Tootfinder

Week 8 winners and losers: Taylor and Cook deliver; CMC and Robinson fall flat https://www.espn.com/fantasy/football/story/_/page/FFSundayHighLows-46735684/nfl-week-8-fantasy-football-winners-losers-inju…

📰 Informiert zu sein, schützt uns vor Gefahren und finanziellen Risiken. Ich suche täglich nach wissenswerten #Nachrichten aus #Forschung, #Medizin,

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

webkb: WebKB graphs (1998)
Web graphs crawled from four Computer Science departments in 1998, with each page manually classified into one of 7 categories: course, department, faculty, project, staff, student, or other. All graphs included in a single .zip; also included are 'co-citation' graphs, which links i and j if they both point to some k. Edge weights count the number of links from i to j.
This network has 286 nodes and 1002 edges.
Tags: Informational, Web gra…

by accident i stumbled on this review by the #NSA on Bruce Schneiers "Applied Crypto" book from long ago.

Photo-induced carrier dynamics in InSb probed with broadband THz spectroscopy based on BNA crystals
Elodie Iglesis, Alexandr Alekhin, Maximilien Cazayous, Alain Sacuto, Yann Gallais, Sarah Houver
https://arxiv.org/abs/2511.20896

My FreeBSD KDE Wayland page (#freebsd

This is a strange warning published in a Chinese state outlet. It basically warns that all forms of online shopping are subject to foreign espionage, and vendors should engage in data minimization.
https://www.globaltimes.cn/page/202510/1346444.shtml

China’s state security ministry warns against personal data theft by foreign espionage in online shopping - Global Times
The Ministry of State Security (MSS) said on Friday that some online-shopping processes could be exploited by foreign intelligence agencies to steal sensitive information.

Técnicamente fue Candida Doyle, quien es miembro de Pulp. Pero si hablamos de voz principal, Miley Cyrus.
👉🏻 https://maloja.altgr.xyz/charts_artists?in=2025&page=0&perpage=10
Re:

Da har hen kjŸpt seg "Carl Olsen Tangen - syndikalisten og rebellen: en historie om kamp mot undertrykkelse og for frigjŸring"
❤️🖤
Du kan finne den her:
https://www.nb.no/items/a8341f11dc88b201401a43810f7b106c?page=0

[Türchenöffnungsgeräusch]
74 Listings, hunderte in monatelanger Vorarbeit handgemalte Stücke: Der #klexadventskalender 2025 öffnete sich eben
https://www.wandklex.art/page/klexadventskalender-2025-63444 zum letzten Mal. Heute mit der alljährlichen Ausnahme von der Regel.☺
Danke fürs Dabeisein, ich wünsch Euch gute Festtage!

High-Resolution Optical Correlation-Domain Reflectometry with 100-km Measurement Range
Takaki Kiyozumi, Soshi Yoshida, Yuta Higa, Keisuke Motoda, Sze Yun Set, Shinji Yamashita, Yosuke Mizuno
https://arxiv.org/abs/2511.18400 https://arxiv.org/pdf/2511.18400 https://arxiv.org/html/2511.18400
arXiv:2511.18400v1 Announce Type: new
Abstract: In the maintenance of optical fiber networks, there is a growing demand for high-precision measurement of optical loss distribution and fault locations over long distances. In this study, we propose an OCDR method incorporating periodic pseudo-random modulation (PPRM), and demonstrate that it enables the acquisition of loss distribution based on Rayleigh scattering and the positions of reflection points in an approximately 100-km optical fiber, with a spatial resolution of about 19 cm and a measurement time of about 20 seconds.
toXiv_bot_toot

"Quite frankly I was pissed off!" Growing online page chronicles Trump Justice Dept. resignation letters (Scott MacFarlane/CBS News)
https://www.cbsnews.com/news/trump-justice-dept-resignation-letters-chronicled/
http://www.memeorandum.com/251123/p76#a251123p76

Many lawyers and career officials at the White House National Security Council, Pentagon and Justice Department ...
who had raised concerns about using lethal force against "narcotraffickers" ...
either left government or were reassigned or removed.
https://skywriter.b…

