Tootfinder

https://forward.com/news/686797/heritage-foundation-wikipedia-antisemitism/

Scoop: Heritage Foundation plans to ‘identify and target’ Wikipedia editors
The conservative think tank told prospective donors that the project was part of its work to combat antisemitism.

Zum Abend noch einige der heute besonders häufig geteilten #News:
Freie Alternative zu Google und Apple: Free Software Foundation plant LibrePhone

»Freie Alternative zu Google und Apple — Free Software Foundation plant LibrePhone:
Die Free Software Foundation (@…) will mit dem LibrePhone Projekt eine freie Alternative zu Android und iOS entwickeln. Es wäre nicht der erste Anlauf der FSF.«
Da bin ich mal gespannt was sich da ergibt und wie es von den Mobile-Herstellern eingesetzt oder verweigert wird.

Freie Alternative zu Google und Apple: Free Software Foundation plant LibrePhone
Die Free Software Foundation (FSF) will mit dem LibrePhone Projekt eine freie Alternative zu Android und iOS entwickeln. Es wäre nicht der erste Anlauf der FSF.

"Freie Alternative zu #Google und #Apple: Free Software Foundation plant #LibrePhone"

"'Aid' stations that killed thousands simply disappear overnight"
Gaza Humanitarian Foundation vanishes into thin air
https://www.thecanary.co/skwawkbox/2025/10/12/israel-us-so-called-gaza-humanitarian-foundation-vanishes-into-thin-air/

Foundation Health, which develops an AI assistant to automate patient communication and prior authorization workflows for pharmacies, raised a $20M Series A (Heather Landi/Fierce Healthcare)
https://www.fiercehealthcare.com/health-te

DeepFleet: Multi-Agent Foundation Models for Mobile Robots
Ameya Agaskar, Sriram Siva, William Pickering, Kyle O'Brien, Charles Kekeh, Ang Li, Brianna Gallo Sarker, Alicia Chua, Mayur Nemade, Charun Thattai, Jiaming Di, Isaac Iyengar, Ramya Dharoor, Dino Kirouani, Jimmy Erskine, Tamir Hegazy, Scott Niekum, Usman A. Khan, Federico Pecora, Joseph W. Durham
ht…

DeepFleet: Multi-Agent Foundation Models for Mobile Robots
We introduce DeepFleet, a suite of foundation models designed to support coordination and planning for large-scale mobile robot fleets. These models are trained on fleet movement data, including robot positions, goals, and interactions, from hundreds of thousands of robots in Amazon warehouses worldwide. DeepFleet consists of four architectures that each embody a distinct inductive bias and collectively explore key points in the design space for multi-agent foundation models: the robot-centric …

PeftCD: Leveraging Vision Foundation Models with Parameter-Efficient Fine-Tuning for Remote Sensing Change Detection
Sijun Dong, Yuxuan Hu, LiBo Wang, Geng Chen, Xiaoliang Meng
https://arxiv.org/abs/2509.09572

PeftCD: Leveraging Vision Foundation Models with Parameter-Efficient Fine-Tuning for Remote Sensing Change Detection
To tackle the prevalence of pseudo changes, the scarcity of labeled samples, and the difficulty of cross-domain generalization in multi-temporal and multi-source remote sensing imagery, we propose PeftCD, a change detection framework built upon Vision Foundation Models (VFMs) with Parameter-Efficient Fine-Tuning (PEFT). At its core, PeftCD employs a weight-sharing Siamese encoder derived from a VFM, into which LoRA and Adapter modules are seamlessly integrated. This design enables highly effici…

Two Sides of the Same Optimization Coin: Model Degradation and Representation Collapse in Graph Foundation Models
Xunkai Li, Daohan Su, Sicheng Liu, Ru Zhang, Rong-Hua Li, Guoren Wang
https://arxiv.org/abs/2509.08401

Two Sides of the Same Optimization Coin: Model Degradation and Representation Collapse in Graph Foundation Models
Graph foundation models, inspired by the success of LLMs, are designed to learn the optimal embedding from multi-domain TAGs for the downstream cross-task generalization capability. During our investigation, graph VQ-MAE stands out among the increasingly diverse landscape of GFM architectures. This is attributed to its ability to jointly encode topology and textual attributes from multiple domains into discrete embedding spaces with clear semantic boundaries. Despite its potential, domain gener…

Foundation Models for Astrobiology: Paper I -- Workshop and Overview
Ryan Felton, Caleb Scharf, Stuart Bartlett, Nathalie A. Cabrol, Victoria Da Poian, Diana Gentry, Jian Gong, Adrienne Hoarfrost, Manil Maskey, Floyd Nichols, Conor A. Nixon, Tejas Panambur, Joseph Pasterski, Anton S. Petrov, Anirudh Prabhu, Brenda Thomson, Hamed Valizadegan, Kimberley Warren-Rhodes, David Wettergreen, Michael L. Wong, Anastasia Yanchilina

Foundation Models for Astrobiology: Paper I -- Workshop and Overview
Advances in machine learning over the past decade have resulted in a proliferation of algorithmic applications for encoding, characterizing, and acting on complex data that may contain many high dimensional features. Recently, the emergence of deep-learning models trained across very large datasets has created a new paradigm for machine learning in the form of Foundation Models. Foundation Models are programs trained on very large and broad datasets with an extensive number of parameters. Once …

Freie Alternative zu Google und Apple: Free Software Foundation plant LibrePhone
Die Free Software Foundation (FSF) will mit dem LibrePhone Projekt eine freie Alternative zu Android und iOS entwickeln. Es wäre nicht der erste Anlauf der FSF.

