Tootfinder

ELMES: An Automated Framework for Evaluating Large Language Models in Educational Scenarios
Shou'ang Wei, Xinyun Wang, Shuzhen Bi, Jian Chen, Ruijia Li, Bo Jiang, Xin Lin, Min Zhang, Yu Song, BingDong Li, Aimin Zhou, Hao Hao
https://arxiv.org/abs/2507.22947

ELMES: An Automated Framework for Evaluating Large Language Models in Educational Scenarios
The emergence of Large Language Models (LLMs) presents transformative opportunities for education, generating numerous novel application scenarios. However, significant challenges remain: evaluation metrics vary substantially across different educational scenarios, while many emerging scenarios lack appropriate assessment metrics. Current benchmarks predominantly measure general intelligence rather than pedagogical capabilities. To address this gap, we introduce ELMES, an open-source automated …

A modular framework for collaborative human-AI, multi-modal and multi-beamline synchrotron experiments
Adam A. Corrao, Phillip M. Maffettone, Bruce Ravel, Thomas A. Caswell, Howie Joress, Stuart I. Wilkins, Daniel Olds
https://arxiv.org/abs/2509.22959

A modular framework for collaborative human-AI, multi-modal and multi-beamline synchrotron experiments
High-throughput materials discovery and studies of complex functional materials increasingly rely on multi-modal characterization performed at synchrotron light sources. However, measurements are typically done with no use of data until after an experiment, neglecting opportunities for data-driven insights to guide measurements. We developed a modular, open-source framework that incorporates artificial intelligence within the Bluesky control and data streaming infrastructure at NSLS-II, enablin…

Sources: Meta is considering using Google's Gemini and open-source Gemma AI models to improve its ad summarization and recommendation system (Erin Woo/The Information)
https://www.theinformation.com/articles/meta-talks-google-use-gemini-improve-a…

Meta in Talks With Google to Use Gemini to Improve Ad Targeting
Meta Platforms staffers have had discussions with Google Cloud about the possibility of using Google’s artificial intelligence models to improve Meta’s ad business, according to people with knowledge of the conversations. The discussions are the latest sign of how Meta’s stumbles with its own AI ...

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[6/6]:
- Patterns in the Transition From Founder-Leadership to Community Governance of Open Source
Mobina Noori, Mahasweta Chakraborti, Amy X Zhang, Seth Frey

Free artificial intelligence technology released by Chinese tech companies appears to be more powerful and popular than that developed by American rivals
https://www.washingtonpost.com/technology/2025/10/13/china-us-open-source-ai/

Analysis | China leads the U.S. on this measure of technological influence
China’s open AI models are now more powerful and popular than those released by American rivals, a shift with implications for the future of technology.

Security Vulnerabilities in Software Supply Chain for Autonomous Vehicles
Md Wasiul Haque, Md Erfan, Sagar Dasgupta, Md Rayhanur Rahman, Mizanur Rahman
https://arxiv.org/abs/2509.16899

Security Vulnerabilities in Software Supply Chain for Autonomous Vehicles
The interest in autonomous vehicles (AVs) for critical missions, including transportation, rescue, surveillance, reconnaissance, and mapping, is growing rapidly due to their significant safety and mobility benefits. AVs consist of complex software systems that leverage artificial intelligence (AI), sensor fusion algorithms, and real-time data processing. Additionally, AVs are becoming increasingly reliant on open-source software supply chains, such as open-source packages, third-party software …

AUDDT: Audio Unified Deepfake Detection Benchmark Toolkit
Yi Zhu, Heitor R. Guimar\~aes, Arthur Pimentel, Tiago Falk
https://arxiv.org/abs/2509.21597 https://

AUDDT: Audio Unified Deepfake Detection Benchmark Toolkit
With the prevalence of artificial intelligence (AI)-generated content, such as audio deepfakes, a large body of recent work has focused on developing deepfake detection techniques. However, most models are evaluated on a narrow set of datasets, leaving their generalization to real-world conditions uncertain. In this paper, we systematically review 28 existing audio deepfake datasets and present an open-source benchmarking toolkit called AUDDT (https://github.com/MuSAELab/AUDDT). The goal of thi…

A Cartography of Open Collaboration in Open Source AI: Mapping Practices, Motivations, and Governance in 14 Open Large Language Model Projects
Johan Lin{\aa}ker, Cailean Osborne, Jennifer Ding, Ben Burtenshaw
https://arxiv.org/abs/2509.25397

A Cartography of Open Collaboration in Open Source AI: Mapping Practices, Motivations, and Governance in 14 Open Large Language Model Projects
The proliferation of open large language models (LLMs) is fostering a vibrant ecosystem of research and innovation in artificial intelligence (AI). However, the methods of collaboration used to develop open LLMs both before and after their public release have not yet been comprehensively studied, limiting our understanding of how open LLM projects are initiated, organized, and governed as well as what opportunities there are to foster this ecosystem even further. We address this gap through an …

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[6/6]:
- Patterns in the Transition From Founder-Leadership to Community Governance of Open Source
Mobina Noori, Mahasweta Chakraborti, Amy X Zhang, Seth Frey

The Amphora of Great Intelligence
https://www.peppercarrot.com/en/miniFantasyTheater/018.html

18. The Amphora of Great Intelligence (AGI) - Pepper&Carrot
Official homepage of Pepper&Carrot, a free(libre) and open-source webcomic about Pepper, a young witch and her cat, Carrot. They live in a fantasy universe of potions, magic, and creatures.