Squirrels at War: First Strike
#writingcommunity #visualinspiration Earlier installments can be read from this page. *** Normally with a new ship we would go on a shakedown cruise for several weeks to test systems and fix bugs. We didn’t have the time. We had to hope t…

wiki_talk: Wikipedia talk networks
Interactions among users of 10 language-specific Wikipedias: Arabic, Chinese, Dutch, English, French, German, Italian, Portuguese, Russian, and Spanish. Nodes are registered wiki editors, and an edge represents a user i having written a message on user j's talk page. Edges are timestamped. The precise dates of the snapshots are uncertain.
This network has 338714 nodes and 607087 edges.
Tags: Social, Communication, Unweighted, Multigrap…

The Guardian is a mixed bag, but I do appreciate the US edition — among other things for its willingness to write headlines without cowardice.
This is currently the top story on their home page.
https://www.theguardian.com/us-news/2025/dec/20/epstein-files-release-strategy-trump

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

Does anyone else have a weird thing happen when using Chrome (I have to for work) where if you're not scrolled just far down enough on a page, it doesn't let you click on things? Until you've scrolled down? It's a new type of bullshit for me

So I built this web page for privacy-enhanced sharing of YouTube videos. You can try it too. In the footer, click "Convert url" and you can paste the url of any YouTube video. It will convert to my url and you can copy the link or visit the page right away.

https://yt.axbom.com/?id=8enXRDlWguU

[2025-11-25 Tue (UTC), 1 new article found for nlin.CD Chaotic Dynamics]
toXiv_bot_toot

RE: https://hachyderm.io/@fantinel/115573316684309556
Looks like it’s working 👀
(Posting this from iPhanpy)

I love that Amazon made a Rome Edition Echo Dot earlier this year for some reason https://www.amazon.it/dp/B0F3LYNQK4

📰 Täglich findest Du hier kostenlose News zu vielen Zukunftsthemen. 😀 Leider muss ich die Hosting-Rechnungen seit Jahren allein zahlen. Ich will die Amazon-Partnerlinks loswerden, aber das geht nur mit Eurer finanziellen Hilfe und reicht leider noch nicht. 😭
Bitte unterstütze meine Arbeit mit einer Steady-Mitgliedschaft: https://steady.page/klimac…

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

See https://archive.org/details/byte-magazine-1975-12/page/n42/mode/2up for the full ad

> Keep in mind that certain details differ between GitHub and Forgejo.
(page does not say a single word about what actually differs)

Old enough to remember 2013-02-07 when any web page that included a Facebook-supplied javascript resource (to enable the, once ubiquitous, Facebook Connect) redirected users to Facebook.
(It's the event that most informed my suspicion in using third-party javascript - without SRI.)
It's 2025: Facebook is retiring external like buttons, but Cloudflare is breaking captchas.

Who is a Better Matchmaker? Human vs. Algorithmic Judge Assignment in a High-Stakes Startup Competition
Sarina Xi, Orelia Pi, Miaomiao Zhang, Becca Xiong, Jacqueline Ng Lane, Nihar B. Shah
https://arxiv.org/abs/2510.12692

Who is a Better Matchmaker? Human vs. Algorithmic Judge Assignment in a High-Stakes Startup Competition
There is growing interest in applying artificial intelligence (AI) to automate and support complex decision-making tasks. However, it remains unclear how algorithms compare to human judgment in contexts requiring semantic understanding and domain expertise. We examine this in the context of the judge assignment problem, matching submissions to suitably qualified judges. Specifically, we tackled this problem at the Harvard President's Innovation Challenge, the university's premier venture compet…

President Trump files a 40-page amended $15B defamation complaint against the NYT and others, after a judge initially dismissed it on Sept. 19 due to its length (The Guardian)
https://www.theguardian.com/us-news/2025/oct/16/trump-new-york-times-defam…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[6/14]:
- AB-UPT: Scaling Neural CFD Surrogates for High-Fidelity Automotive Aerodynamics Simulations via A...
Alkin, Bleeker, Kurle, Kronlachner, Sonnleitner, Dorfer, Brandstetter

Hyperspectral data augmentation with transformer-based diffusion models
Mattia Ferrari, Lorenzo Bruzzone
https://arxiv.org/abs/2510.08363 https://arxiv.org…