LECTURES> Prof. Vesna A. Wallace, "The Interrelationship Between the Texts, Images, and Rituals in Mongolian Buddhism" - MaMa Charitable Foundation Lecture Series in Buddhist Studies
https://ift.tt/QPiMwc8
Seeking Book Reviewers for Women and Social Movements in the United States Erica Hayden 1…

https://meta.wikimedia.org/wiki/Objections_to_the_2025_WMF_Board_election_removals

As a consequence of The Mothership changing its logo, ASF #SpamAssassin is also doing so, with a contest open to all.
We have not yet put together the details for this, but the last time we did this (before I even *used* SA) was 2004 and we did it like this then:

Foundation Models for Autonomous Driving Perception: A Survey Through Core Capabilities
Rajendramayavan Sathyam, Yueqi Li
https://arxiv.org/abs/2509.08302 https://

Foundation Models for Autonomous Driving Perception: A Survey Through Core Capabilities
Foundation models are revolutionizing autonomous driving perception, transitioning the field from narrow, task-specific deep learning models to versatile, general-purpose architectures trained on vast, diverse datasets. This survey examines how these models address critical challenges in autonomous perception, including limitations in generalization, scalability, and robustness to distributional shifts. The survey introduces a novel taxonomy structured around four essential capabilities for rob…

https://engineering.fb.com/2025/10/07/open-source/introducing-the-react-foundation-the-new-home-for-react-react-native/ 🧐

Introducing the React Foundation: The New Home for React & React Native
Meta open-sourced React over a decade ago to help developers build better user experiences. Since then, React has grown into one of the world’s most popular open source projects, powering over 50 m…

An Open Benchmark Dataset for GeoAI Foundation Models for Oil Palm Mapping in Indonesia
M. Warizmi Wafiq, Peter Cutter, Ate Poortinga, Daniel Marc G. dela Torre, Karis Tenneson, Vanna Teck, Enikoe Bihari, Chanarun Saisaward, Weraphong Suaruang, Andrea McMahon, Andi Vika Faradiba Muin, Karno B. Batiran, Chairil A, Nurul Qomar, Arya Arismaya Metananda, David Ganz, David Saah

An Open Benchmark Dataset for GeoAI Foundation Models for Oil Palm Mapping in Indonesia
Oil palm cultivation remains one of the leading causes of deforestation in Indonesia. To better track and address this challenge, detailed and reliable mapping is needed to support sustainability efforts and emerging regulatory frameworks. We present an open-access geospatial dataset of oil palm plantations and related land cover types in Indonesia, produced through expert labeling of high-resolution satellite imagery from 2020 to 2024. The dataset provides polygon-based, wall-to-wall annotatio…

Bringing Multi-Modal Multi-Task Federated Foundation Models to Education Domain: Prospects and Challenges
Kasra Borazjani, Naji Khosravan, Rajeev Sahay, Bita Akram, Seyyedali Hosseinalipour
https://arxiv.org/abs/2509.07946

Bringing Multi-Modal Multi-Task Federated Foundation Models to Education Domain: Prospects and Challenges
Multi-modal multi-task (M3T) foundation models (FMs) have recently shown transformative potential in artificial intelligence, with emerging applications in education. However, their deployment in real-world educational settings is hindered by privacy regulations, data silos, and limited domain-specific data availability. We introduce M3T Federated Foundation Models (FedFMs) for education: a paradigm that integrates federated learning (FL) with M3T FMs to enable collaborative, privacy-preserving…

Well this is very cool and very handy, especially as Google Trabslate keeps getting worse, somehow.
https://www.icelandreview.com/news/new-online-dictionary-aims-to-make-icelandic-more-accessible/

New Online Dictionary Aims to Make Icelandic More Accessible
A new online Icelandic–English dictionary has been launched by the Árni Magnússon Institute for Icelandic Studies. This handy, modern resource is perfect for aspiring language learners, translators, and anyone interested in the Icelandic language. Built on the foundation of the multilingual Scandinavian project ISLEX, the new site combines linguistic research with user-friendly digital tools. The […]

I wanted to help with carbon, the programming language, but having to sign a CLA is a major obstacle to me.
With my limited time I would rather not invest in this.
Granted, the intentions seem good. They plan to transfer all rights to a newly founded foundation once things are running. It's just not my cup of tea. I prefer the viral chaos of the linux situation; i.e.. GPLv2 never going away because too many contributors are difficult to find.

The Linux Foundation will launch the React Foundation, a new home for Meta's React and React Native; founding members include Amazon, Meta, Microsoft, others (Engineering at Meta)
https://engineering.fb.com/2025/10/07/

Introducing the React Foundation: The New Home for React & React Native
Meta open-sourced React over a decade ago to help developers build better user experiences. Since then, React has grown into one of the world’s most popular open source projects, powering over 50 m…

Multi-modal Foundation Model for Cosmological Simulation Data
Bin Xia, Nesar Ramachandra, Azton I. Wells, Salman Habib, John Wise
https://arxiv.org/abs/2510.07684 https://

Multi-modal Foundation Model for Cosmological Simulation Data
We present a multi-modal foundation model for astrophysical galaxy data, designed to map between simulation- and observation-based galactic features. Our encoder-only transformer flexibly ingests scalar quantities (e.g., redshifts, galaxy masses) and vectors (e.g., star formation histories, spectra), supporting multi-task training that includes within-modality reconstruction and cross-modality prediction. With a dynamic masking strategy, the model can query arbitrary galaxy properties from part…

LECTURES> Prof. Vesna A. Wallace, "The Interrelationship Between the Texts, Images, and Rituals in Mongolian Buddhism" - MaMa Charitable Foundation Lecture Series in Buddhist Studies
https://ift.tt/i9AavK4
Seeking Book Reviewers for Women and Social Movements in the United States Erica Hayden 1…

Efficient Autoregressive Inference for Transformer Probabilistic Models
Conor Hassan, Nasrulloh Loka, Cen-You Li, Daolang Huang, Paul E. Chang, Yang Yang, Francesco Silvestrin, Samuel Kaski, Luigi Acerbi
https://arxiv.org/abs/2510.09477

Efficient Autoregressive Inference for Transformer Probabilistic Models
Transformer-based models for amortized probabilistic inference, such as neural processes, prior-fitted networks, and tabular foundation models, excel at single-pass marginal prediction. However, many real-world applications, from signal interpolation to multi-column tabular predictions, require coherent joint distributions that capture dependencies between predictions. While purely autoregressive architectures efficiently generate such distributions, they sacrifice the flexible set-conditioning…

Representation Potentials of Foundation Models for Multimodal Alignment: A Survey
Jianglin Lu, Hailing Wang, Yi Xu, Yizhou Wang, Kuo Yang, Yun Fu
https://arxiv.org/abs/2510.05184

