Tootfinder

Opt-in global Mastodon full text search. Join the index!

@arXiv_csCY_bot@mastoxiv.page
2025-08-19 10:38:00

Urban AI Governance Must Embed Legal Reasonableness for Democratic and Sustainable Cities
Rashid Mushkani
arxiv.org/abs/2508.12174 arxiv.or…

Urban AI Governance Must Embed Legal Reasonableness for Democratic and Sustainable Cities
This position paper argues that embedding the legal "reasonable person" standard in municipal AI systems is essential for democratic and sustainable urban governance. As cities increasingly deploy artificial intelligence (AI) systems, concerns around equity, accountability, and normative legitimacy are growing. This paper introduces the Urban Reasonableness Layer (URL), a conceptual framework that adapts the legal "reasonable person" standard for supervisory oversight in municipal AI systems, i…

@axbom@axbom.me
2025-10-17 09:24:45

Full segment about "AI" from the NPR interview, with Ari Shapiro interviewing David Simon.

https://player.mediadelivery.net/embed/514292/496557e3-992b-492d-84d3-5dbfdf261cce

@arXiv_eessIV_bot@mastoxiv.page
2025-08-20 09:27:00

Optimizing Region of Interest Selection for Effective Embedding in Video Steganography Based on Genetic Algorithms
Nizheen A. Ali, Ramadhan J. Mstafa
arxiv.org/abs/2508.13710

Optimizing Region of Interest Selection for Effective Embedding in Video Steganography Based on Genetic Algorithms
With the widespread use of the internet, there is an increasing need to ensure the security and privacy of transmitted data. This has led to an intensified focus on the study of video steganography, which is a technique that hides data within a video cover to avoid detection. The effectiveness of any steganography method depends on its ability to embed data without altering the original video quality while maintaining high efficiency. This paper proposes a new method to video steganography, whi…

@Techmeme@techhub.social
2025-10-14 13:15:47

Salesforce expands its partnerships with OpenAI and Anthropic to embed their AI models into Agentforce 360, including letting customers access it in ChatGPT (Larry Dignan/Constellation Research)
constellationr.com/blog-news/i

Salesforce expands OpenAI, Anthropic partnerships, eyes Agentforce everywhere
Salesforce expanded partnerships with OpenAI and Anthropic to embed their large language models into Agentforce 360. At Dreamforce 2025, Salesforce said it has expanded a partnership with OpenAI so customers can access Agentforce 360 in ChatGPT. Salesforce customers will be able to access sales records, review conversations and build Tableau visualizations from within ChatGPT.

@arXiv_csAI_bot@mastoxiv.page
2025-08-19 10:59:40

Reliability, Embeddedness, and Agency: A Utility-Driven Mathematical Framework for Agent-Centric AI Adoption
Faruk Alpay, Taylan Alpay
arxiv.org/abs/2508.12896

Reliability, Embeddedness, and Agency: A Utility-Driven Mathematical Framework for Agent-Centric AI Adoption
We formalize three design axioms for sustained adoption of agent-centric AI systems executing multi-step tasks: (A1) Reliability > Novelty; (A2) Embed > Destination; (A3) Agency > Chat. We model adoption as a sum of a decaying novelty term and a growing utility term and derive the phase conditions for troughs/overshoots with full proofs. We introduce: (i) an identifiability/confounding analysis for $(α,β,N_0,U_{\max})$ with delta-method gradients; (ii) a non-monotone comparator (logistic-with…

@arXiv_hepth_bot@mastoxiv.page
2025-09-19 09:58:22

Yang-Mills Theory and the $\mathcal{N}=2$ Spinning Path Integral
Carlo Alberto Cremonini, Ivo Sachs
arxiv.org/abs/2509.14792 arxiv.org/pdf/…

Yang-Mills Theory and the $\mathcal{N}=2$ Spinning Path Integral
We embed the perturbative Fock state of the Yang-Mills BV-multiplet in the vertex operator algebra of the path-integral for the $\mathcal{N}=2$ supersymmetric world line and evaluate the pull-back of the latter to an integral form on supermoduli space. Choosing a suitable Poincaré dual on the latter, we show that this integral form describes an extension of Yang-Mills theory. Upon projection back to the Fock space, we recover the Yang-Mills action from the world line. This furthermore gives an…

@arXiv_csRO_bot@mastoxiv.page
2025-08-19 10:59:00

Improving Pre-Trained Vision-Language-Action Policies with Model-Based Search
Cyrus Neary, Omar G. Younis, Artur Kuramshin, Ozgur Aslan, Glen Berseth
arxiv.org/abs/2508.12211

Improving Pre-Trained Vision-Language-Action Policies with Model-Based Search
Pre-trained vision-language-action (VLA) models offer a promising foundation for generalist robot policies, but often produce brittle behaviours or unsafe failures when deployed zero-shot in out-of-distribution scenarios. We present Vision-Language-Action Planning & Search (VLAPS) -- a novel framework and accompanying algorithms that embed model-based search into the inference procedure of pre-trained VLA policies to improve their performance on robotic tasks. Specifically, our method biases a …

@arXiv_csCR_bot@mastoxiv.page
2025-09-19 09:59:31

Watermarking and Anomaly Detection in Machine Learning Models for LORA RF Fingerprinting
Aarushi Mahajan, Wayne Burleson
arxiv.org/abs/2509.15170

Watermarking and Anomaly Detection in Machine Learning Models for LORA RF Fingerprinting
Radio frequency fingerprint identification (RFFI) distinguishes wireless devices by the small variations in their analog circuits, avoiding heavy cryptographic authentication. While deep learning on spectrograms improves accuracy, models remain vulnerable to copying, tampering, and evasion. We present a stronger RFFI system combining watermarking for ownership proof and anomaly detection for spotting suspicious inputs. Using a ResNet-34 on log-Mel spectrograms, we embed three watermarks: a simp…

@arXiv_mathph_bot@mastoxiv.page
2025-09-19 08:38:11

Distances between pure quantum states induced by a distance matrix
Tomasz Miller, Rafa{\l} Bistro\'n
arxiv.org/abs/2509.14727 arxiv.org…

Distances between pure quantum states induced by a distance matrix
With the help of a given distance matrix of size $n$, we construct an infinite family of distances $d_p$ (where $p \geq 2$) on the the complex projective space $\mathbb{P}(\mathbb{C}^n)$, modelling the space of pure states of an $n$-dimensional quantum system. The construction can be seen as providing a natural way to isometrically embed any given finite metric space into the space of pure quantum states 'spanned' upon it. In order to show that the maps $d_p$ are indeed distance functions -- in…

@qbi@freie-re.de
2025-09-05 18:31:44

#Netto wird 35 Jahre und "feiert" das mit einem Ladepreis von 35 ¢/kWh.
Karte:
google.com/maps/d/embed?mid=1H

Netto – Google My Maps
Netto

@thek3nger@mastodon.social
2025-08-18 17:10:13

To inaugurate my new section for short and impromptu articles, I share my Dataview script to list all the movies I watched in a given time period (and it supports movies watched multiple times).
davideaversa.it/bytes/20250818

Movie Posters Grid in Obsidian With Dataview
With the upcoming Bases update in Obsidian, this may become obsolete, but for the time being I am still quite happy using Dataview to embed little graphical elements in my notes. For example, I have a note summarizing all the movies I watched each month. For that I use a combination of CSS and a Dataview query to generate a grid of movie posters. Until recently I used a very simple Dataview query, but I had a problem: if I watched a movie twice in a month, I got only one entry in my poster grid…

@arXiv_csCV_bot@mastoxiv.page
2025-08-18 09:56:10

Is ChatGPT-5 Ready for Mammogram VQA?
Qiang Li, Shansong Wang, Mingzhe Hu, Mojtaba Safari, Zachary Eidex, Xiaofeng Yang
arxiv.org/abs/2508.11628

Is ChatGPT-5 Ready for Mammogram VQA?
Mammogram visual question answering (VQA) integrates image interpretation with clinical reasoning and has potential to support breast cancer screening. We systematically evaluated the GPT-5 family and GPT-4o model on four public mammography datasets (EMBED, InBreast, CMMD, CBIS-DDSM) for BI-RADS assessment, abnormality detection, and malignancy classification tasks. GPT-5 consistently was the best performing model but lagged behind both human experts and domain-specific fine-tuned models. On EM…

@johnleonard@mastodon.social
2025-09-12 13:23:24

The UK's flagship programme to embed AI into NHS hospitals is facing significant hurdles, with a new study revealing that implementing the technology is far more difficult than policymakers anticipated.
computing.co.uk/news/2025/ai/a

AI rollout in NHS hospitals stalled by major implementation challenges, study finds
The UK's flagship programme to embed AI into NHS hospitals is facing significant hurdles, with a new study revealing that implementing the technology is far ...