Hyperspectral data augmentation with transformer-based diffusion models
The introduction of new generation hyperspectral satellite sensors, combined with advancements in deep learning methodologies, has significantly enhanced the ability to discriminate detailed land-cover classes at medium-large scales. However, a significant challenge in deep learning methods is the risk of overfitting when training networks with small labeled datasets. In this work, we propose a data augmentation technique that leverages a guided diffusion model. To effectively train the model w…

Proceedings of the International Workshop on Verification of Scientific Software
Stephen F. Siegel, Ganesh Gopalakrishnan
https://arxiv.org/abs/2510.12314 https://

Proceedings of the International Workshop on Verification of Scientific Software
This volume contains the proceedings of the Verification of Scientific Software (VSS 2025) workshop, held on 4 May 2025 at McMaster University, Canada, as part of ETAPS 2025. VSS brings together researchers in software verification and scientific computing to address challenges in ensuring the correctness and reliability of large-scale scientific codes. The program featured five peer-reviewed papers, three invited contributions, and a set of challenge problems, covering themes such as deductive…

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[4/5]:
- Exploring the Frontier of Vision-Language Models: A Survey of Current Methodologies and Future Di...
Akash Ghosh, Arkadeep Acharya, Sriparna Saha, Vinija Jain, Aman Chadha

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[8/8]:
- Online Rubrics Elicitation from Pairwise Comparisons
Rezaei, Vacareanu, Wang, Wang, Liu, He, Aky\"urek

Lightweight CNN-Based Wi-Fi Intrusion Detection Using 2D Traffic Representations
Rayed Suhail Ahmad, Rehan Ahmad, Quamar Niyaz
https://arxiv.org/abs/2510.11898 https://

Lightweight CNN-Based Wi-Fi Intrusion Detection Using 2D Traffic Representations
Wi-Fi networks are ubiquitous in both home and enterprise environments, serving as a primary medium for Internet access and forming the backbone of modern IoT ecosystems. However, their inherent vulnerabilities, combined with widespread adoption, create opportunities for malicious actors to gain unauthorized access or compromise sensitive data stored on connected devices. To address these challenges, we propose a deep learning based network intrusion detection system (NIDS) for Wi-Fi environmen…

Replaced article(s) found for cs.SE. https://arxiv.org/list/cs.SE/new
[2/2]:
- Leveraging Large Language Models for Cybersecurity Risk Assessment -- A Case from Forestry Cyber-...
Fikret Mert Gultekin, Oscar Lilja, Ranim Khojah, Rebekka Wohlrab, Marvin Damschen, Mazen Mohamad

Dimension-Free Minimax Rates for Learning Pairwise Interactions in Attention-Style Models
Shai Zucker, Xiong Wang, Fei Lu, Inbar Seroussi
https://arxiv.org/abs/2510.11789 https:…

Dimension-Free Minimax Rates for Learning Pairwise Interactions in Attention-Style Models
We study the convergence rate of learning pairwise interactions in single-layer attention-style models, where tokens interact through a weight matrix and a non-linear activation function. We prove that the minimax rate is $M^{-\frac{2β}{2β+1}}$ with $M$ being the sample size, depending only on the smoothness $β$ of the activation, and crucially independent of token count, ambient dimension, or rank of the weight matrix. These results highlight a fundamental dimension-free statistical efficie…

'Quite the thing to admit': Experts call Trump's new move 'page 1 of the fascist playbook' - Alternet.org
https://www.alternet.org/trump-antifa-kristi-noem/

Chrome now has a bug where if a web page pops up "log in with Google" it happens in the browser UI, not in the web page UI. And it freezes things up enough so Ctrl-W no longer works to close the tab while the "log in" dialog is displayed.
Good jerb! I suspect this is related to some monopolistic practice of Google favoring their proprietary, privacy-invading login system in their browser.

I had to (wanted to, really… more later) put together a web page with a bunch of evaluation data (not for work).
Chart.js is pretty nice for this.
https://www.chartjs.org/

Chart.js
Simple yet flexible JavaScript charting library for the modern web

Replaced article(s) found for math.GN. https://arxiv.org/list/math.GN/new
[1/1]:
- Infinitely ludic categories
Matheus Duzi, Paul Szeptycki, Walter Tholen
https://arxiv.org/abs/2401.03484 https://mastoxiv.page/@arXiv_mathGN_bot/111724153632157856
- Every group retraction can be realized as a topological retraction
Pedro J. Chocano
https://arxiv.org/abs/2511.03472 https://mastoxiv.page/@arXiv_mathAT_bot/115501820264863765
toXiv_bot_toot

On the enumeration of records of rooted trees and rooted forests
Adri\'an Lillo, Mercedes Rosas, Stefan Trandafir
https://arxiv.org/abs/2510.12536 https://

On the enumeration of records of rooted trees and rooted forests
A record of a rooted Cayley tree is a node whose label is the largest along the unique path to the root. In this work, we find elegant functional equations relating the generating functions for records of rooted Cayley trees and for records of forests of rooted trees with the Cayley tree function, and explore the consequences of our results.