Representation Potentials of Foundation Models for Multimodal Alignment: A Survey
Foundation models learn highly transferable representations through large-scale pretraining on diverse data. An increasing body of research indicates that these representations exhibit a remarkable degree of similarity across architectures and modalities. In this survey, we investigate the representation potentials of foundation models, defined as the latent capacity of their learned representations to capture task-specific information within a single modality while also providing a transferabl…

MM-DINOv2: Adapting Foundation Models for Multi-Modal Medical Image Analysis
Daniel Scholz, Ayhan Can Erdur, Viktoria Ehm, Anke Meyer-Baese, Jan C. Peeken, Daniel Rueckert, Benedikt Wiestler
https://arxiv.org/abs/2509.06617

MM-DINOv2: Adapting Foundation Models for Multi-Modal Medical Image Analysis
Vision foundation models like DINOv2 demonstrate remarkable potential in medical imaging despite their origin in natural image domains. However, their design inherently works best for uni-modal image analysis, limiting their effectiveness for multi-modal imaging tasks that are common in many medical fields, such as neurology and oncology. While supervised models perform well in this setting, they fail to leverage unlabeled datasets and struggle with missing modalities, a frequent challenge in c…

What Makes the Raiders' Foundation Special to Build Upon https://www.si.com/nfl/raiders/las-vegas-pete-carroll-mark-davis-tom-brady-new-england-patriots

In a short blog post for the MacArthur Foundation, my colleague Veronica Thamaini and I discuss the Abstract Wikipedia proposal, one of five finalists for the ongoing 100&Change program.
A Path to a World Where Everyone Can Share in the Sum of All Knowledge
https://www.

A Path to a World Where Everyone Can Share in the Sum of All Knowledge

Co-Authoring the Self: A Human-AI Interface for Interest Reflection in Recommenders
Ruixuan Sun, Junyuan Wang, Sanjali Roy, Joseph A. Konstan
https://arxiv.org/abs/2510.08930 ht…

Co-Authoring the Self: A Human-AI Interface for Interest Reflection in Recommenders
Natural language-based user profiles in recommender systems have been explored for their interpretability and potential to help users scrutinize and refine their interests, thereby improving recommendation quality. Building on this foundation, we introduce a human-AI collaborative profile for a movie recommender system that presents editable personalized interest summaries of a user's movie history. Unlike static profiles, this design invites users to directly inspect, modify, and reflect on th…

#LinuxFoundation Announces the Formation of the #DeveloperRelations Foundation

Vision-Language Semantic Aggregation Leveraging Foundation Model for Generalizable Medical Image Segmentation
Wenjun Yu, Yinchen Zhou, Jia-Xuan Jiang, Shubin Zeng, Yuee Li, Zhong Wang
https://arxiv.org/abs/2509.08570

Vision-Language Semantic Aggregation Leveraging Foundation Model for Generalizable Medical Image Segmentation
Multimodal models have achieved remarkable success in natural image segmentation, yet they often underperform when applied to the medical domain. Through extensive study, we attribute this performance gap to the challenges of multimodal fusion, primarily the significant semantic gap between abstract textual prompts and fine-grained medical visual features, as well as the resulting feature dispersion. To address these issues, we revisit the problem from the perspective of semantic aggregation. S…

Join me at two events at the British Library later this month:
https://www.bl.uk/stories/blogs/posts/knowledge-is-human
On 20 October, the British Library is joining forces with Wikimedia UK and the Wikimedia Foundation to explore the impact of AI on ope…

Knowledge is Human: The Information Ecosystem in the age of AI
A summit to mark the role of human-created, open knowledge in the age of AI and our collective responsibility to safeguard knowledge integrity and sustainability.

Next week we’ll be in Geneva for the @… together with the European e-Infrastructures Assembly—EGI Foundation, EUDAT, @…, and PRACE.
Come by our joint booth (#2) at

Freedom of the Press Foundation and 404 Media file a FOIA lawsuit against the US DHS and CMS, seeking documents about Medicaid patient data sharing with ICE (Joseph Cox/404 Media)
https://www.404media.co/404-media-and-freedom-of-the-press-foundation-sue-dhs/

404 Media and Freedom of the Press Foundation Sue DHS
Both organizations are seeking a copy of a data sharing agreement that is giving the personal data of nearly 80 million Medicaid patients to ICE.

Calib3R: A 3D Foundation Model for Multi-Camera to Robot Calibration and 3D Metric-Scaled Scene Reconstruction
Davide Allegro, Matteo Terreran, Stefano Ghidoni
https://arxiv.org/abs/2509.08813

Calib3R: A 3D Foundation Model for Multi-Camera to Robot Calibration and 3D Metric-Scaled Scene Reconstruction
Robots often rely on RGB images for tasks like manipulation and navigation. However, reliable interaction typically requires a 3D scene representation that is metric-scaled and aligned with the robot reference frame. This depends on accurate camera-to-robot calibration and dense 3D reconstruction, tasks usually treated separately, despite both relying on geometric correspondences from RGB data. Traditional calibration needs patterns, while RGB-based reconstruction yields geometry with an unknow…

CORSIKA 8: A modern and universal framework for particle cascade simulations
Marvin Gottowik (for the CORSIKA 8 collaboration)
https://arxiv.org/abs/2508.08755 https://

CORSIKA 8: A modern and universal framework for particle cascade simulations
CORSIKA 8 represents a significant update in the simulation of particle showers, building on the well-established foundation of CORSIKA 7. It has been entirely rewritten as a modular and modern C++ framework, addressing the limitations of its predecessor to provide a flexible platform designed to satisfy current and novel use cases. This allows for application beyond pure air-shower scenarios such as cross-media particle cascades and an advanced calculation of the radio emission. A first offici…

EXCLUSIVE: 'I Made A Mistake': Heritage Foundation President Apologizes to Staff for Video Refusal to Cancel Tucker Carlson and Throws Shade at Former Chief of Staff (Eliana Johnson/The Washington Free Beacon)
https://freebeacon.com/politics/i-made-a-mistake-heritage-foundation-president-apologizes-to-staff-for-video-refusal-to-cancel-tucker-carlson-and-throws-shade-at-former-chief-of-staff/
http://www.memeorandum.com/251105/p126#a251105p126