@arXiv_csLG_bot@mastoxiv.page
2025-09-18 10:14:01

TopoSizing: An LLM-aided Framework of Topology-based Understanding and Sizing for AMS Circuits
Ziming Wei, Zichen Kong, Yuan Wang, David Z. Pan, Xiyuan Tang
arxiv.org/abs/2509.14169

TopoSizing: An LLM-aided Framework of Topology-based Understanding and Sizing for AMS Circuits
Analog and mixed-signal circuit design remains challenging due to the shortage of high-quality data and the difficulty of embedding domain knowledge into automated flows. Traditional black-box optimization achieves sampling efficiency but lacks circuit understanding, which often causes evaluations to be wasted in low-value regions of the design space. In contrast, learning-based methods embed structural knowledge but are case-specific and costly to retrain. Recent attempts with large language m…

@EgorKotov@datasci.social
2025-08-11 14:26:22

ChatGPT Connectors 0click Attack labs.zenity.io/p/agentflayer-c that's why I don't like the idea of connecting any of my services to any of my other services. Convenience has costs.

AgentFlayer: ChatGPT Connectors Oclick Attack (7 minute read) Researchers discovered a zero-click attack exploiting ChatGPT's connector feature to steal data from Google Drive and other services. Attackers embed invisible prompt injections in documents that, when uploaded to ChatGPT, instruct the Al to search connected drives and embed stolen data in image URLs. The malicious prompts then embed stolen data as URL parameters in rendered images hosted on trusted Azure Blob storage.
@axbom@axbom.me
2025-10-18 09:16:23
@… @… I also use DuckDuckGo. This does the same as the DuckDuckGo embed - if you open the link in a browser or session where you are not logged into YouTube. I built it explicitly for sharing YouTub…
@Techmeme@techhub.social
2025-10-18 00:30:49

Google says North Korea hackers are using "EtherHiding" to embed malware on blockchains, the first time it has seen a nation-state threat actor using the method (Bill Toulas/BleepingComputer)
bleepingcomputer.com/news/secu

@Mediagazer@mstdn.social
2025-10-14 16:01:23

WPP and Google strike a $400M deal to embed Google's AI tools like Veo in WPP marketing and give WPP early access to Google's latest video and image models (Daniel Thomas/Financial Times)
ft.com/content/ccf5ea33-1398-4
…

@arXiv_mathCO_bot@mastoxiv.page
2025-09-17 08:35:40

Toroidal Cartesian Products Where One Factor is 3-Connected
Elizabeth Badgett, Christian Millichap
arxiv.org/abs/2509.12354 arxiv.org/pdf/2…

Toroidal Cartesian Products Where One Factor is 3-Connected
In this paper, we provide a partial classification of Cartesian products of graphs that embed on the torus where one factor is $3$-connected. We show that if $G \square H$ embeds on the torus and $G$ is $3$-connected, then $H$ must be a path on two vertices, $P_2$, and we provide significant evidence that $G$ must be outer-cylindrical. At the same time, we show that if $G$ is outer-cylindrical, then $G \square P_2$ embeds on the torus. This all leads us to conjecture that if $G$ is $3$-connecte…

@arXiv_csHC_bot@mastoxiv.page
2025-09-17 10:23:30

Textarium: Entangling Annotation, Abstraction and Argument
Philipp Proff, Marian D\"ork
arxiv.org/abs/2509.13191 arxiv.org/pdf/2509.13…

Textarium: Entangling Annotation, Abstraction and Argument
We present a web-based environment that connects annotation, abstraction, and argumentation during the interpretation of text. As a visual interface for scholarly reading and writing, Textarium combines human analysis with lightweight computational processing to bridge close and distant reading practices. Readers can highlight text, group keywords into concepts, and embed these observations as anchors in essays. The interface renders these interpretive actions as parameterized visualization sta…

@arXiv_csCY_bot@mastoxiv.page
2025-09-19 09:00:41

From Pixels to Urban Policy-Intelligence: Recovering Legacy Effects of Redlining with a Multimodal LLM
Anthony Howell, Nancy Wu, Sharmistha Bagchi, Yushim Kim, Chayn Sun
arxiv.org/abs/2509.15132

From Pixels to Urban Policy-Intelligence: Recovering Legacy Effects of Redlining with a Multimodal LLM
This paper shows how a multimodal large language model (MLLM) can expand urban measurement capacity and support tracking of place-based policy interventions. Using a structured, reason-then-estimate pipeline on street-view imagery, GPT-4o infers neighborhood poverty and tree canopy, which we embed in a quasi-experimental design evaluating the legacy of 1930s redlining. GPT-4o recovers the expected adverse socio-environmental legacy effects of redlining, with estimates statistically indistinguis…

@arXiv_statML_bot@mastoxiv.page
2025-09-16 09:33:36

Contrastive Network Representation Learning
Zihan Dong, Xin Zhou, Ryumei Nakada, Lexin Li, Linjun Zhang
arxiv.org/abs/2509.11316 arxiv.org/…

Contrastive Network Representation Learning
Network representation learning seeks to embed networks into a low-dimensional space while preserving the structural and semantic properties, thereby facilitating downstream tasks such as classification, trait prediction, edge identification, and community detection. Motivated by challenges in brain connectivity data analysis that is characterized by subject-specific, high-dimensional, and sparse networks that lack node or edge covariates, we propose a novel contrastive learning-based statistic…

@bici@mastodon.social
2025-07-23 15:27:06

Cacio e Pepe, the queen 👸🏻 of all the Roman dishes, and my favourite too!
NO butter, NO cream, NO bullshit.
This is the real one and this is my way of making it!
--Daniela Maiorano
the real deal
instagram.com/p/DFKGZnszaYI/?u

Daniela Maiorano on Instagram: "Cacio e Pepe, the queen 👸🏻 of all the Roman dishes, and my favourite too! 3 ingredients only: 👉🏻 parmigiano 👉🏻 pecorino 👉🏻 black pepper NO butter, NO cream, NO bullshit. This is the real one and this is my way of making it! I know you can taste it from there 🫠 #cacioepepe"
163K likes, 1,727 comments - daniela.maiorano on January 22, 2025: "Cacio e Pepe, the queen 👸🏻 of all the Roman dishes, and my favourite too! 3 ingredients only: 👉🏻 parmigiano 👉🏻 pecorino 👉🏻 black pepper NO butter, NO cream, NO bullshit. This is the real one and this is my way of making it! I know you can taste it from there 🫠 #cacioepepe".

@fanf@mendeddrum.org
2025-08-11 20:42:03

from my link log —
CriTcl: easily embed C code in Tcl.
andreas-kupries.github.io/crit
saved 2025-08-03

@arXiv_csNE_bot@mastoxiv.page
2025-09-17 08:17:30

A Neuromorphic Model of Learning Meaningful Sequences with Long-Term Memory
Laxmi R. Iyer, Ali A. Minai
arxiv.org/abs/2509.12850 arxiv.org/…

A Neuromorphic Model of Learning Meaningful Sequences with Long-Term Memory
Learning meaningful sentences is different from learning a random set of words. When humans understand the meaning, the learning occurs relatively quickly. What mechanisms enable this to happen? In this paper, we examine the learning of novel sequences in familiar situations. We embed the Small World of Words (SWOW-EN), a Word Association Norms (WAN) dataset, in a spiking neural network based on the Hierarchical Temporal Memory (HTM) model to simulate long-term memory. Results show that in the …

@mro@digitalcourage.social
2025-07-22 22:19:32

#† #RIP #AD2025 ♫ 🎸 🇬🇧 🦇 Ozzy Osbourne
youtube.com/embed/PrZFscfJxXc
¹

@arXiv_csNI_bot@mastoxiv.page
2025-09-16 10:37:16

Empowering AI-Native 6G Wireless Networks with Quantum Federated Learning
Shaba Shaon, Md Raihan Uddin, Dinh C. Nguyen, Seyyedali Hosseinalipour, Dusit Niyato, Octavia A. Dobre
arxiv.org/abs/2509.10559

Empowering AI-Native 6G Wireless Networks with Quantum Federated Learning
AI-native 6G networks are envisioned to tightly embed artificial intelligence (AI) into the wireless ecosystem, enabling real-time, personalized, and privacy-preserving intelligence at the edge. A foundational pillar of this vision is federated learning (FL), which allows distributed model training across devices without sharing raw data. However, implementing classical FL methods faces several bottlenecks in heterogeneous dynamic wireless networks, including limited device compute capacity, un…