Replaced article(s) found for math.LO. https://arxiv.org/list/math.LO/new
[1/1]:
- Measurable domatic partitions
Edward Hou
https://arxiv.…

On the Number of Small Points for Rational Maps
Jit Wu Yap
https://arxiv.org/abs/2510.12039 https://arxiv.org/pdf/2510.12039…

On the Number of Small Points for Rational Maps
Let $K$ be a number field and $f: \mathbb{P}^1 \to \mathbb{P}^1$ a rational map of degree $d \geq 2$ with at most $s$ places of bad reduction, where we include all archimedean places. We prove that there exists constants $c_1,c_2 > 0$, depending only on $d$ and not on $f$ or $K$, such that $$ \# \left\{ x \in \mathbb{P}^1(K) \mid \widehat{h}_f(x) \leq \frac{c_1}{s} h_{\operatorname{rat}_d}(\langle f \rangle) \right\} \leq c_2 s \log(s). $$ Here, $\operatorname{rat}_d$ is the moduli space of rat…

A q-analogue of Mirzakhani's recursion for Weil-Petersson volumes
Norman Do, Paul Norbury
https://arxiv.org/abs/2510.12431 https://arxiv.org/pdf/2510.1…

Okay, I'm done with the SMB2 theme for the time being. Got the chords annotated, tweaked a bit of the tab to make it easier.
#smb #bass #music

Structure of quantum measurements implementable with one round of classical communication
Arthur C. R. Dutra, Ties-A. Ohst, Hai-Chau Nguyen, Otfried G\"uhne
https://arxiv.org/abs/2510.09381

Structure of quantum measurements implementable with one round of classical communication
Measurements that can be implemented via local operations and classical communication (LOCC) constitute a class of operations that is available in future quantum networks in which parties share entangled resource states. We characterise the different classes of measurements implementable with LOCC, where communication is restricted to a single round with a fixed direction. In particular, using the framework of constrained separability problems, we provide a complete characterisation of the clas…

New LP dropping soon. It will be a set of orchestral mockups with decent sound.

Facebook removes Chicago-area page dedicated to ICE sightings after Justice Department intervenes (Lauryn Azu/Chicago Tribune)
https://www.chicagotribune.com/2025/10/14/facebook-removes-chicago-ice-watch-page/
http://www.memeorandum.com/251014/p147#a251014p147

The FBI director, Kash Patel, is
“in over his head”
and leading a “chronically under-performing” agency
paralyzed by fear and plummeting morale,
according to a scathing 115-page report compiled by a national alliance of retired and active-duty FBI special agents and analysts.
The leaked assessment, obtained by the New York Post and prepared for both congressional Senate and House judiciary committees, is based on confidential accounts from 24 FBI sources.
…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[5/14]:
- QUITO-X: A New Perspective on Context Compression from the Information Bottleneck Theory
Wang, Huang, Tian, Su, Yu, Liao, Fan, Guo, Cheng

SPICE: Simple and Practical Image Clarification and Enhancement
Alexander Belyaev, Pierre-Alain Fayolle, Michael Cohen
https://arxiv.org/abs/2510.08358 https://

SPICE: Simple and Practical Image Clarification and Enhancement
We introduce a simple and efficient method to enhance and clarify images. More specifically, we deal with low light image enhancement and clarification of hazy imagery (hazy/foggy images, images containing sand dust, and underwater images). Our method involves constructing an image filter to simulate low-light or hazy conditions and deriving approximate reverse filters to minimize distortions in the enhanced images. Experimental results show that our approach is highly competitive and often sur…

Replaced article(s) found for cs.CL. https://arxiv.org/list/cs.CL/new
[1/5]:
- MLRIP: Pre-training a military language representation model with informative factual knowledge a...
Hui Li, Xuekang Yang