StarEmbed: Benchmarking Time Series Foundation Models on Astronomical Observations of Variable Stars
Weijian Li, Hong-Yu Chen, Qinjie Lin, Nabeel Rehemtulla, Ved G. Shah, Dennis Wu, Adam A. Miller, Han Liu
https://arxiv.org/abs/2510.06200

StarEmbed: Benchmarking Time Series Foundation Models on Astronomical Observations of Variable Stars
Time series foundation models (TSFMs) are increasingly being adopted as highly-capable general-purpose time series representation learners. Although their training corpora are vast, they exclude astronomical time series data. Observations of stars produce peta-scale time series with unique challenges including irregular sampling and heteroskedasticity. We introduce StarEmbed, the first public benchmark for rigorous and standardized evaluation of state-of-the-art TSFMs on stellar time series obs…

What a headline…
Person a bit upset by hearing about a nasty thing.
https://www.bbc.co.uk/news/articles/c2ej877g7w1o

Prince William visibly moved as widow tells of husband's suicide
Prince William's foundation is giving £1m to set up a suicide prevention network.

Physically Valid Biomolecular Interaction Modeling with Gauss-Seidel Projection
Siyuan Chen, Minghao Guo, Caoliwen Wang, Anka He Chen, Yikun Zhang, Jingjing Chai, Yin Yang, Wojciech Matusik, Peter Yichen Chen
https://arxiv.org/abs/2510.08946

Physically Valid Biomolecular Interaction Modeling with Gauss-Seidel Projection
Biomolecular interaction modeling has been substantially advanced by foundation models, yet they often produce all-atom structures that violate basic steric feasibility. We address this limitation by enforcing physical validity as a strict constraint during both training and inference with a uniffed module. At its core is a differentiable projection that maps the provisional atom coordinates from the diffusion model to the nearest physically valid conffguration. This projection is achieved usin…

Synthetic Series-Symbol Data Generation for Time Series Foundation Models
Wenxuan Wang, Kai Wu, Yujian Betterest Li, Dan Wang, Xiaoyu Zhang
https://arxiv.org/abs/2510.08445 http…

Synthetic Series-Symbol Data Generation for Time Series Foundation Models
Foundation models for time series analysis (TSA) have attracted significant attention. However, challenges such as training data scarcity and imbalance continue to hinder their development. Inspired by complex dynamic system theories, we design a series-symbol data generation mechanism, enabling the unrestricted creation of high-quality time series data paired with corresponding symbolic expressions. To leverage series-symbol data pairs with strong correlations, we develop \texttt{SymTime}, a p…

Open-source security group pulls out of U.S. grant, citing DEI restrictions
https://cyberscoop.com/python-software-foundation-rejects-federal-grant-funding-citing-dei-restrictions/

Experimental observation of energy-band Riemann surface
Dali Cheng, Heming Wang, Janet Zhong, Eran Lustig, Charles Roques-Carmes, Shanhui Fan
https://arxiv.org/abs/2510.08819 ht…

Experimental observation of energy-band Riemann surface
Non-Hermiticity naturally arises in many physical systems that exchange energy with their environment. The presence of non-Hermiticity leads to many novel topological physics phenomena and device applications. In the non-Hermitian energy band theory, the foundation of these physics and applications, both energies and wavevectors can take complex values. The energy bands thus become a Riemann surface, and such an energy-band Riemann surface underlies all the important signatures of non-Hermitian…

Apache Foundation has changed its logo.
https://news.apache.org/foundation/entry/introducing-the-asfs-new-logo

Introducing The ASF’s New Logo  - The Apache Software Foundation Blog
Last year we shared that The Apache® Software Foundation (ASF) would be evolving its corporate logo and brand system to better represent our enduring ethos of community over code. Today, we are proud to unveil the new ASF logo.  Why an Oak Leaf? The centerpiece of our new logo is an oak leaf, chosen for […]

Spectral and Nilpotent Matrix Orderings: Comparison and Applications in Dynamic Systems
Shih-Yu Chang
https://arxiv.org/abs/2510.08579 https://arxiv.org/pd…

Spectral and Nilpotent Matrix Orderings: Comparison and Applications in Dynamic Systems
In our earlier work, we proposed the \emph{Spectral and Nilpotent Ordering} (SNO) as a new framework that extends matrix comparison beyond the Hermitian setting by incorporating both spectral and nilpotent structures. Building on that foundation, the present paper develops concrete certificates and applications of SNO. First, we employ generalized Gershgorin theorems to design certificates for spectral ordering that avoid direct eigenvalue computation and analyze their robustness under perturba…

At Electric Nashville, a one night synth show benefiting the Bob Moog Foundation https://www.electricnashville.org/

#SteadySupporter
Das #DKFZ entwickelt mit dem „Human Radiome Project“ ein KI-Foundation-Model, das Millionen radiologische #Bilddaten analysiert. Es soll als

DKFZ entwickelt KI-Foundation-Model für die Radiologie
Forscher des DKFZ arbeiten am Human Radiome Project und entwickeln ein KI-Foundation-Model, das radiologische Diagnosen verbessern soll.

Cross-device Zero-shot Label Transfer via Alignment of Time Series Foundation Model Embeddings
Neal G. Ravindra, Arijit Sehanobish
https://arxiv.org/abs/2509.06966 https://

Cross-device Zero-shot Label Transfer via Alignment of Time Series Foundation Model Embeddings
High-quality, medically validated labels exist for clinical actigraphy data but not for ubiquitous consumer wearables like the Apple Watch. Manually labeling wearables data is expensive and doesn't scale. This paper offers a novel framework that transfers valuable labels from a source domain (e.g., actigraphy) to a target domain (e.g., Apple Watch) without requiring paired data. Instead of working with raw time-series signals, we project both domains into a shared latent embedding space using t…

"...the conservative writer William F Buckley Jr’s boundaries for the conservative movement: expunge all antisemitism and “expel the lunatics”."
Buckley also opposed racism and white supremacists.
Yes, there was a time when, while disagreeing with conservatives & Republicans on many issues, I at least felt I understood the basic premises and that we shared at least some values. It's amazing how the John BIrch wing has dominated, and how a reality show snake-oil…

