small Language Models (SLMs), and human experts-they often focus narrowly on the labeling step itself. A critical gap remains in the holistic process control required to manage these sources dynamically, addressing complex scheduling and quality-cost trade-offs in a unified manner. Inspired by real-wor…

Differentially private federated learning for localized control of infectious disease dynamics
Raouf Kerkouche, Henrik Zunker, Mario Fritz, Martin J. K\"uhn
https://arxiv.org/abs/2509.14024

Differentially private federated learning for localized control of infectious disease dynamics
In times of epidemics, swift reaction is necessary to mitigate epidemic spreading. For this reaction, localized approaches have several advantages, limiting necessary resources and reducing the impact of interventions on a larger scale. However, training a separate machine learning (ML) model on a local scale is often not feasible due to limited available data. Centralizing the data is also challenging because of its high sensitivity and privacy constraints. In this study, we consider a localiz…

Computational complexity of Berry phase estimation in topological phases of matter
Ryu Hayakawa, Kazuki Sakamoto, Chusei Kiumi
https://arxiv.org/abs/2509.13423 https://

Computational complexity of Berry phase estimation in topological phases of matter
The Berry phase is a fundamental quantity in the classification of topological phases of matter. In this paper, we present a new quantum algorithm and several complexity-theoretical results for the Berry phase estimation (BPE) problems. Our new quantum algorithm achieves BPE in a more general setting than previously known quantum algorithms, with a theoretical guarantee. For the complexity-theoretic results, we consider three cases. First, we prove $\mathsf{BQP}$-completeness when we are given …

Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision
Dulhan Jayalath, Shashwat Goel, Thomas Foster, Parag Jain, Suchin Gururangan, Cheng Zhang, Anirudh Goyal, Alan Schelten
https://arxiv.org/abs/2509.14234

Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision
Where do learning signals come from when there is no ground truth in post-training? We propose turning exploration into supervision through Compute as Teacher (CaT), which converts the model's own exploration at inference-time into reference-free supervision by synthesizing a single reference from a group of parallel rollouts and then optimizing toward it. Concretely, the current policy produces a group of rollouts; a frozen anchor (the initial policy) reconciles omissions and contradictions to…

Exploring Major Transitions in the Evolution of Biological Cognition With Artificial Neural Networks
Konstantinos Voudouris, Andrew Barron, Marta Halina, Colin Klein, Matishalin Patel
https://arxiv.org/abs/2509.13968

Exploring Major Transitions in the Evolution of Biological Cognition With Artificial Neural Networks
Transitional accounts of evolution emphasise a few changes that shape what is evolvable, with dramatic consequences for derived lineages. More recently it has been proposed that cognition might also have evolved via a series of major transitions that manipulate the structure of biological neural networks, fundamentally changing the flow of information. We used idealised models of information flow, artificial neural networks (ANNs), to evaluate whether changes in information flow in a network ca…

Localized degenerate solutions to the massless Dirac and Weyl equations
Georgios N. Tsigaridas, Aristides I. Kechriniotis, Christos A. Tsonos, Konstantinos K. Delibasis
https://arxiv.org/abs/2509.14212

Localized degenerate solutions to the massless Dirac and Weyl equations
In this article we present a general class of degenerate solutions to the massless Dirac and Weyl equations, which can describe localized particles and/or particles with variable energy, that could be interpreted as virtual particles appearing either in the vacuum or in materials supporting massless Dirac or Weyl particles. These solutions exist in a wide range of electromagnetic 4-potentials and fields, which are explicitly calculated. In addition, we describe a method for controlling the tran…

SteeringControl: Holistic Evaluation of Alignment Steering in LLMs
Vincent Siu, Nicholas Crispino, David Park, Nathan W. Henry, Zhun Wang, Yang Liu, Dawn Song, Chenguang Wang
https://arxiv.org/abs/2509.13450