@arXiv_eessAS_bot@mastoxiv.page
2025-08-18 08:44:20

Expressive Speech Retrieval using Natural Language Descriptions of Speaking Style
Wonjune Kang, Deb Roy
arxiv.org/abs/2508.11187 arxiv.org/…

Expressive Speech Retrieval using Natural Language Descriptions of Speaking Style
We introduce the task of expressive speech retrieval, where the goal is to retrieve speech utterances spoken in a given style based on a natural language description of that style. While prior work has primarily focused on performing speech retrieval based on what was said in an utterance, we aim to do so based on how something was said. We train speech and text encoders to embed speech and text descriptions of speaking styles into a joint latent space, which enables using free-form text prompt…

@arXiv_csCR_bot@mastoxiv.page
2025-09-17 09:00:19

Yet Another Watermark for Large Language Models
Siyuan Bao, Ying Shi, Zhiguang Yang, Hanzhou Wu, Xinpeng Zhang
arxiv.org/abs/2509.12574 arx…

Yet Another Watermark for Large Language Models
Existing watermarking methods for large language models (LLMs) mainly embed watermark by adjusting the token sampling prediction or post-processing, lacking intrinsic coupling with LLMs, which may significantly reduce the semantic quality of the generated marked texts. Traditional watermarking methods based on training or fine-tuning may be extendable to LLMs. However, most of them are limited to the white-box scenario, or very time-consuming due to the massive parameters of LLMs. In this paper…

@arXiv_csAI_bot@mastoxiv.page
2025-10-10 10:20:19

Language Models Do Not Embed Numbers Continuously
Alex O. Davies, Roussel Nzoyem, Nirav Ajmeri, Telmo M. Silva Filho
arxiv.org/abs/2510.08009

Language Models Do Not Embed Numbers Continuously
Recent research has extensively studied how large language models manipulate integers in specific arithmetic tasks, and on a more fundamental level, how they represent numeric values. These previous works have found that language model embeddings can be used to reconstruct the original values, however, they do not evaluate whether language models actually model continuous values as continuous. Using expected properties of the embedding space, including linear reconstruction and principal compon…

@arXiv_nuclth_bot@mastoxiv.page
2025-09-18 09:23:01

Nonperturbative Heavy-Flavor Transport Approach for Hot QCD
Tharun Krishna, Ralf Rapp, Yu Fu, Steffen A. Bass, Weiyao Ke
arxiv.org/abs/2509.13881

Nonperturbative Heavy-Flavor Transport Approach for Hot QCD
The heavy charm and bottom quarks are unique probes of the transport properties of the quark-gluon plasma (QGP) and its hadronization in high-energy nuclear collisions. A key challenge in this context is to embed the interactions of the heavy quarks in the expanding medium compatible with the strong-coupling nature of the QGP, and thus to unravel the underlying microscopic mechanisms. In the present work we progress toward this goal by combining recent $T$-matrix interactions for elastic scatte…

@arXiv_csCC_bot@mastoxiv.page
2025-10-14 07:37:10

The algorithmic regulator
Giulio Ruffini
arxiv.org/abs/2510.10300 arxiv.org/pdf/2510.10300

The algorithmic regulator
The regulator theorem states that, under certain conditions, any optimal controller must embody a model of the system it regulates, grounding the idea that controllers embed, explicitly or implicitly, internal models of the controlled. This principle underpins neuroscience and predictive brain theories like the Free-Energy Principle or Kolmogorov/Algorithmic Agent theory. However, the theorem is only proven in limited settings. Here, we treat the deterministic, closed, coupled world-regulator s…

@arXiv_physicschemph_bot@mastoxiv.page
2025-09-16 08:13:16

Assessing the Limits of Graph Neural Networks for Vapor-Liquid Equilibrium Prediction: A Cryogenic Mixture Case Study
Aryan Gupta
arxiv.org/abs/2509.10565

Assessing the Limits of Graph Neural Networks for Vapor-Liquid Equilibrium Prediction: A Cryogenic Mixture Case Study
Accurate and fast thermophysical models are needed to embed vapor-liquid equilibrium (VLE) calculations in design, optimization, and control loops for cryogenic mixtures. This study asks whether a structure-aware graph neural network (GNN; DimeNet++) trained on GERG-2008/CoolProp data can act as a practical surrogate for an equation of state (EoS). We generate a ternary dataset over 90-200 K and pressures to 100 bar, curate it with a 15% density filter (reducing 5,200 states to 1,516), and pair…

@arXiv_mathAT_bot@mastoxiv.page
2025-10-14 09:08:38

A Schauder Basis for Multiparameter Persistence
Peter Bubenik, Zachariah Ross
arxiv.org/abs/2510.10347 arxiv.org/pdf/2510.10347

A Schauder Basis for Multiparameter Persistence
Certain classes of multiparameter persistence modules may be encoded as signed barcodes, represented as points in a polyhedral subset of Euclidean space, we refer to as signed persistence diagrams. These signed persistence diagrams exist in the dual space of compactly supported, Lipschitz functionals on a polyhedral pair. In the interest of statistics and machine learning on multiparameter persistence modules, we aim to embed these signed persistence diagrams into Banach or Hilbert space. We us…

@servelan@newsie.social
2025-08-24 04:52:15

6 cops took down a guy eating in DC.
instagram.com/reel/DNoySZLRzmn

@arXiv_csLG_bot@mastoxiv.page
2025-09-04 10:31:21

Cluster and then Embed: A Modular Approach for Visualization
Elizabeth Coda, Ery Arias-Castro, Gal Mishne
arxiv.org/abs/2509.03373 arxiv.or…

Cluster and then Embed: A Modular Approach for Visualization
Dimensionality reduction methods such as t-SNE and UMAP are popular methods for visualizing data with a potential (latent) clustered structure. They are known to group data points at the same time as they embed them, resulting in visualizations with well-separated clusters that preserve local information well. However, t-SNE and UMAP also tend to distort the global geometry of the underlying data. We propose a more transparent, modular approach consisting of first clustering the data, then embe…

@axbom@axbom.me
2025-10-16 17:07:08

If you're unclear on why you have to load the video before you can play it it's because the first load only loads the image, title and channel name to make the page itself load much faster.

The person viewing is then allowed to make a more considered choice before activating the video. Perhaps you want to open the link an incognito window instead for example.

One great bonus to this embed is that it shows way less ads, if any.

@arXiv_grqc_bot@mastoxiv.page
2025-10-14 10:16:08

Monotonicity of Causal Killing Vectors and Geometry of ADM Mass Minimizers
Sven Hirsch, Lan-Hsuan Huang
arxiv.org/abs/2510.10306 arxiv.org/…

Monotonicity of Causal Killing Vectors and Geometry of ADM Mass Minimizers
We address two problems concerning the ADM mass-minimizing initial data sets. First, we show that the equality case of the positive mass theorem embeds into a pp-wave spacetime. Second, we show that positive Bartnik mass minimizers embed into strongly stationary vacuum spacetimes, thereby confirming the Bartnik stationary vacuum conjecture. A key ingredient is a new monotonicity formula for the Lorentzian length of a causal Killing vector field, which, among other applications, yields a strong …

@arXiv_csCL_bot@mastoxiv.page
2025-09-26 10:16:31

Bounds of Chain-of-Thought Robustness: Reasoning Steps, Embed Norms, and Beyond
Dingzirui Wang, Xuanliang Zhang, Keyan Xu, Qingfu Zhu, Wanxiang Che, Yang Deng
arxiv.org/abs/2509.21284

Bounds of Chain-of-Thought Robustness: Reasoning Steps, Embed Norms, and Beyond
Existing research indicates that the output of Chain-of-Thought (CoT) is significantly affected by input perturbations. Although many methods aim to mitigate such impact by optimizing prompts, a theoretical explanation of how these perturbations influence CoT outputs remains an open area of research. This gap limits our in-depth understanding of how input perturbations propagate during the reasoning process and hinders further improvements in prompt optimization methods. Therefore, in this pape…

@arXiv_csCY_bot@mastoxiv.page
2025-08-18 07:39:30

Bias is a Math Problem, AI Bias is a Technical Problem: 10-year Literature Review of AI/LLM Bias Research Reveals Narrow [Gender-Centric] Conceptions of 'Bias', and Academia-Industry Gap
Sourojit Ghosh, Kyra Wilson
arxiv.org/abs/2508.11067