Foundation models for equation discovery in high energy physics
Manuel Morales-Alvarado
https://arxiv.org/abs/2510.03397 https://arxiv.org/pdf/2510.03397…

Foundation models for equation discovery in high energy physics
Foundation models, large machine learning models trained on broad, multimodal datasets, have been gaining increasing attention in scientific applications due to their strong performance on diverse downstream tasks. Large Language Models (LLMs), a prominent instance of foundation models, have achieved remarkable success in tasks such as text and image generation. In this work, we investigate their potential for equation discovery in high energy physics, focusing on symbolic regression. We apply …

Quantum Walks for Chemical Reaction Networks
Seenivasan Hariharan, Sebastian Zur, Sachin Kinge, Lucas Visscher, Kareljan Schoutens, Stacey Jeffery
https://arxiv.org/abs/2509.07890

Quantum Walks for Chemical Reaction Networks
We lay the foundation for a quantum algorithmic framework to analyse fixed-structure chemical reaction networks (CRNs) using quantum random walks (QRWs) via electrical circuit theory. We model perturbations to CRNs, such as, species injections that shift steady-state concentrations, while keeping the underlying species-reaction graph fixed. Under physically meaningful mass-action constraints, we develop quantum algorithms that (i) decide reachability of target species after perturbation, (ii) s…

The Ethereum Foundation announces the "Privacy cluster", a team of 47 blockchain industry experts developing protocol-level privacy features for the network (Vince Quill/Cointelegraph)
https://cointelegraph.com/news/ethereum-foundation-privacy-cluster-team…

PuzzlePlex: Benchmarking Foundation Models on Reasoning and Planning with Puzzles
Yitao Long, Yuru Jiang, Hongjun Liu, Yilun Zhao, Jingchen Sun, Yiqiu Shen, Chen Zhao, Arman Cohan, Dennis Shasha
https://arxiv.org/abs/2510.06475

PuzzlePlex: Benchmarking Foundation Models on Reasoning and Planning with Puzzles
This work investigates the reasoning and planning capabilities of foundation models and their scalability in complex, dynamic environments. We introduce PuzzlePlex, a benchmark designed to assess these capabilities through a diverse set of puzzles. PuzzlePlex consists of 15 types of puzzles, including deterministic and stochastic games of varying difficulty, as well as single-player and two-player scenarios. The PuzzlePlex framework provides a comprehensive environment for each game, and suppor…

Leveraging Generic Foundation Models for Multimodal Surgical Data Analysis
Simon Pezold, J\'er\^ome A. Kurylec, Jan S. Liechti, Beat P. M\"uller, Jo\"el L. Lavanchy
https://arxiv.org/abs/2509.06831

Leveraging Generic Foundation Models for Multimodal Surgical Data Analysis
We investigate how both the adaptation of a generic foundation model via transfer learning and the integration of complementary modalities from the operating room (OR) can support surgical data science. To this end, we use V-JEPA as the single-modality foundation of a multimodal model for minimally invasive surgery support. We analyze how the model's downstream performance can benefit (a) from finetuning on unlabeled surgical video data and (b) from providing additional time-resolved data strea…

RoentMod: A Synthetic Chest X-Ray Modification Model to Identify and Correct Image Interpretation Model Shortcuts
Lauren H. Cooke, Matthias Jung, Jan M. Brendel, Nora M. Kerkovits, Borek Foldyna, Michael T. Lu, Vineet K. Raghu
https://arxiv.org/abs/2509.08640

RoentMod: A Synthetic Chest X-Ray Modification Model to Identify and Correct Image Interpretation Model Shortcuts
Chest radiographs (CXRs) are among the most common tests in medicine. Automated image interpretation may reduce radiologists\' workload and expand access to diagnostic expertise. Deep learning multi-task and foundation models have shown strong performance for CXR interpretation but are vulnerable to shortcut learning, where models rely on spurious and off-target correlations rather than clinically relevant features to make decisions. We introduce RoentMod, a counterfactual image editing framewo…

LECTURES> Prof. Vesna A. Wallace, "The Interrelationship Between the Texts, Images, and Rituals in Mongolian Buddhism" - MaMa Charitable Foundation Lecture Series in Buddhist Studies
https://ift.tt/QkBDnhJ
Call for Abstracts: Culture and Society in Greek, Roman, and Byzantine Egypt - SCS San Fr…

General Demographic Foundation Models for Enhancing Predictive Performance Across Diseases
Li-Chin Chen, Ji-Tian Sheu, Yuh-Jue Chuang
https://arxiv.org/abs/2509.07330 https://…

General Demographic Foundation Models for Enhancing Predictive Performance Across Diseases
Demographic attributes are universally present in electronic health records and serve as vital predictors in clinical risk stratification and treatment decisions. Despite their significance, these attributes are often relegated to auxiliary roles in model design, with limited attention has been given to learning their representations. This study proposes a General Demographic Pre-trained (GDP) model as a foundational representation framework tailored to age and gender. The model is pre-trained …

Curia: A Multi-Modal Foundation Model for Radiology
Corentin Dancette, Julien Khlaut, Antoine Saporta, Helene Philippe, Elodie Ferreres, Baptiste Callard, Th\'eo Danielou, L\'eo Alberge, L\'eo Machado, Daniel Tordjman, Julie Dupuis, Korentin Le Floch, Jean Du Terrail, Mariam Moshiri, Laurent Dercle, Tom Boeken, Jules Gregory, Maxime Ronot, Fran\c{c}ois Legou, Pascal Roux, Marc Sapoval, Pierre Manceron, Paul H\'erent

Curia: A Multi-Modal Foundation Model for Radiology
AI-assisted radiological interpretation is based on predominantly narrow, single-task models. This approach is impractical for covering the vast spectrum of imaging modalities, diseases, and radiological findings. Foundation models (FMs) hold the promise of broad generalization across modalities and in low-data settings. However, this potential has remained largely unrealized in radiology. We introduce Curia, a foundation model trained on the entire cross-sectional imaging output of a major hos…