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[7/8]:
- System Prompt Optimization with Meta-Learning
Yumin Choi, Jinheon Baek, Sung Ju Hwang

Right now, you can call your senator (yes, again) and urge them to replace Chuck Schumer.
https://www.theguardian.com/us-news/live/2025/nov/10/us-government-shutdown-record-donald-trump-syria-president-ahmed-al-sharaa-rudy-giuliani-pardon-politics-live-news-updates?page=with:block-691237948f08d3736687b5e9

edit_wikiquote: Wikiquote edits (2010)
A bipartite user-page network extracted from Wikiquotes. A user connects to a page if that user edited that page. Edits (edges) are timestamped. Edge weights represent counts of the number of edits.
This network has 6008 nodes and 54892 edges.
Tags: Informational, Web graph, Multigraph, Timestamps

Formally Verified Certification of Unsolvability of Temporal Planning Problems
David Wang, Mohammad Abdulaziz
https://arxiv.org/abs/2510.10189 https://arxi…

Formally Verified Certification of Unsolvability of Temporal Planning Problems
We present an approach to unsolvability certification of temporal planning. Our approach is based on encoding the planning problem into a network of timed automata, and then using an efficient model checker on the network followed by a certificate checker to certify the output of the model checker. Our approach prioritises trustworthiness of the certification: we formally verify our implementation of the encoding to timed automata using the theorem prover Isabelle/HOL and we use an existing cer…

Replaced article(s) found for cs.SE. https://arxiv.org/list/cs.SE/new
[1/2]:
- Can Large Language Models Serve as Data Analysts? A Multi-Agent Assisted Approach for Qualitative...
Rasheed, Waseem, Ahmad, Kemell, Xiaofeng, Duc, Abrahamsson

Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory
Einar Urdshals, Edmund Lau, Jesse Hoogland, Stan van Wingerden, Daniel Murfet
https://arxiv.org/abs/2510.12077

Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory
We study neural network compressibility by using singular learning theory to extend the minimum description length (MDL) principle to singular models like neural networks. Through extensive experiments on the Pythia suite with quantization, factorization, and other compression techniques, we find that complexity estimates based on the local learning coefficient (LLC) are closely, and in some cases, linearly correlated with compressibility. Our results provide a path toward rigorously evaluating…

📰 Hier findest Du täglich Informationen zu #Klima & #Wissenschaft auf Deutsch. Mit Deiner Unterstützung kann ich das weiterhin kostenlose tun. Ich möchte helfen, #Sprachbarrieren zu überb…

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

Data-Model Co-Evolution: Growing Test Sets to Refine LLM Behavior
Minjae Lee, Minsuk Kahng
https://arxiv.org/abs/2510.12728 https://arxiv.org/pdf/2510.1272…

Data-Model Co-Evolution: Growing Test Sets to Refine LLM Behavior
A long-standing challenge in machine learning has been the rigid separation between data work and model refinement, enforced by slow fine-tuning cycles. The rise of Large Language Models (LLMs) overcomes this historical barrier, allowing applications developers to instantly govern model behavior by editing prompt instructions. This shift enables a new paradigm: data-model co-evolution, where a living test set and a model's instructions evolve in tandem. We operationalize this paradigm in an int…

GPS Spoofing Attack Detection in Autonomous Vehicles Using Adaptive DBSCAN
Ahmad Mohammadi, Reza Ahmari, Vahid Hemmati, Frederick Owusu-Ambrose, Mahmoud Nabil Mahmoud, Parham Kebria, Abdollah Homaifar, Mehrdad Saif
https://arxiv.org/abs/2510.10766

GPS Spoofing Attack Detection in Autonomous Vehicles Using Adaptive DBSCAN
As autonomous vehicles become an essential component of modern transportation, they are increasingly vulnerable to threats such as GPS spoofing attacks. This study presents an adaptive detection approach utilizing a dynamically tuned Density Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, designed to adjust the detection threshold (ε) in real-time. The threshold is updated based on the recursive mean and standard deviation of displacement errors between GPS and in-vehic…