Bias is a Math Problem, AI Bias is a Technical Problem: 10-year Literature Review of AI/LLM Bias Research Reveals Narrow [Gender-Centric] Conceptions of 'Bias', and Academia-Industry Gap
The rapid development of AI tools and implementation of LLMs within downstream tasks has been paralleled by a surge in research exploring how the outputs of such AI/LLM systems embed biases, a research topic which was already being extensively explored before the era of ChatGPT. Given the high volume of research around the biases within the outputs of AI systems and LLMs, it is imperative to conduct systematic literature reviews to document throughlines within such research. In this paper, we c…

@arXiv_csPL_bot@mastoxiv.page
2025-10-10 08:13:49

The Functional Machine Calculus III: Control
Willem Heijltjes
arxiv.org/abs/2510.07851 arxiv.org/pdf/2510.07851

The Functional Machine Calculus III: Control
The Functional Machine Calculus (Heijltjes 2022) is a new approach to unifying the imperative and functional programming paradigms. It extends the lambda-calculus, preserving the key features of confluent reduction and typed termination, to embed computational effects, evaluation strategies, and control flow operations. The first instalment modelled sequential higher-order computation with global store, input/output, probabilities, and non-determinism, and embedded both the call-by-name and cal…

@arXiv_mathDS_bot@mastoxiv.page
2025-08-05 10:07:11

Factorizable embeddings and the period of an irreducible sofic shift
Brian Marcus, Tom Meyerovitch, Klaus Thomsen, Chengyu Wu
arxiv.org/abs/2508.02554

Factorizable embeddings and the period of an irreducible sofic shift
Generalizing a result of MacDonald we give necessary and sufficient conditions for an arbitrary subshift to embed into an irreducible sofic shift factoring through a given cover by an irreducible subshift of finite type (SFT). We obtain also necessary and sufficient conditions for an arbitrary subshift to embed into an irreducible sofic shift factoring through \emph{some} sliding block code out of an irreducible SFT. We do that when the code is required to be surjective, and hence a factor code…

@arXiv_csSI_bot@mastoxiv.page
2025-08-13 07:42:22

Effective and Efficient Attributed Hypergraph Embedding on Nodes and Hyperedges
Yiran Li, Gongyao Guo, Chen Feng, Jieming Shi
arxiv.org/abs/2508.08807

Effective and Efficient Attributed Hypergraph Embedding on Nodes and Hyperedges
An attributed hypergraph comprises nodes with attributes and hyperedges that connect varying numbers of nodes. Attributed hypergraph node and hyperedge embedding (AHNEE) maps nodes and hyperedges to compact vectors for use in important tasks such as node classification, hyperedge link prediction, and hyperedge classification. Generating high-quality embeddings is challenging due to the complexity of attributed hypergraphs and the need to embed both nodes and hyperedges, especially in large-scal…

@arXiv_astrophCO_bot@mastoxiv.page
2025-08-01 08:20:41

How to embed any likelihood into SBI: Application to Planck Stage IV galaxy surveys and Dynamical Dark Energy
Guillermo Franco Abell\'an, Noemi Anau Montel, Oleg Savchenko, Christoph Weniger
arxiv.org/abs/2507.22990

How to embed any likelihood into SBI: Application to Planck + Stage IV galaxy surveys and Dynamical Dark Energy
Simulation-based inference (SBI) allows fast Bayesian inference for simulators encoding implicit likelihoods. However, some explicit likelihoods cannot be easily reformulated as simulators, hindering their integration into combined analyses within SBI frameworks. One key example in cosmology is given by the Planck CMB likelihoods. We present a simple method to construct an effective simulator for any explicit likelihood using samples from a previously converged Markov Chain Monte Carlo (MCMC) r…

@CubitOom@social.linux.pizza
2025-09-29 17:14:35

Look And Listen (sing-along)
Music:
Look And Listen
Mister Rogers
It's Such A Good Feeling: The Best Of Mister Rogers
Full videos:
1. peertube.wtf/videos/embed/4nbt
2.

@cdarwin@c.im
2025-08-31 04:07:50

Breaking down ‘EchoLeak’, the First Zero-Click AI Vulnerability Enabling Data Exfiltration from Microsoft 365 Copilot.
Aim Labs reported CVE-2025-32711 against Microsoft 365 Copilot back in January, and the fix is now rolled out.
This is an extended variant of the prompt injection exfiltration attacks we've seen in a dozen different products already:
an attacker gets malicious instructions into an LLM system which cause it to access private data and then embed that in …

Breaking down ‘EchoLeak’, the First Zero-Click AI Vulnerability Enabling Data Exfiltration from Microsoft 365 Copilot
Aim Labs reported CVE-2025-32711 against Microsoft 365 Copilot back in January, and the fix is now rolled out. This is an extended variant of the prompt injection exfiltration attacks we've …

@axbom@axbom.me
2025-10-15 18:24:24

Trying out a new way of sharing links to YouTube videos, linking to a more privacy-friendly embed. This is a good one to start with, Karen Hao’s reporting on chatbots and mental health.

https://xbm.se/yt/?id=zkGk_A4noxI

@arXiv_mathCO_bot@mastoxiv.page
2025-09-15 09:11:21

Projective Planar Cartesian Products of Graphs
Nicholas Abell, Elizabeth McDermott, Christian Millichap
arxiv.org/abs/2509.10261 arxiv.org/…

Projective Planar Cartesian Products of Graphs
In this paper, we provide a complete classification of Cartesian products of graphs that embed in the projective plane. Our work requires us to determine minimal Cartesian products that are nonprojective planar, organize their essential properties to be used as constraints for projective planar embeddings, and explicitly construct projective planar embeddings for Cartesian products that satisfy these constraints. A corollary of our work shows that only six of the 35 forbidden minors for the pro…

@arXiv_csSE_bot@mastoxiv.page
2025-08-08 07:38:32

Automated Bug Frame Retrieval from Gameplay Videos Using Vision-Language Models
Wentao Lu, Alexander Senchenko, Abram Hindle, Cor-Paul Bezemer
arxiv.org/abs/2508.04895

Automated Bug Frame Retrieval from Gameplay Videos Using Vision-Language Models
Modern game studios deliver new builds and patches at a rapid pace, generating thousands of bug reports, many of which embed gameplay videos. To verify and triage these bug reports, developers must watch the submitted videos. This manual review is labour-intensive, slow, and hard to scale. In this paper, we introduce an automated pipeline that reduces each video to a single frame that best matches the reported bug description, giving developers instant visual evidence that pinpoints the bug. …

@jonippolito@digipres.club
2025-09-30 00:43:31

Update on attempt to emulate a Shockwave Director web page: I have tried the DirPlayer Chrome extension but get this error:
"Could not deserialize 'VWCF' chunk"
I included both <object> and <embed> tags pointing to the same .dcr file. Does anyone have other emulators to recommend?

DirPlayer - Shockwave Emulator - Chrome Web Store
Play Shockwave content directly from your browser.

@shoppingtonz@mastodon.social
2025-08-12 03:48:10

I'm sorry DuckDuckGo but it looks like you are force feeding your users with Microsoft JavaScript.
You see M$ doesn't give a **** about you.
THEY DON'T TRUST YOU...and that's why they are giving you THEIR JAVASCRIPT.
When serving an ad you could make the ad be natural as part of your web page...
that way I won't have to "accept ads"...I mean if I ALREADY accept your webpage.
EMBED YOUR ADS
Is this a tech problem? I think this …

@Techmeme@techhub.social
2025-10-09 14:15:49

Austin-based Routefusion, whose API for financial institutions lets them embed accounts, payments, currency conversion, and compliance, raised a $26.7M Series A (Mary Ann Azevedo/Crunchbase News)
news.crunchbase.com/venture/fi

Exclusive: Payments Tech Startup Routefusion Raises $26.7M Series A 
Routefusion says it will use its new funding to help grow its engineering product and compliance teams, and expand its go-to-market efforts.

@arXiv_mathGT_bot@mastoxiv.page
2025-10-09 08:51:01

Whitehead doubling, rank estimate and nonembeddability of contractible open manifolds
Shijie Gu, Jian Wang, Yanqing Zou
arxiv.org/abs/2510.06598

Whitehead doubling, rank estimate and nonembeddability of contractible open manifolds
Let $K$ be a nontrivial knot. For each $n\in \mathbb{N}$, we prove that the rank of its $n$th iterated Whitehead doubled knot group $π_1(S^3 \setminus \operatorname{WD}^n(K))$ is bounded below by $n+1$. As an application, we show that there exist infinitely many non-homeomorphic contractible open $n$-manifolds ($n\geq 3$) which cannot embed in a compact, locally connected and locally 1-connected $n$-dimensional metric space.