Probabilistic operator learning: generative modeling and uncertainty quantification for foundation models of differential equations
Benjamin J. Zhang, Siting Liu, Stanley J. Osher, Markos A. Katsoulakis
https://arxiv.org/abs/2509.05186

Probabilistic operator learning: generative modeling and uncertainty quantification for foundation models of differential equations
In-context operator networks (ICON) are a class of operator learning methods based on the novel architectures of foundation models. Trained on a diverse set of datasets of initial and boundary conditions paired with corresponding solutions to ordinary and partial differential equations (ODEs and PDEs), ICON learns to map example condition-solution pairs of a given differential equation to an approximation of its solution operator. Here, we present a probabilistic framework that reveals ICON as …

CuspAI, which develops AI foundation models for materials discovery, raised a $100M Series A led by NEA and Temasek, a source says at a ~$520M valuation (Jeremy Kahn/Fortune)
https://fortune.com/2025/09/10/cuspai-raises-100-million-in…

AI for chemistry startup CuspAI raises $100 million in new venture capital funding
NEA and Temasek are leading the investment into CuspAI, with Nvidia's NVentures, Samsung, and Hyundai participating.

Q&A with EFF Executive Director Cindy Cohn, who will leave the role later this year after leading the nonprofit since 2015, on privacy, encryption, AI, and more (Dell Cameron/Wired)
https://www.wired.com/story/eff-cindy-cohn-stepping-down/

Cindy Cohn Is Leaving the EFF, but Not the Fight for Digital Rights
After 25 years at the Electronic Frontier Foundation, Cindy Cohn is stepping down as executive director. In a WIRED interview, she reflects on encryption, AI, and why she’s not ready to quit the battle.

Towards Interpretable Deep Neural Networks for Tabular Data
Khawla Elhadri, J\"org Schl\"otterer, Christin Seifert
https://arxiv.org/abs/2509.08617 https://

Towards Interpretable Deep Neural Networks for Tabular Data
Tabular data is the foundation of many applications in fields such as finance and healthcare. Although DNNs tailored for tabular data achieve competitive predictive performance, they are blackboxes with little interpretability. We introduce XNNTab, a neural architecture that uses a sparse autoencoder (SAE) to learn a dictionary of monosemantic features within the latent space used for prediction. Using an automated method, we assign human-interpretable semantics to these features. This allows u…

LECTURES> Prof. Vesna A. Wallace, "The Interrelationship Between the Texts, Images, and Rituals in Mongolian Buddhism" - MaMa Charitable Foundation Lecture Series in Buddhist Studies https://networks.h-net.org/group/annou

Exploring Autoregressive Vision Foundation Models for Image Compression
Huu-Tai Phung, Yu-Hsiang Lin, Yen-Kuan Ho, Wen-Hsiao Peng
https://arxiv.org/abs/2509.05169 https://

Exploring Autoregressive Vision Foundation Models for Image Compression
This work presents the first attempt to repurpose vision foundation models (VFMs) as image codecs, aiming to explore their generation capability for low-rate image compression. VFMs are widely employed in both conditional and unconditional generation scenarios across diverse downstream tasks, e.g., physical AI applications. Many VFMs employ an encoder-decoder architecture similar to that of end-to-end learned image codecs and learn an autoregressive (AR) model to perform next-token prediction. …

heise | Home Assistant: Interview über Erfolg, KI-Code und das nächste Feature
Franck Nijhof leitet die Home-Assistant-Entwicklung bei der Open Home Foundation. Im Interview erzählt er, welche Neuerungen Nutzer 2025 noch erwarten.

VA-Adapter: Adapting Ultrasound Foundation Model to Echocardiography Probe Guidance
Teng Wang, Haojun Jiang, Yuxuan Wang, Zhenguo Sun, Shiji Song, Gao Huang
https://arxiv.org/abs/2510.06809

VA-Adapter: Adapting Ultrasound Foundation Model to Echocardiography Probe Guidance
Echocardiography is a critical tool for detecting heart diseases. Recently, ultrasound foundation models have demonstrated remarkable capabilities in cardiac ultrasound image analysis. However, obtaining high-quality ultrasound images is a prerequisite for accurate diagnosis. Due to the exceptionally high operational difficulty of cardiac ultrasound, there is a shortage of highly skilled personnel, which hinders patients from receiving timely examination services. In this paper, we aim to adapt…

An entropy formula for the Deep Linear Network
Govind Menon, Tianmin Yu
https://arxiv.org/abs/2509.09088 https://arxiv.org/pdf/2509.09088

An entropy formula for the Deep Linear Network
We study the Riemannian geometry of the Deep Linear Network (DLN) as a foundation for a thermodynamic description of the learning process. The main tools are the use of group actions to analyze overparametrization and the use of Riemannian submersion from the space of parameters to the space of observables. The foliation of the balanced manifold in the parameter space by group orbits is used to define and compute a Boltzmann entropy. We also show that the Riemannian geometry on the space of obs…

VCoT-Grasp: Grasp Foundation Models with Visual Chain-of-Thought Reasoning for Language-driven Grasp Generation
Haoran Zhang, Shuanghao Bai, Wanqi Zhou, Yuedi Zhang, Qi Zhang, Pengxiang Ding, Cheng Chi, Donglin Wang, Badong Chen
https://arxiv.org/abs/2510.05827

VCoT-Grasp: Grasp Foundation Models with Visual Chain-of-Thought Reasoning for Language-driven Grasp Generation
Robotic grasping is one of the most fundamental tasks in robotic manipulation, and grasp detection/generation has long been the subject of extensive research. Recently, language-driven grasp generation has emerged as a promising direction due to its practical interaction capabilities. However, most existing approaches either lack sufficient reasoning and generalization capabilities or depend on complex modular pipelines. Moreover, current grasp foundation models tend to overemphasize dialog and…

A Foundation Model for Chest X-ray Interpretation with Grounded Reasoning via Online Reinforcement Learning
Qika Lin, Yifan Zhu, Bin Pu, Ling Huang, Haoran Luo, Jingying Ma, Zhen Peng, Tianzhe Zhao, Fangzhi Xu, Jian Zhang, Kai He, Zhonghong Ou, Swapnil Mishra, Mengling Feng
https://arxiv.org/abs/2509.03906