SteeringControl: Holistic Evaluation of Alignment Steering in LLMs
We introduce SteeringControl, a benchmark for evaluating representation steering methods across core alignment objectives--bias, harmful generation, and hallucination--and their effects on secondary behaviors such as sycophancy and commonsense morality. While prior alignment work often highlights truthfulness or reasoning ability to demonstrate the side effects of representation steering, we find there are many unexplored tradeoffs not yet understood in a systematic way. We collect a dataset of…

A Variational Framework for Residual-Based Adaptivity in Neural PDE Solvers and Operator Learning
Juan Diego Toscano, Daniel T. Chen, Vivek Oommen, George Em Karniadakis
https://arxiv.org/abs/2509.14198

A Variational Framework for Residual-Based Adaptivity in Neural PDE Solvers and Operator Learning
Residual-based adaptive strategies are widely used in scientific machine learning but remain largely heuristic. We introduce a unifying variational framework that formalizes these methods by integrating convex transformations of the residual. Different transformations correspond to distinct objective functionals: exponential weights target the minimization of uniform error, while linear weights recover the minimization of quadratic error. Within this perspective, adaptive weighting is equivalen…

Quantum Reinforcement Learning-Guided Diffusion Model for Image Synthesis via Hybrid Quantum-Classical Generative Model Architectures
Chi-Sheng Chen, En-Jui Kuo
https://arxiv.org/abs/2509.14163

Quantum Reinforcement Learning-Guided Diffusion Model for Image Synthesis via Hybrid Quantum-Classical Generative Model Architectures
Diffusion models typically employ static or heuristic classifier-free guidance (CFG) schedules, which often fail to adapt across timesteps and noise conditions. In this work, we introduce a quantum reinforcement learning (QRL) controller that dynamically adjusts CFG at each denoising step. The controller adopts a hybrid quantum--classical actor--critic architecture: a shallow variational quantum circuit (VQC) with ring entanglement generates policy features, which are mapped by a compact multil…

Evaluating the Limits of QAOA Parameter Transfer at High-Rounds on Sparse Ising Models With Geometrically Local Cubic Terms
Elijah Pelofske, Marek Rams, Andreas B\"artschi, Piotr Czarnik, Paolo Braccia, Lukasz Cincio, Stephan Eidenbenz
https://arxiv.org/abs/2509.13528

Evaluating the Limits of QAOA Parameter Transfer at High-Rounds on Sparse Ising Models With Geometrically Local Cubic Terms
The emergent practical applicability of the Quantum Approximate Optimization Algorithm (QAOA) for approximate combinatorial optimization is a subject of considerable interest. One of the primary limitations of QAOA is the task of finding a set of good parameters. Parameter transfer is a phenomenon where QAOA angles trained on problem instances that are self-similar tend to perform well for other problem instances from that similar class. This suggests a potentially highly efficient and scalable…

Hybrid Quantum-Classical Neural Networks for Few-Shot Credit Risk Assessment
Zheng-an Wang, Yanbo J. Wang, Jiachi Zhang, Qi Xu, Yilun Zhao, Jintao Li, Yipeng Zhang, Bo Yang, Xinkai Gao, Xiaofeng Cao, Kai Xu, Pengpeng Hao, Xuan Yang, Heng Fan
https://arxiv.org/abs/2509.13818

Hybrid Quantum-Classical Neural Networks for Few-Shot Credit Risk Assessment
Quantum Machine Learning (QML) offers a new paradigm for addressing complex financial problems intractable for classical methods. This work specifically tackles the challenge of few-shot credit risk assessment, a critical issue in inclusive finance where data scarcity and imbalance limit the effectiveness of conventional models. To address this, we design and implement a novel hybrid quantum-classical workflow. The methodology first employs an ensemble of classical machine learning models (Logi…

Adaptive Client Selection via Q-Learning-based Whittle Index in Wireless Federated Learning
Qiyue Li, Yingxin Liu, Hang Qi, Jieping Luo, Zhizhang Liu, Jingjin Wu
https://arxiv.org/abs/2509.13933