@Mediagazer@mstdn.social
2025-09-05 12:45:55

ProRata.ai, which lets publishers embed custom AI search on their sites with a 50/50 revenue share, raised a $40M Series B, bringing its total raised to $75M (Kerry Flynn/Axios)
axios.com/2025/09/05/prorata-a

Exclusive: ProRata.ai raises $40M and launches new search tool for publishers
The new product provides publishers custom AI search on their sites.

@arXiv_csCR_bot@mastoxiv.page
2025-10-15 10:05:11

Targeted Pooled Latent-Space Steganalysis Applied to Generative Steganography, with a Fix
Etienne Levecque (LIST3N), Aur\'elien Noirault (CRIStAL), Tom\'a\v{s} Pevn\'y (CTU), Jan Butora (CRIStAL), Patrick Bas (CRIStAL), R\'emi Cogranne (LIST3N)
arxiv.org/abs/2510.12414

Targeted Pooled Latent-Space Steganalysis Applied to Generative Steganography, with a Fix
Steganographic schemes dedicated to generated images modify the seed vector in the latent space to embed a message, whereas most steganalysis methods attempt to detect the embedding in the image space. This paper proposes to perform steganalysis in the latent space by modeling the statistical distribution of the norm of the latent vector. Specifically, we analyze the practical security of a scheme proposed by Hu et. al. for latent diffusion models, which is both robust and practically undetecta…

@arXiv_quantph_bot@mastoxiv.page
2025-08-05 11:43:51

Enhancement of Quantum Semi-Supervised Learning via Improved Laplacian and Poisson Methods
Hamed Gholipour, Farid Bozorgnia, Hamzeh Mohammadigheymasi, Kailash Hambarde, Javier Mancilla, Hugo Proenca, Joao Neves, Moharram Challenger
arxiv.org/abs/2508.02054

Enhancement of Quantum Semi-Supervised Learning via Improved Laplacian and Poisson Methods
This paper develops a hybrid quantum approach for graph-based semi-supervised learning to enhance performance in scenarios where labeled data is scarce. We introduce two enhanced quantum models, the Improved Laplacian Quantum Semi-Supervised Learning (ILQSSL) and the Improved Poisson Quantum Semi-Supervised Learning (IPQSSL), that incorporate advanced label propagation strategies within variational quantum circuits. These models utilize QR decomposition to embed graph structure directly into qu…

@DieGesellschafterinLang@swiss.social
2025-07-31 09:22:29

Bahnhof #Basel - Die Galerie Gleis 4 zeigt ab dem 06. September das Werk «Saint or Sinner» (Heiliger oder Sünder)
Kunst von Mason Storm instagram.com/masonstormgenius/?utm_source=ig_embed

Donald Trump wird im Bahnhof Basel SBB ans Kreuz geschnallt
In der ehemaligen Brasserie im Westflügel kommt es zu einer Zwischennutzung der Galerie Gleis 4. Ein Werk dürfte an der Eröffnung für Aufsehen sorgen.

@arXiv_csAI_bot@mastoxiv.page
2025-10-14 12:25:28

Analyzing and Internalizing Complex Policy Documents for LLM Agents
Jiateng Liu, Zhenhailong Wang, Xiaojiang Huang, Yingjie Li, Xing Fan, Xiang Li, Chenlei Guo, Ruhi Sarikaya, Heng Ji
arxiv.org/abs/2510.11588

Analyzing and Internalizing Complex Policy Documents for LLM Agents
Large Language Model (LLM)-based agentic systems rely on in-context policy documents encoding diverse business rules. As requirements grow, these documents expand rapidly, causing high computational overhead. This motivates developing internalization methods that embed policy documents into model priors while preserving performance. Prior prompt compression work targets generic prompts, but agentic policy documents span multiple complexity levels and require deeper reasoning, making internaliza…

@arXiv_mathGR_bot@mastoxiv.page
2025-08-06 08:33:40

The symmetric groups $S_n, n\geq 4$, and finite non-abelian simple groups are not embeddable in any Riordan group
Tian-Xiao He, Nikolai A. Krylov
arxiv.org/abs/2508.03056

The symmetric groups $S_n, n\geq 4$, and finite non-abelian simple groups are not embeddable in any Riordan group
We prove that the symmetric group of degree greater than three cannot be embedded into the Riordan group with coefficients in any commutative ring. We also prove the impossibility to embed finite non-abelian simple groups. As a closely related topic, we show why all truncated Riordan groups are solvable, in stark contrast to the unsolvability of the infinite-sized Riordan groups. Finally, we give an explicit embedding of the alternating group $A_4$ into the Lagrange subgroup with coefficients i…

@arXiv_qbioNC_bot@mastoxiv.page
2025-08-08 08:40:02

Delay-constrained re-entry governs large-scale brain seizures and other network pathologies
Paul Triebkorn, Huifang E. Wang, Marmaduke Woodman, Maxime Guye, Fabrice Bartolomei, Viktor Jirsa
arxiv.org/abs/2508.04824

Delay-constrained re-entry governs large-scale brain seizures and other network pathologies
Re-entry of travelling excitation loops is a long-suspected driver of human seizures, yet how such loops arise in patient brain networks -- and how susceptible they are to targeted disruption -- remains unclear. We reconstruct a millimetre-scale virtual brain from diffusion MRI of a drug-resistant epilepsy patient, embed excitable Epileptor neural fields, and show that realistic cortico-cortical delays are sufficient to generate self-sustaining re-entry. Systematic parameter sweeps reveal a nar…

@arXiv_csIR_bot@mastoxiv.page
2025-09-05 08:36:41

NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings
Or Shachar, Uri Katz, Yoav Goldberg, Oren Glickman
arxiv.org/abs/2509.04011

NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddings
We present NER Retriever, a zero-shot retrieval framework for ad-hoc Named Entity Retrieval, a variant of Named Entity Recognition (NER), where the types of interest are not provided in advance, and a user-defined type description is used to retrieve documents mentioning entities of that type. Instead of relying on fixed schemas or fine-tuned models, our method builds on internal representations of large language models (LLMs) to embed both entity mentions and user-provided open-ended type desc…

@arXiv_hepph_bot@mastoxiv.page
2025-08-06 08:11:20

Standard Model Mass Spectrum and Interactions In The Holomorphic Unified Field Theory
J. W. Moffat, E. J. Thompson
arxiv.org/abs/2508.02747

Standard Model Mass Spectrum and Interactions In The Holomorphic Unified Field Theory
We present a unified, ultraviolet-finite framework for the full Standard Model particle mass spectrum based on the Holomorphic Unified Field Theory augmented by nonlocal entire-function regulators. Starting from a single holomorphic action on the complexified spacetime manifold $M^4_{\mathbb{C}}$, with a Hermitian metric unifying gravity, gauge and matter sectors, we embed exponential regulator insertions to render all loop integrals finite without breaking gauge or diffeomorphism invariance. A…

@Techmeme@techhub.social
2025-09-08 13:35:41

Atlanta-based Rainforest, which lets platforms embed payment processing, raised a $29M Series B led by Matrix and Infinity, taking its total funding to $57.5M (Crunchbase News)
news.crunchbase.com/fintech/st

Exclusive: Stripe Challenger Rainforest Lands $29M Series B
Rainforest, a startup that embeds payment processing into other software platforms, has raised $29 million in a Series B funding round, the company told Crunchbase News exclusively.