A Foundation Model for Chest X-ray Interpretation with Grounded Reasoning via Online Reinforcement Learning
Medical foundation models (FMs) have shown tremendous promise amid the rapid advancements in artificial intelligence (AI) technologies. However, current medical FMs typically generate answers in a black-box manner, lacking transparent reasoning processes and locally grounded interpretability, which hinders their practical clinical deployments. To this end, we introduce DeepMedix-R1, a holistic medical FM for chest X-ray (CXR) interpretation. It leverages a sequential training pipeline: initiall…

Evaluating Fundus-Specific Foundation Models for Diabetic Macular Edema Detection
Franco Javier Arellano, Jos\'e Ignacio Orlando
https://arxiv.org/abs/2510.07277 https://

Evaluating Fundus-Specific Foundation Models for Diabetic Macular Edema Detection
Diabetic Macular Edema (DME) is a leading cause of vision loss among patients with Diabetic Retinopathy (DR). While deep learning has shown promising results for automatically detecting this condition from fundus images, its application remains challenging due the limited availability of annotated data. Foundation Models (FM) have emerged as an alternative solution. However, it is unclear if they can cope with DME detection in particular. In this paper, we systematically compare different FM an…

The UAE's Institute of Foundation Models open sources its K2 Think model, trained on only ~2,000 AI chips and designed for math, coding, and science research (Cade Metz/New York Times)
https://www.nytimes.com/2025/09/09/technology/uae-emirates-ai-open-sourc…

United Arab Emirates Joins U.S. and China in Giving Away A.I. Technology
The Persian Gulf nation has “open sourced” technology meant to compete with OpenAI and China’s DeepSeek.

CLAPS: A CLIP-Unified Auto-Prompt Segmentation for Multi-Modal Retinal Imaging
Zhihao Zhao, Yinzheng Zhao, Junjie Yang, Xiangtong Yao, Quanmin Liang, Shahrooz Faghihroohi, Kai Huang, Nassir Navab, M. Ali Nasseri
https://arxiv.org/abs/2509.08618

CLAPS: A CLIP-Unified Auto-Prompt Segmentation for Multi-Modal Retinal Imaging
Recent advancements in foundation models, such as the Segment Anything Model (SAM), have significantly impacted medical image segmentation, especially in retinal imaging, where precise segmentation is vital for diagnosis. Despite this progress, current methods face critical challenges: 1) modality ambiguity in textual disease descriptions, 2) a continued reliance on manual prompting for SAM-based workflows, and 3) a lack of a unified framework, with most methods being modality- and task-specifi…

LECTURES> Prof. Vesna A. Wallace, "The Interrelationship Between the Texts, Images, and Rituals in Mongolian Buddhism" - MaMa Charitable Foundation Lecture Series in Buddhist Studies
https://ift.tt/PGgfjrn
Hill on Baranski, 'The Globalization of Wheat: A Critical History of the Green Revolu…

FoMo4Wheat: Toward reliable crop vision foundation models with globally curated data
Bing Han, Chen Zhu, Dong Han, Rui Yu, Songliang Cao, Jianhui Wu, Scott Chapman, Zijian Wang, Bangyou Zheng, Wei Guo, Marie Weiss, Benoit de Solan, Andreas Hund, Lukas Roth, Kirchgessner Norbert, Andrea Visioni, Yufeng Ge, Wenjuan Li, Alexis Comar, Dong Jiang, Dejun Han, Fred Baret, Yanfeng Ding, Hao Lu, Shouyang Liu

FoMo4Wheat: Toward reliable crop vision foundation models with globally curated data
Vision-driven field monitoring is central to digital agriculture, yet models built on general-domain pretrained backbones often fail to generalize across tasks, owing to the interaction of fine, variable canopy structures with fluctuating field conditions. We present FoMo4Wheat, one of the first crop-domain vision foundation model pretrained with self-supervision on ImAg4Wheat, the largest and most diverse wheat image dataset to date (2.5 million high-resolution images collected over a decade a…

VER: Vision Expert Transformer for Robot Learning via Foundation Distillation and Dynamic Routing
Yixiao Wang, Mingxiao Huo, Zhixuan Liang, Yushi Du, Lingfeng Sun, Haotian Lin, Jinghuan Shang, Chensheng Peng, Mohit Bansal, Mingyu Ding, Masayoshi Tomizuka
https://arxiv.org/abs/2510.05213

VER: Vision Expert Transformer for Robot Learning via Foundation Distillation and Dynamic Routing
Pretrained vision foundation models (VFMs) advance robotic learning via rich visual representations, yet individual VFMs typically excel only in specific domains, limiting generality across tasks. Distilling multiple VFMs into a unified representation for policy can mitigate this limitation but often yields inflexible task-specific feature selection and requires costly full re-training to incorporate robot-domain knowledge. We propose VER, a Vision Expert transformer for Robot learning. During …

Q&A with EFF Executive Director Cindy Cohn, who will leave the role later this year after leading the nonprofit since 2015, on privacy, encryption, AI, and more (Dell Cameron/Wired)
https://www.wired.com/story/eff-cindy-cohn-stepping-down/

Cindy Cohn Is Leaving the EFF, but Not the Fight for Digital Rights
After 25 years at the Electronic Frontier Foundation, Cindy Cohn is stepping down as executive director. In a WIRED interview, she reflects on encryption, AI, and why she’s not ready to quit the battle.

Intel unveils Panther Lake, or Intel Core Ultra Series 3, the first chip built on its 18A process, coming to laptops and handhelds in late 2025 and early 2026 (Sean Hollister/The Verge)
https://www.theverge.com/report/797146/intel-…

Here is Panther Lake, Intel’s 2026 laptop chip with next-gen graphics
Intel’s Panther Lake, built on its 18A process, is the foundation of its next Intel Core Ultra Series 3 laptop chips. Here’s what we know.

FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases
Matteo Poggi, Fabio Tosi
https://arxiv.org/abs/2509.05297 https://arxiv.or…

FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases
We present FlowSeek, a novel framework for optical flow requiring minimal hardware resources for training. FlowSeek marries the latest advances on the design space of optical flow networks with cutting-edge single-image depth foundation models and classical low-dimensional motion parametrization, implementing a compact, yet accurate architecture. FlowSeek is trained on a single consumer-grade GPU, a hardware budget about 8x lower compared to most recent methods, and still achieves superior cros…

Long-tailed Recognition with Model Rebalancing
Jiaan Luo, Feng Hong, Qiang Hu, Xiaofeng Cao, Feng Liu, Jiangchao Yao
https://arxiv.org/abs/2510.08177 https://

Long-tailed Recognition with Model Rebalancing
Long-tailed recognition is ubiquitous and challenging in deep learning and even in the downstream finetuning of foundation models, since the skew class distribution generally prevents the model generalization to the tail classes. Despite the promise of previous methods from the perspectives of data augmentation, loss rebalancing and decoupled training etc., consistent improvement in the broad scenarios like multi-label long-tailed recognition is difficult. In this study, we dive into the essent…

Efficient Video-to-Audio Generation via Multiple Foundation Models Mapper
Gehui Chen, Guan'an Wang, Xiaowen Huang, Jitao Sang
https://arxiv.org/abs/2509.04957 https://

Efficient Video-to-Audio Generation via Multiple Foundation Models Mapper
Recent Video-to-Audio (V2A) generation relies on extracting semantic and temporal features from video to condition generative models. Training these models from scratch is resource intensive. Consequently, leveraging foundation models (FMs) has gained traction due to their cross-modal knowledge transfer and generalization capabilities. One prior work has explored fine-tuning a lightweight mapper network to connect a pre-trained visual encoder with a text-to-audio generation model for V2A. Inspi…

FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts
Heming Zou, Yunliang Zang, Wutong Xu, Yao Zhu, Xiangyang Ji
https://arxiv.org/abs/2510.08396

FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts
Low-Rank Adaptation (LoRA) is a widely used parameter-efficient fine-tuning method for foundation models, but it suffers from parameter interference, resulting in suboptimal performance. Although Mixture-of-Experts (MoE)-based LoRA variants show promise in mitigating intra-task correlations in single-task instruction tuning, they introduce additional router parameters and remain ineffective in multi-task model merging where inter-task interference arises. Inspired by the fly olfactory circuit, …

How Wikipedia became the factual foundation of the web and why it's under attack from Musk, conservative groups, the Trump administration, and other governments (Josh Dzieza/The Verge)
https://www.theverge.com/cs/features/717322/wikipedia-atta…

How Wikipedia survives while the rest of the internet breaks
How the world’s largest encyclopedia became the factual foundation of the web, but now it’s under attack from the right wing, tech billionaires, and AI.

ActiveMark: on watermarking of visual foundation models via massive activations
Anna Chistyakova, Mikhail Pautov
https://arxiv.org/abs/2510.04966 https://a…

ActiveMark: on watermarking of visual foundation models via massive activations
Being trained on large and vast datasets, visual foundation models (VFMs) can be fine-tuned for diverse downstream tasks, achieving remarkable performance and efficiency in various computer vision applications. The high computation cost of data collection and training motivates the owners of some VFMs to distribute them alongside the license to protect their intellectual property rights. However, a dishonest user of the protected model's copy may illegally redistribute it, for example, to make …

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[4/8]:
- Bringing Graphs to the Table: Zero-shot Node Classification via Tabular Foundation Models
Adrian Hayler, Xingyue Huang, \.Ismail \.Ilkan Ceylan, Michael Bronstein, Ben Finkelshtein

On the optimization dynamics of RLVR: Gradient gap and step size thresholds
Joe Suk, Yaqi Duan
https://arxiv.org/abs/2510.08539 https://arxiv.org/pdf/2510.…

On the optimization dynamics of RLVR: Gradient gap and step size thresholds
Reinforcement Learning with Verifiable Rewards (RLVR), which uses simple binary feedback to post-train large language models, has shown significant empirical success. However, a principled understanding of why it works has been lacking. This paper builds a theoretical foundation for RLVR by analyzing its training process at both the full-response (trajectory) and token levels. Central to our analysis is a quantity called the Gradient Gap, which formalizes the direction of improvement from low-r…

Turning Tabular Foundation Models into Graph Foundation Models
Dmitry Eremeev, Gleb Bazhenov, Oleg Platonov, Artem Babenko, Liudmila Prokhorenkova
https://arxiv.org/abs/2508.20906

Turning Tabular Foundation Models into Graph Foundation Models
While foundation models have revolutionized such fields as natural language processing and computer vision, their application and potential within graph machine learning remain largely unexplored. One of the key challenges in designing graph foundation models (GFMs) is handling diverse node features that can vary across different graph datasets. Although many works on GFMs have been focused exclusively on text-attributed graphs, the problem of handling arbitrary features of other types in GFMs …

FloodVision: Urban Flood Depth Estimation Using Foundation Vision-Language Models and Domain Knowledge Graph
Zhangding Liu, Neda Mohammadi, John E. Taylor
https://arxiv.org/abs/2509.04772

FloodVision: Urban Flood Depth Estimation Using Foundation Vision-Language Models and Domain Knowledge Graph
Timely and accurate floodwater depth estimation is critical for road accessibility and emergency response. While recent computer vision methods have enabled flood detection, they suffer from both accuracy limitations and poor generalization due to dependence on fixed object detectors and task-specific training. To enable accurate depth estimation that can generalize across diverse flood scenarios, this paper presents FloodVision, a zero-shot framework that combines the semantic reasoning abilit…

Training-Free Out-Of-Distribution Segmentation With Foundation Models
Laith Nayal, Hadi Salloum, Ahmad Taha, Yaroslav Kholodov, Alexander Gasnikov
https://arxiv.org/abs/2510.02909

Training-Free Out-Of-Distribution Segmentation With Foundation Models
Detecting unknown objects in semantic segmentation is crucial for safety-critical applications such as autonomous driving. Large vision foundation models, includ- ing DINOv2, InternImage, and CLIP, have advanced visual representation learn- ing by providing rich features that generalize well across diverse tasks. While their strength in closed-set semantic tasks is established, their capability to detect out- of-distribution (OoD) regions in semantic segmentation remains underexplored. In this …

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