OSINT or BULLSHINT? Exploring Open-Source Intelligence tweets about the Russo-Ukrainian War
Johannes Niu, Mila Stillman, Anna Kruspe
https://arxiv.org/abs/2508.03599 https://

OSINT or BULLSHINT? Exploring Open-Source Intelligence tweets about the Russo-Ukrainian War
This paper examines the role of Open Source Intelligence (OSINT) on Twitter regarding the Russo-Ukrainian war, distinguishing between genuine OSINT and deceptive misinformation efforts, termed "BULLSHINT." Utilizing a dataset spanning from January 2022 to July 2023, we analyze nearly 2 million tweets from approximately 1,040 users involved in discussing real-time military engagements, strategic analyses, and misinformation related to the conflict. Using sentiment analysis, partisanship detectio…

Forecasting Russian Equipment Losses Using Time Series and Deep Learning Models
Jonathan Teagan
https://arxiv.org/abs/2509.07813 https://arxiv.org/pdf/2509…

Forecasting Russian Equipment Losses Using Time Series and Deep Learning Models
This study applies a range of forecasting techniques,including ARIMA, Prophet, Long Short Term Memory networks (LSTM), Temporal Convolutional Networks (TCN), and XGBoost, to model and predict Russian equipment losses during the ongoing war in Ukraine. Drawing on daily and monthly open-source intelligence (OSINT) data from WarSpotting, we aim to assess trends in attrition, evaluate model performance, and estimate future loss patterns through the end of 2025. Our findings show that deep learning …

Reflection AI, which is developing an open-source AI model to compete with DeepSeek, raised $2B led by Nvidia, valuing it at $8B, up from $545M in March (Michael J. de la Merced/New York Times)
https://www.nytimes.com/2025/10/09/business/dealbook/ref…

Reflection AI Raises $2 Billion as It Aims to Compete With DeepSeek
The big fund-raising round was the latest sign of investor fervor for artificial intelligence companies despite concerns that the boom is overheated.

All You Need Is A Fuzzing Brain: An LLM-Powered System for Automated Vulnerability Detection and Patching
Ze Sheng, Qingxiao Xu, Jianwei Huang, Matthew Woodcock, Heqing Huang, Alastair F. Donaldson, Guofei Gu, Jeff Huang
https://arxiv.org/abs/2509.07225

All You Need Is A Fuzzing Brain: An LLM-Powered System for Automated Vulnerability Detection and Patching
Our team, All You Need Is A Fuzzing Brain, was one of seven finalists in DARPA's Artificial Intelligence Cyber Challenge (AIxCC), placing fourth in the final round. During the competition, we developed a Cyber Reasoning System (CRS) that autonomously discovered 28 security vulnerabilities - including six previously unknown zero-days - in real-world open-source C and Java projects, and successfully patched 14 of them. The complete CRS is open source at https://github.com/o2lab/afc-crs-all-you-ne…

The Economics and Game Theory of OSINT Frontline Photography: Risk, Attention, and the Collective Dilemma
Jonathan Teagan
https://arxiv.org/abs/2509.10548 https://

The Economics and Game Theory of OSINT Frontline Photography: Risk, Attention, and the Collective Dilemma
This paper develops an economic model of the Open Source Intelligence (OSINT) attention economy in contemporary armed conflict. We conceptualize attention (e.g. social media views, followers, likes) as revenue, and time and risk spent in analysis as costs. Using utility functions and simple game theoretic setups, we show how OSINT actors (amateurs, journalists, analysts, and state operatives) allocate effort to maximize net attention benefit. We incorporate strategic behaviors such as a first m…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[4/5]:
- Evaluating the Robustness of Open-Source Vision-Language Models to Domain Shift in Object Captioning
Federico Tavella, Amber Drinkwater, Angelo Cangelosi

Paris-based Filigran, which develops open-source threat intelligence tools, raised a $58M Series C led by French VC Eurazeo and reports 6K users (Daphné Leprince-Ringuet/Sifted)
https://sifted.eu/articles/cybersecurity-startup-filigran-raises-58m/

A Living Review Pipeline for AI/ML Applications in Accelerator Physics
Adnan Ghribi
https://arxiv.org/abs/2510.09376 https://arxiv.org/pdf/2510.09376

A Living Review Pipeline for AI/ML Applications in Accelerator Physics
We present an open-source pipeline for generating a \emph{living review} of artificial intelligence (AI) and machine learning (ML) applications in accelerator physics and technologies. Traditional review articles provide static snapshots that are quickly outdated by the rapid pace of research. The presented system automatically harvests publications from multiple bibliographic sources (arXiv, InspireHEP, HAL, OpenAlex, Crossref, and Springer), deduplicates entries, applies semantic filtering to…

You Have Been LaTeXpOsEd: A Systematic Analysis of Information Leakage in Preprint Archives Using Large Language Models
Richard A. Dubniczky, Bertalan Borsos, Tihanyi Norbert
https://arxiv.org/abs/2510.03761

You Have Been LaTeXpOsEd: A Systematic Analysis of Information Leakage in Preprint Archives Using Large Language Models
The widespread use of preprint repositories such as arXiv has accelerated the communication of scientific results but also introduced overlooked security risks. Beyond PDFs, these platforms provide unrestricted access to original source materials, including LaTeX sources, auxiliary code, figures, and embedded comments. In the absence of sanitization, submissions may disclose sensitive information that adversaries can harvest using open-source intelligence. In this work, we present the first lar…