@arXiv_eessSP_bot@mastoxiv.page
2025-09-05 07:58:00

A Low-Cost Open-Source BLE-Based Asian Hornet Tracking System
Gilles Callebaut, Jan Van Moer
arxiv.org/abs/2509.03979 arxiv.org/pdf/2509.03…

A Low-Cost Open-Source BLE-Based Asian Hornet Tracking System
The Asian hornet (Vespa velutina) poses a serious threat to ecosystems and beekeeping. Locating nests is essential, but usually involves time-consuming manual triangulation. We present a low-cost, open-source tracking system based on Bluetooth Low Energy (BLE). The system consists of a lightweight BLE tag and a software-defined radio (SDR) receiver implemented in GNU Radio. By bypassing the BLE stack, we embed a custom pseudo-noise (PN) sequence in the uncoded PHY for correlation-based detectio…

@arXiv_csCV_bot@mastoxiv.page
2025-10-09 10:48:51

SpecGuard: Spectral Projection-based Advanced Invisible Watermarking
Inzamamul Alam, Md Tanvir Islam, Khan Muhammad, Simon S. Woo
arxiv.org/abs/2510.07302

SpecGuard: Spectral Projection-based Advanced Invisible Watermarking
Watermarking embeds imperceptible patterns into images for authenticity verification. However, existing methods often lack robustness against various transformations primarily including distortions, image regeneration, and adversarial perturbation, creating real-world challenges. In this work, we introduce SpecGuard, a novel watermarking approach for robust and invisible image watermarking. Unlike prior approaches, we embed the message inside hidden convolution layers by converting from the spa…

@arXiv_csCY_bot@mastoxiv.page
2025-09-16 09:24:17

SCOR: A Framework for Responsible AI Innovation in Digital Ecosystems
Mohammad Saleh Torkestani, Taha Mansouri
arxiv.org/abs/2509.10653 arx…

SCOR: A Framework for Responsible AI Innovation in Digital Ecosystems
AI-driven digital ecosystems span diverse stakeholders including technology firms, regulators, accelerators and civil society, yet often lack cohesive ethical governance. This paper proposes a four-pillar framework (SCOR) to embed accountability, fairness, and inclusivity across such multi-actor networks. Leveraging a design science approach, we develop a Shared Ethical Charter(S), structured Co-Design and Stakeholder Engagement protocols(C), a system of Continuous Oversight and Learning(O), an…

@arXiv_physicsfludyn_bot@mastoxiv.page
2025-08-05 10:01:10

Physics-informed Fourier Basis Neural Network for Fluid Mechanics
Chao Wang, Shilong Li, Zelong Yuan, Chunyu Guo
arxiv.org/abs/2508.02166 a…

Physics-informed Fourier Basis Neural Network for Fluid Mechanics
Solving partial differential equations (PDEs) is an important yet challenging task in fluid mechanics. In this study, we embed an improved Fourier series into neural networks and propose a physics-informed Fourier basis neural network (FBNN) by incorporating physical information to solve canonical PDEs in fluid mechanics. The results demonstrated that the proposed framework exhibits a strong nonlinear fitting capability and exceptional periodic modeling performance. In particular, our model sho…

@arXiv_csLG_bot@mastoxiv.page
2025-09-12 10:09:29

Graph Alignment via Dual-Pass Spectral Encoding and Latent Space Communication
Maysam Behmanesh, Erkan Turan, Maks Ovsjanikov
arxiv.org/abs/2509.09597

Graph Alignment via Dual-Pass Spectral Encoding and Latent Space Communication
Graph alignment-the problem of identifying corresponding nodes across multiple graphs-is fundamental to numerous applications. Most existing unsupervised methods embed node features into latent representations to enable cross-graph comparison without ground-truth correspondences. However, these methods suffer from two critical limitations: the degradation of node distinctiveness due to oversmoothing in GNN-based embeddings, and the misalignment of latent spaces across graphs caused by structura…

@arXiv_csCR_bot@mastoxiv.page
2025-10-14 12:00:38

Toxic Ink on Immutable Paper: Content Moderation for Ethereum Input Data Messages (IDMs)
Xihan Xiong, Zhipeng Wang, Qin Wang, William Knottenbelt
arxiv.org/abs/2510.10761

Toxic Ink on Immutable Paper: Content Moderation for Ethereum Input Data Messages (IDMs)
Decentralized communication is becoming an important use case within Web3. On Ethereum, users can repurpose the transaction input data field to embed natural-language messages, commonly known as Input Data Messages (IDMs). However, as IDMs gain wider adoption, there has been a growing volume of toxic content on-chain. This trend is concerning, as Ethereum provides no protocol-level support for content moderation. We propose two moderation frameworks for Ethereum IDMs: (i) BUILDERMOD, where bu…

@Techmeme@techhub.social
2025-09-05 12:35:50

ProRata.ai, which lets publishers embed custom AI search on their sites with a 50/50 revenue share, raised a $40M Series B, bringing its total raised to $70M (Kerry Flynn/Axios)
axios.com/2025/09/05/prorata-a

Exclusive: ProRata.ai raises $40M and launches new search tool for publishers
The new product provides publishers custom AI search on their sites.

@arXiv_csCR_bot@mastoxiv.page
2025-10-14 12:15:28

MPCitH-based Signatures from Restricted Decoding Problems
Michele Battagliola, Sebastian Bitzer, Antonia Wachter-Zeh, Violetta Weger
arxiv.org/abs/2510.11224

MPCitH-based Signatures from Restricted Decoding Problems
Threshold-Computation-in-the-Head (TCitH) and VOLE-in-the-Head (VOLEitH), two recent developments of the MPC-in-the-Head (MPCitH) paradigm, have significantly improved the performance of digital signature schemes in this framework. In this note, we embed the restricted decoding problem within these frameworks. We propose a structurally simple modeling that achieves competitive signature sizes. Specifically, by instantiating the restricted decoding problem with the same hardness assumption und…

@arXiv_csRO_bot@mastoxiv.page
2025-10-03 10:08:41

An Anytime, Scalable and Complete Algorithm for Embedding a Manufacturing Procedure in a Smart Factory
Christopher Leet, Aidan Sciortino, Sven Koenig
arxiv.org/abs/2510.01770

An Anytime, Scalable and Complete Algorithm for Embedding a Manufacturing Procedure in a Smart Factory
Modern automated factories increasingly run manufacturing procedures using a matrix of programmable machines, such as 3D printers, interconnected by a programmable transport system, such as a fleet of tabletop robots. To embed a manufacturing procedure into a smart factory, an operator must: (a) assign each of its processes to a machine and (b) specify how agents should transport parts between machines. The problem of embedding a manufacturing process into a smart factory is termed the Smart Fa…

@arXiv_mathGR_bot@mastoxiv.page
2025-08-05 08:31:00

Cyclic orders and actions of Leary--Minasyan groups on coarse $\mathrm{PD}(n)$ spaces
Arka Banerjee, Kevin Schreve
arxiv.org/abs/2508.01075

Cyclic orders and actions of Leary--Minasyan groups on coarse $\mathrm{PD}(n)$ spaces
We show that for $n \geq 3$, there are torsion-free CAT(0) groups with visual boundaries that embed into $S^n$ but which are not virtually the fundamental group of a compact aspherical $n+1$-manifold. The groups are the CAT(0) and not bi-automatic groups constructed previously by Leary and Minasyan. The obstruction comes from analyzing certain cyclic orders on the boundary of the Bass-Serre tree, in the same manner as Kapovich-Kleiner ruled out actions of Baumslag-Solitar groups on coarse $\mat…

@arXiv_csCR_bot@mastoxiv.page
2025-10-14 11:40:18

Zk-SNARK Marketplace with Proof of Useful Work
Samuel Oleksak, Richard Gazdik, Martin Peresini, Ivan Homoliak
arxiv.org/abs/2510.09729 arxi…

Zk-SNARK Marketplace with Proof of Useful Work
Proof of Work (PoW) is widely regarded as the most secure permissionless blockchain consensus protocol. However, its reliance on computationally intensive yet externally useless puzzles results in excessive electric energy wasting. To alleviate this, Proof of Useful Work (PoUW) has been explored as an alternative to secure blockchain platforms while also producing real-world value. Despite this promise, existing PoUW proposals often fail to embed the integrity of the chain and identity of the m…

@arXiv_csAI_bot@mastoxiv.page
2025-10-08 10:03:29

From Agentification to Self-Evolving Agentic AI for Wireless Networks: Concepts, Approaches, and Future Research Directions
Changyuan Zhao, Ruichen Zhang, Jiacheng Wang, Dusit Niyato, Geng Sun, Xianbin Wang, Shiwen Mao, Abbas Jamalipour
arxiv.org/abs/2510.05596

From Agentification to Self-Evolving Agentic AI for Wireless Networks: Concepts, Approaches, and Future Research Directions
Self-evolving agentic artificial intelligence (AI) offers a new paradigm for future wireless systems by enabling autonomous agents to continually adapt and improve without human intervention. Unlike static AI models, self-evolving agents embed an autonomous evolution cycle that updates models, tools, and workflows in response to environmental dynamics. This paper presents a comprehensive overview of self-evolving agentic AI, highlighting its layered architecture, life cycle, and key techniques,…

@arXiv_csCY_bot@mastoxiv.page
2025-10-13 09:03:00

AI and Human Oversight: A Risk-Based Framework for Alignment
Laxmiraju Kandikatla, Branislav Radeljic
arxiv.org/abs/2510.09090 arxiv.org/pd…