Adaptive Client Selection via Q-Learning-based Whittle Index in Wireless Federated Learning
We consider the client selection problem in wireless Federated Learning (FL), with the objective of reducing the total required time to achieve a certain level of learning accuracy. Since the server cannot observe the clients' dynamic states that can change their computation and communication efficiency, we formulate client selection as a restless multi-armed bandit problem. We propose a scalable and efficient approach called the Whittle Index Learning in Federated Q-learning (WILF-Q), which us…

Data Denoising and Derivative Estimation for Data-Driven Modeling of Nonlinear Dynamical Systems
Jiaqi Yao, Lewis Mitchell, John Maclean, Hemanth Saratchandran
https://arxiv.org/abs/2509.14219

Data Denoising and Derivative Estimation for Data-Driven Modeling of Nonlinear Dynamical Systems
Data-driven modeling of nonlinear dynamical systems is often hampered by measurement noise. We propose a denoising framework, called Runge-Kutta and Total Variation Based Implicit Neural Representation (RKTV-INR), that represents the state trajectory with an implicit neural representation (INR) fitted directly to noisy observations. Runge-Kutta integration and total variation are imposed as constraints to ensure that the reconstructed state is a trajectory of a dynamical system that remains clo…

Exploring the Relationship between Brain Hemisphere States and Frequency Bands through Deep Learning Optimization Techniques
Robiul Islam, Dmitry I. Ignatov, Karl Kaberg, Roman Nabatchikov
https://arxiv.org/abs/2509.14078

Exploring the Relationship between Brain Hemisphere States and Frequency Bands through Deep Learning Optimization Techniques
This study investigates classifier performance across EEG frequency bands using various optimizers and evaluates efficient class prediction for the left and right hemispheres. Three neural network architectures - a deep dense network, a shallow three-layer network, and a convolutional neural network (CNN) - are implemented and compared using the TensorFlow and PyTorch frameworks. Results indicate that the Adagrad and RMSprop optimizers consistently perform well across different frequency bands,…

Graph-Regularized Learning of Gaussian Mixture Models
Shamsiiat Abdurakhmanova, Alex Jung
https://arxiv.org/abs/2509.13855 https://arxiv.org/pdf/2509.13855…

Graph-Regularized Learning of Gaussian Mixture Models
We present a graph-regularized learning of Gaussian Mixture Models (GMMs) in distributed settings with heterogeneous and limited local data. The method exploits a provided similarity graph to guide parameter sharing among nodes, avoiding the transfer of raw data. The resulting model allows for flexible aggregation of neighbors' parameters and outperforms both centralized and locally trained GMMs in heterogeneous, low-sample regimes.

ST-LINK: Spatially-Aware Large Language Models for Spatio-Temporal Forecasting
Hyotaek Jeon, Hyunwook Lee, Juwon Kim, Sungahn Ko
https://arxiv.org/abs/2509.13753 https://…

ST-LINK: Spatially-Aware Large Language Models for Spatio-Temporal Forecasting
Traffic forecasting represents a crucial problem within intelligent transportation systems. In recent research, Large Language Models (LLMs) have emerged as a promising method, but their intrinsic design, tailored primarily for sequential token processing, introduces notable challenges in effectively capturing spatial dependencies. Specifically, the inherent limitations of LLMs in modeling spatial relationships and their architectural incompatibility with graph-structured spatial data remain la…

Masked Diffusion Models as Energy Minimization
Sitong Chen, Shen Nie, Jiacheng Sun, Zijin Feng, Zhenguo Li, Ji-Rong Wen, Chongxuan Li
https://arxiv.org/abs/2509.13866 https://…

Masked Diffusion Models as Energy Minimization
We present a systematic theoretical framework that interprets masked diffusion models (MDMs) as solutions to energy minimization problems in discrete optimal transport. Specifically, we prove that three distinct energy formulations--kinetic, conditional kinetic, and geodesic energy--are mathematically equivalent under the structure of MDMs, and that MDMs minimize all three when the mask schedule satisfies a closed-form optimality condition. This unification not only clarifies the theoretical fo…