Replaced article(s) found for math.GN. https://arxiv.org/list/math.GN/new
[1/1]:
- An Adaptation of the Vietoris Topology for Ordered Compact Sets
Christopher Caruvana, Jared Holshouser
https://arxiv.org/abs/2507.17936 https://mastoxiv.page/@arXiv_mathGN_bot/114912817437529340
- No Nowhere Constant Continuous Function Maps All Non-Normal Numbers to Normal Numbers
Chokri Manai
https://arxiv.org/abs/2506.15422 https://mastoxiv.page/@arXiv_mathNT_bot/114709233846620023
toXiv_bot_toot

Never thought about this. Use the good ol' image maps to provide alt text for possibly more complicated images https://www.w3.org/WAI/tutorials/images/imagemap/
The `href` attribute for `<area>` may be omitted too

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

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

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[4/14]:
- An approach for systematic decomposition of complex llm tasks
Tianle Zhou, Jiakai Xu, Guanhong Liu, Jiaxiang Liu, Haonan Wang, Eugene Wu

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[6/8]:
- K-ASTRO: Structure-Aware Adaptation of LLMs for Code Vulnerability Detection
Yifan Zhang, Michael Sandborn, Stefan Larson, Yu Huang, Kevin Leach

[2025-10-14 Tue (UTC), 9 new articles found for cs.LO Logic in Computer Science]
toXiv_bot_toot

The EmpathiSEr: Development and Validation of Software Engineering Oriented Empathy Scales
Hashini Gunatilake, John Grundy, Rashina Hoda, Ingo Mueller
https://arxiv.org/abs/2510.12546

The EmpathiSEr: Development and Validation of Software Engineering Oriented Empathy Scales
Empathy plays a critical role in software engineering (SE), influencing collaboration, communication, and user-centred design. Although SE research has increasingly recognised empathy as a key human aspect, there remains no validated instrument specifically designed to measure it within the unique socio-technical contexts of SE. Existing generic empathy scales, while well-established in psychology and healthcare, often rely on language, scenarios, and assumptions that are not meaningful or inte…

Statistical Guarantees for High-Dimensional Stochastic Gradient Descent
Jiaqi Li, Zhipeng Lou, Johannes Schmidt-Hieber, Wei Biao Wu
https://arxiv.org/abs/2510.12013 https://

Statistical Guarantees for High-Dimensional Stochastic Gradient Descent
Stochastic Gradient Descent (SGD) and its Ruppert-Polyak averaged variant (ASGD) lie at the heart of modern large-scale learning, yet their theoretical properties in high-dimensional settings are rarely understood. In this paper, we provide rigorous statistical guarantees for constant learning-rate SGD and ASGD in high-dimensional regimes. Our key innovation is to transfer powerful tools from high-dimensional time series to online learning. Specifically, by viewing SGD as a nonlinear autoregres…

Social Simulation for Integrating Self-Care: Measuring the Effects of Contextual Environments in Augmented Reality for Mental Health Practice
Anna Fang, Jiayang Shi, Hriday Chhabria, Bosi Li, Haiyi Zhu
https://arxiv.org/abs/2510.12081

Social Simulation for Integrating Self-Care: Measuring the Effects of Contextual Environments in Augmented Reality for Mental Health Practice
Despite growing interest in virtual and augmented reality (VR/AR) for mental well-being, prior work using immersive interventions to teach mental health skills has largely focused on calming or abstract settings. As a result, little is known about how realistic social simulation may better support the transfer and application of skills to in-person environments. In this work, we present a 14-day user study with 43-participants comparing an augmented reality intervention simulating a realistic c…

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[5/5]:
- TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Robotics
Han, Chi, Zhou, Rong, An, Wang, Wang, Sheng, Zhang

FocusMed: A Large Language Model-based Framework for Enhancing Medical Question Summarization with Focus Identification
Chao Liu, Ling Luo, Tengxiao Lv, Huan Zhuang, Lejing Yu, Jian Wang, Hongfei Lin
https://arxiv.org/abs/2510.04671

FocusMed: A Large Language Model-based Framework for Enhancing Medical Question Summarization with Focus Identification
With the rapid development of online medical platforms, consumer health questions (CHQs) are inefficient in diagnosis due to redundant information and frequent non-professional terms. The medical question summary (MQS) task aims to transform CHQs into streamlined doctors' frequently asked questions (FAQs), but existing methods still face challenges such as poor identification of question focus and model hallucination. This paper explores the potential of large language models (LLMs) in the MQS …