AI and Human Oversight: A Risk-Based Framework for Alignment
As Artificial Intelligence (AI) technologies continue to advance, protecting human autonomy and promoting ethical decision-making are essential to fostering trust and accountability. Human agency (the capacity of individuals to make informed decisions) should be actively preserved and reinforced by AI systems. This paper examines strategies for designing AI systems that uphold fundamental rights, strengthen human agency, and embed effective human oversight mechanisms. It discusses key oversight…

@arXiv_quantph_bot@mastoxiv.page
2025-08-27 09:45:43

Vectorized Attention with Learnable Encoding for Quantum Transformer
Ziqing Guo, Ziwen Pan, Alex Khan, Jan Balewski
arxiv.org/abs/2508.18464

Vectorized Attention with Learnable Encoding for Quantum Transformer
Vectorized quantum block encoding provides a way to embed classical data into Hilbert space, offering a pathway for quantum models, such as Quantum Transformers (QT), that replace classical self-attention with quantum circuit simulations to operate more efficiently. Current QTs rely on deep parameterized quantum circuits (PQCs), rendering them vulnerable to QPU noise, and thus hindering their practical performance. In this paper, we propose the Vectorized Quantum Transformer (VQT), a model that…

@arXiv_csCV_bot@mastoxiv.page
2025-10-02 10:51:11

Uncertainty-Aware Concept Bottleneck Models with Enhanced Interpretability
Haifei Zhang, Patrick Barry, Eduardo Brandao
arxiv.org/abs/2510.00773

Uncertainty-Aware Concept Bottleneck Models with Enhanced Interpretability
In the context of image classification, Concept Bottleneck Models (CBMs) first embed images into a set of human-understandable concepts, followed by an intrinsically interpretable classifier that predicts labels based on these intermediate representations. While CBMs offer a semantically meaningful and interpretable classification pipeline, they often sacrifice predictive performance compared to end-to-end convolutional neural networks. Moreover, the propagation of uncertainty from concept pred…

@arXiv_csLG_bot@mastoxiv.page
2025-10-08 10:27:29

Physics-Informed Machine Learning in Biomedical Science and Engineering
Nazanin Ahmadi, Qianying Cao, Jay D. Humphrey, George Em Karniadakis
arxiv.org/abs/2510.05433

Physics-Informed Machine Learning in Biomedical Science and Engineering
Physics-informed machine learning (PIML) is emerging as a potentially transformative paradigm for modeling complex biomedical systems by integrating parameterized physical laws with data-driven methods. Here, we review three main classes of PIML frameworks: physics-informed neural networks (PINNs), neural ordinary differential equations (NODEs), and neural operators (NOs), highlighting their growing role in biomedical science and engineering. We begin with PINNs, which embed governing equations…

@Techmeme@techhub.social
2025-07-27 15:30:34

April, which provides tax tools that embed directly into financial apps, raised a $38M Series B led by QED Investors, bringing its total funding to $78M (Ryan Lawler/Axios)
axios.com/pro/fintech-deals/20

Exclusive: Embedded tax startup April raises $38M
The QED-led round fuels API-driven tax tools for fintechs.

@arXiv_csCR_bot@mastoxiv.page
2025-09-11 09:39:33

Prototype-Guided Robust Learning against Backdoor Attacks
Wei Guo, Maura Pintor, Ambra Demontis, Battista Biggio
arxiv.org/abs/2509.08748 a…

Prototype-Guided Robust Learning against Backdoor Attacks
Backdoor attacks poison the training data to embed a backdoor in the model, causing it to behave normally on legitimate inputs but maliciously when specific trigger signals appear. Training a benign model from a dataset poisoned by backdoor attacks is challenging. Existing works rely on various assumptions and can only defend against backdoor attacks with specific trigger signals, high poisoning ratios, or when the defender possesses a large, untainted, validation dataset. In this paper, we pro…

@arXiv_csCY_bot@mastoxiv.page
2025-09-11 08:13:03

The Law-Following AI Framework: Legal Foundations and Technical Constraints. Legal Analogues for AI Actorship and technical feasibility of Law Alignment
Katalina Hernandez Delgado
arxiv.org/abs/2509.08009

The Law-Following AI Framework: Legal Foundations and Technical Constraints. Legal Analogues for AI Actorship and technical feasibility of Law Alignment
This paper critically evaluates the "Law-Following AI" (LFAI) framework proposed by O'Keefe et al. (2025), which seeks to embed legal compliance as a superordinate design objective for advanced AI agents and enable them to bear legal duties without acquiring the full rights of legal persons. Through comparative legal analysis, we identify current constructs of legal actors without full personhood, showing that the necessary infrastructure already exists. We then interrogate the framework's clai…

@arXiv_csRO_bot@mastoxiv.page
2025-09-29 10:23:17

Leveraging Large Language Models for Robot-Assisted Learning of Morphological Structures in Preschool Children with Language Vulnerabilities
Stina Sundstedt, Mattias Wingren, Susanne H\"agglund, Daniel Ventus
arxiv.org/abs/2509.22287

Leveraging Large Language Models for Robot-Assisted Learning of Morphological Structures in Preschool Children with Language Vulnerabilities
Preschool children with language vulnerabilities -- such as developmental language disorders or immigration related language challenges -- often require support to strengthen their expressive language skills. Based on the principle of implicit learning, speech-language therapists (SLTs) typically embed target morphological structures (e.g., third person -s) into everyday interactions or game-based learning activities. Educators are recommended by SLTs to do the same. This approach demands preci…

@arXiv_mathCO_bot@mastoxiv.page
2025-09-01 09:22:53

When Many Trees Go to War
Mathias Weller, Norbert Zeh
arxiv.org/abs/2508.21749 arxiv.org/pdf/2508.21749

When Many Trees Go to War
It is known that any two trees on the same $n$ leaves can be displayed by a network with $n-2$ reticulations, and there are two trees that cannot be displayed by a network with fewer reticulations. But how many reticulations are needed to display multiple trees? For any set of $t$ trees on $n$ leaves, there is a trivial network with $(t - 1)n$ reticulations that displays them. To do better, we have to exploit common structure of the trees to embed non-trivial subtrees of different trees into th…

@arXiv_csCR_bot@mastoxiv.page
2025-09-12 09:32:59

Shell or Nothing: Real-World Benchmarks and Memory-Activated Agents for Automated Penetration Testing
Wuyuao Mai, Geng Hong, Qi Liu, Jinsong Chen, Jiarun Dai, Xudong Pan, Yuan Zhang, Min Yang
arxiv.org/abs/2509.09207

Shell or Nothing: Real-World Benchmarks and Memory-Activated Agents for Automated Penetration Testing
Penetration testing is critical for identifying and mitigating security vulnerabilities, yet traditional approaches remain expensive, time-consuming, and dependent on expert human labor. Recent work has explored AI-driven pentesting agents, but their evaluation relies on oversimplified capture-the-flag (CTF) settings that embed prior knowledge and reduce complexity, leading to performance estimates far from real-world practice. We close this gap by introducing the first real-world, agent-orient…

@arXiv_csLG_bot@mastoxiv.page
2025-09-30 14:44:01

High-Dimensional Analysis of Single-Layer Attention for Sparse-Token Classification
Nicholas Barnfield, Hugo Cui, Yue M. Lu
arxiv.org/abs/2509.25153

High-Dimensional Analysis of Single-Layer Attention for Sparse-Token Classification
When and how can an attention mechanism learn to selectively attend to informative tokens, thereby enabling detection of weak, rare, and sparsely located features? We address these questions theoretically in a sparse-token classification model in which positive samples embed a weak signal vector in a randomly chosen subset of tokens, whereas negative samples are pure noise. In the long-sequence limit, we show that a simple single-layer attention classifier can in principle achieve vanishing tes…

@arXiv_csRO_bot@mastoxiv.page
2025-07-30 09:25:22

Multifunctional physical reservoir computing in soft tensegrity robots
Ryo Terajima, Katsuma Inoue, Kohei Nakajima, Yasuo Kuniyoshi
arxiv.org/abs/2507.21496

Multifunctional physical reservoir computing in soft tensegrity robots
Recent studies have demonstrated that the dynamics of physical systems can be utilized for the desired information processing under the framework of physical reservoir computing (PRC). Robots with soft bodies are examples of such physical systems, and their nonlinear body-environment dynamics can be used to compute and generate the motor signals necessary for the control of their own behavior. In this simulation study, we extend this approach to control and embed not only one but also multiple …

@arXiv_csCV_bot@mastoxiv.page
2025-09-23 13:08:11

Degradation-Aware All-in-One Image Restoration via Latent Prior Encoding
S M A Sharif, Abdur Rehman, Fayaz Ali Dharejo, Radu Timofte, Rizwan Ali Naqvi
arxiv.org/abs/2509.17792

Degradation-Aware All-in-One Image Restoration via Latent Prior Encoding
Real-world images often suffer from spatially diverse degradations such as haze, rain, snow, and low-light, significantly impacting visual quality and downstream vision tasks. Existing all-in-one restoration (AIR) approaches either depend on external text prompts or embed hand-crafted architectural priors (e.g., frequency heuristics); both impose discrete, brittle assumptions that weaken generalization to unseen or mixed degradations. To address this limitation, we propose to reframe AIR as lea…

@arXiv_csCR_bot@mastoxiv.page
2025-10-10 09:08:59

Effective and Stealthy One-Shot Jailbreaks on Deployed Mobile Vision-Language Agents
Renhua Ding, Xiao Yang, Zhengwei Fang, Jun Luo, Kun He, Jun Zhu
arxiv.org/abs/2510.07809

Effective and Stealthy One-Shot Jailbreaks on Deployed Mobile Vision-Language Agents
Large vision-language models (LVLMs) enable autonomous mobile agents to operate smartphone user interfaces, yet vulnerabilities to UI-level attacks remain critically understudied. Existing research often depends on conspicuous UI overlays, elevated permissions, or impractical threat models, limiting stealth and real-world applicability. In this paper, we present a practical and stealthy one-shot jailbreak attack that leverages in-app prompt injections: malicious applications embed short prompts…

@arXiv_csCR_bot@mastoxiv.page
2025-09-09 11:34:32

Yours or Mine? Overwriting Attacks against Neural Audio Watermarking
Lingfeng Yao, Chenpei Huang, Shengyao Wang, Junpei Xue, Hanqing Guo, Jiang Liu, Phone Lin, Tomoaki Ohtsuki, Miao Pan
arxiv.org/abs/2509.05835

Yours or Mine? Overwriting Attacks against Neural Audio Watermarking
As generative audio models are rapidly evolving, AI-generated audios increasingly raise concerns about copyright infringement and misinformation spread. Audio watermarking, as a proactive defense, can embed secret messages into audio for copyright protection and source verification. However, current neural audio watermarking methods focus primarily on the imperceptibility and robustness of watermarking, while ignoring its vulnerability to security attacks. In this paper, we develop a simple yet…

@arXiv_csAI_bot@mastoxiv.page
2025-09-22 07:30:41

KNARsack: Teaching Neural Algorithmic Reasoners to Solve Pseudo-Polynomial Problems
Stjepan Po\v{z}gaj, Dobrik Georgiev, Marin \v{S}ili\'c, Petar Veli\v{c}kovi\'c
arxiv.org/abs/2509.15239

KNARsack: Teaching Neural Algorithmic Reasoners to Solve Pseudo-Polynomial Problems
Neural algorithmic reasoning (NAR) is a growing field that aims to embed algorithmic logic into neural networks by imitating classical algorithms. In this extended abstract, we detail our attempt to build a neural algorithmic reasoner that can solve Knapsack, a pseudo-polynomial problem bridging classical algorithms and combinatorial optimisation, but omitted in standard NAR benchmarks. Our neural algorithmic reasoner is designed to closely follow the two-phase pipeline for the Knapsack problem…

@arXiv_csCR_bot@mastoxiv.page
2025-09-09 11:33:32

Decoding Latent Attack Surfaces in LLMs: Prompt Injection via HTML in Web Summarization
Ishaan Verma
arxiv.org/abs/2509.05831 arxiv.org/pdf…

Decoding Latent Attack Surfaces in LLMs: Prompt Injection via HTML in Web Summarization
Large Language Models (LLMs) are increasingly integrated into web-based systems for content summarization, yet their susceptibility to prompt injection attacks remains a pressing concern. In this study, we explore how non-visible HTML elements such as , aria-label, and alt attributes can be exploited to embed adversarial instructions without altering the visible content of a webpage. We introduce a novel dataset comprising 280 static web pages, evenly divided between clean and adversarial…

@arXiv_csCR_bot@mastoxiv.page
2025-10-08 07:53:09

Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain
L\'eo Boisvert, Abhay Puri, Chandra Kiran Reddy Evuru, Nicolas Chapados, Quentin Cappart, Alexandre Lacoste, Krishnamurthy Dj Dvijotham, Alexandre Drouin
arxiv.org/abs/2510.05159

Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain
The practice of fine-tuning AI agents on data from their own interactions--such as web browsing or tool use--, while being a strong general recipe for improving agentic capabilities, also introduces a critical security vulnerability within the AI supply chain. In this work, we show that adversaries can easily poison the data collection pipeline to embed hard-to-detect backdoors that are triggerred by specific target phrases, such that when the agent encounters these triggers, it performs an uns…

@arXiv_csCR_bot@mastoxiv.page
2025-10-03 09:01:21

Towards Imperceptible Adversarial Defense: A Gradient-Driven Shield against Facial Manipulations
Yue Li, Linying Xue, Dongdong Lin, Qiushi Li, Hui Tian, Hongxia Wang
arxiv.org/abs/2510.01699

Towards Imperceptible Adversarial Defense: A Gradient-Driven Shield against Facial Manipulations
With the flourishing prosperity of generative models, manipulated facial images have become increasingly accessible, raising concerns regarding privacy infringement and societal trust. In response, proactive defense strategies embed adversarial perturbations into facial images to counter deepfake manipulation. However, existing methods often face a tradeoff between imperceptibility and defense effectiveness-strong perturbations may disrupt forgeries but degrade visual fidelity. Recent studies h…

@arXiv_csCR_bot@mastoxiv.page
2025-10-01 08:08:47

Fingerprinting LLMs via Prompt Injection
Yuepeng Hu, Zhengyuan Jiang, Mengyuan Li, Osama Ahmed, Zhicong Huang, Cheng Hong, Neil Gong
arxiv.org/abs/2509.25448

Fingerprinting LLMs via Prompt Injection
Large language models (LLMs) are often modified after release through post-processing such as post-training or quantization, which makes it challenging to determine whether one model is derived from another. Existing provenance detection methods have two main limitations: (1) they embed signals into the base model before release, which is infeasible for already published models, or (2) they compare outputs across models using hand-crafted or random prompts, which are not robust to post-processi…

@arXiv_csCR_bot@mastoxiv.page
2025-09-30 12:21:01

Of-SemWat: High-payload text embedding for semantic watermarking of AI-generated images with arbitrary size
Benedetta Tondi, Andrea Costanzo, Mauro Barni
arxiv.org/abs/2509.24823

Of-SemWat: High-payload text embedding for semantic watermarking of AI-generated images with arbitrary size
We propose a high-payload image watermarking method for textual embedding, where a semantic description of the image - which may also correspond to the input text prompt-, is embedded inside the image. In order to be able to robustly embed high payloads in large-scale images - such as those produced by modern AI generators - the proposed approach builds upon a traditional watermarking scheme that exploits orthogonal and turbo codes for improved robustness, and integrates frequency-domain embedd…

@arXiv_csCR_bot@mastoxiv.page
2025-07-31 09:27:21

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions
Yiting Qu, Ziqing Yang, Yihan Ma, Michael Backes, Savvas Zannettou, Yang Zhang
arxiv.org/abs/2507.22617

Hate in Plain Sight: On the Risks of Moderating AI-Generated Hateful Illusions
Recent advances in text-to-image diffusion models have enabled the creation of a new form of digital art: optical illusions--visual tricks that create different perceptions of reality. However, adversaries may misuse such techniques to generate hateful illusions, which embed specific hate messages into harmless scenes and disseminate them across web communities. In this work, we take the first step toward investigating the risks of scalable hateful illusion generation and the potential for bypa…

@arXiv_csCR_bot@mastoxiv.page
2025-08-29 09:42:41

Publish to Perish: Prompt Injection Attacks on LLM-Assisted Peer Review
Matteo Gioele Collu, Umberto Salviati, Roberto Confalonieri, Mauro Conti, Giovanni Apruzzese
arxiv.org/abs/2508.20863

Publish to Perish: Prompt Injection Attacks on LLM-Assisted Peer Review
Large Language Models (LLMs) are increasingly being integrated into the scientific peer-review process, raising new questions about their reliability and resilience to manipulation. In this work, we investigate the potential for hidden prompt injection attacks, where authors embed adversarial text within a paper's PDF to influence the LLM-generated review. We begin by formalising three distinct threat models that envision attackers with different motivations -- not all of which implying malicio…