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[3/14]:
- Adapting and Evaluating Multimodal Large Language Models for Adolescent Idiopathic Scoliosis Self...
Zhaolong Wu, Pu Luo, Nan Meng, Jason Pui Yin Cheung, Teng Zhang

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[5/8]:
- Spatiotemporal Forecasting as Planning: A Model-Based Reinforcement Learning Approach with Genera...
Wu, Gao, Shi, Li, Xu, Zhang, Zhu, Wang, Luo, Wang, Wu, Huang

edit_wikiquote: Wikiquote edits (2010)
A bipartite user-page network extracted from Wikiquotes. A user connects to a page if that user edited that page. Edits (edges) are timestamped. Edge weights represent counts of the number of edits.
This network has 3929 nodes and 20595 edges.
Tags: Informational, Web graph, Multigraph, Timestamps

iCodeReviewer: Improving Secure Code Review with Mixture of Prompts
Yun Peng, Kisub Kim, Linghan Meng, Kui Liu
https://arxiv.org/abs/2510.12186 https://arx…

iCodeReviewer: Improving Secure Code Review with Mixture of Prompts
Code review is an essential process to ensure the quality of software that identifies potential software issues at an early stage of software development. Among all software issues, security issues are the most important to identify, as they can easily lead to severe software crashes and service disruptions. Recent research efforts have been devoted to automated approaches to reduce the manual efforts required in the secure code review process. Despite the progress, current automated approaches…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[2/14]:
- TCP: a Benchmark for Temporal Constraint-Based Planning
Zifeng Ding, Sikuan Yan, Zhangdie Yuan, Xianglong Hu, Fangru Lin, Andreas Vlachos

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[4/5]:
- HIVTP: A Training-Free Method to Improve VLMs Efficiency via Hierarchical Visual Token Pruning Us...
Jingqi Xu, Jingxi Lu, Chenghao Li, Sreetama Sarkar, Peter A. Beerel

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[4/8]:
- Latent Variable Modeling in Multi-Agent Reinforcement Learning via Expectation-Maximization for U...
Mazyar Taghavi, Rahman Farnoosh

edit_wiktionary: Wiktionary edits (2010)
Three bipartite user-page networks extracted from Wiktionary, for French, German, and English. A user connects to a page if that user edited that page. Edits (edges) are timestamped. Edge weights represent counts of the number of edits.
This network has 22048 nodes and 175134 edges.
Tags: Informational, Web graph, Multigraph, Timestamps

Enhancing Neural Code Representation with Additional Context
Huy Nguyen, Christoph Treude, Patanamon Thongtanunam
https://arxiv.org/abs/2510.12082 https://…

Enhancing Neural Code Representation with Additional Context
Automated program comprehension underpins many software engineering tasks, from code summarisation to clone detection. Recent deep learning models achieve strong results but typically rely on source code alone, overlooking contextual information such as version history or structural relationships. This limits their ability to capture how code evolves and operates. We conduct an empirical study on how enriching code representations with such contextual signals affects neural model performance on…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[3/8]:
- EFRame: Deeper Reasoning via Exploration-Filter-Replay Reinforcement Learning Framework
Chen Wang, Lai Wei, Yanzhi Zhang, Chenyang Shao, Zedong Dan, Weiran Huang, Yuzhi Zhang, Yue Wang

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[3/5]:
- VisionTS : Cross-Modal Time Series Foundation Model with Continual Pre-trained Vision Backbones
Lefei Shen, Mouxiang Chen, Xu Liu, Han Fu, Xiaoxue Ren, Jianling Sun, Zhuo Li, Chenghao Liu

edit_wikiquote: Wikiquote edits (2010)
A bipartite user-page network extracted from Wikiquotes. A user connects to a page if that user edited that page. Edits (edges) are timestamped. Edge weights represent counts of the number of edits.
This network has 3369 nodes and 13926 edges.
Tags: Informational, Web graph, Multigraph, Timestamps

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

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

Lingxi: Repository-Level Issue Resolution Framework Enhanced by Procedural Knowledge Guided Scaling
Xu Yang, Jiayuan Zhou, Michael Pacheco, Wenhan Zhu, Pengfei He, Shaowei Wang, Kui Liu, Ruiqi Pan
https://arxiv.org/abs/2510.11838

Lingxi: Repository-Level Issue Resolution Framework Enhanced by Procedural Knowledge Guided Scaling
Driven by the advancements of Large Language Models (LLMs), LLM-powered agents are making significant improvements in software engineering tasks, yet struggle with complex, repository-level issue resolution. Existing agent-based methods have two key limitations. First, they lack of procedural knowledge (i.e., how an issue is fixed step-by-step and rationales behind it) to learn and leverage for issue resolution. Second, they rely on massive computational power to blindly explore the solution sp…

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[2/5]:
- Uncertainty-Aware Diffusion Guided Refinement of 3D Scenes
Bose, Dutta, Nag, Zhang, Li, Karydis, Chowdhury
…

Crosslisted article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[5/5]:
- Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distr...
Cao, Huang, Guo, Zhang, Nan, Mai, Wang, Cheng, Sun, Han, Zhao, Zhang, Guo, Zheng, Song, Li, Luo, Luo
…

edit_wikinews: Wikipedia news edits (2010)
Two bipartite user-page networks extracted from Wikipedia, about news events. A user connects to a page if that user edited that page. Edits (edges) are timestamped. Edge weights represent counts of the number of edits.
This network has 4946 nodes and 23441 edges.
Tags: Informational, Web graph, Multigraph, Timestamps

eye2vec: Learning Distributed Representations of Eye Movement for Program Comprehension Analysis
Haruhiko Yoshioka, Kazumasa Shimari, Hidetake Uwano, Kenichi Matsumoto
https://arxiv.org/abs/2510.11722 …

eye2vec: Learning Distributed Representations of Eye Movement for Program Comprehension Analysis
This paper presents eye2vec, an infrastructure for analyzing software developers' eye movements while reading source code. In common eye-tracking studies in program comprehension, researchers must preselect analysis targets such as control flow or syntactic elements, and then develop analysis methods to extract appropriate metrics from the fixation for source code. Here, researchers can define various levels of AOIs like words, lines, or code blocks, and the difference leads to different result…

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[1/5]:
- PRVR: Partially Relevant Video Retrieval
Xianke Chen, Daizong Liu, Xun Yang, Xirong Li, Jianfeng Dong, Meng Wang, Xun Wang

edit_wikinews: Wikipedia news edits (2010)
Two bipartite user-page networks extracted from Wikipedia, about news events. A user connects to a page if that user edited that page. Edits (edges) are timestamped. Edge weights represent counts of the number of edits.
This network has 4457 nodes and 13336 edges.
Tags: Informational, Web graph, Multigraph, Timestamps

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[7/7]:
- An Analytical and AI-discovered Stable, Accurate, and Generalizable Subgrid-scale Closure for Geo...
Karan Jakhar, Yifei Guan, Pedram Hassanzadeh

webkb: WebKB graphs (1998)
Web graphs crawled from four Computer Science departments in 1998, with each page manually classified into one of 7 categories: course, department, faculty, project, staff, student, or other. All graphs included in a single .zip; also included are 'co-citation' graphs, which links i and j if they both point to some k. Edge weights count the number of links from i to j.
This network has 334 nodes and 32988 edges.
Tags: Informational, Web gr…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[6/7]:
- Is Limited Participant Diversity Impeding EEG-based Machine Learning?
Philipp Bomatter, Henry Gouk

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[5/7]:
- Statistically Truthful Auctions via Acceptance Rule
Roy Maor Lotan, Inbal Talgam-Cohen, Yaniv Romano

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[4/7]:
- Replicable Reinforcement Learning with Linear Function Approximation
Eric Eaton, Marcel Hussing, Michael Kearns, Aaron Roth, Sikata Bela Sengupta, Jessica Sorrell

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[3/7]:
- Towards a Progress Bar for Reasoning: Progress Prediction in Large Reasoning Models
Hans Peter Lynsg{\o}e Raaschou-jensen, Constanza Fierro, Anders S{\o}gaard

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[2/7]:
- Federated Dynamic Modeling and Learning for Spatiotemporal Data Forecasting
Thien Pham, Angelo Furno, Fa\"icel Chamroukhi, Latifa Oukhellou

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[1/7]:
- Learning Dynamic Graph Embeddings with Neural Controlled Differential Equations
Tiexin Qin, Benjamin Walker, Terry Lyons, Hong Yan, Haoliang Li