Tootfinder

Selection-Based Vulnerabilities: Clean-Label Backdoor Attacks in Active Learning
Yuhan Zhi, Longtian Wang, Xiaofei Xie, Chao Shen, Qiang Hu, Xiaohong Guan
https://arxiv.org/abs/2508.05681

Selection-Based Vulnerabilities: Clean-Label Backdoor Attacks in Active Learning
Active learning(AL), which serves as the representative label-efficient learning paradigm, has been widely applied in resource-constrained scenarios. The achievement of AL is attributed to acquisition functions, which are designed for identifying the most important data to label. Despite this success, one question remains unanswered: is AL safe? In this work, we introduce ALA, a practical and the first framework to utilize the acquisition function as the poisoning attack surface to reveal the w…

slashdot_zoo: Slashdot Zoo friend-foe network (2009)
A network of interactions among users on Slashdot (slashdot.org), a technology news website. Users name each other as friends or foe. The friend label increases the scores of post, and the foe label decreases the score.
This network has 79120 nodes and 515397 edges.
Tags: Social, Online, Signed

Balancing Quality and Variation: Spam Filtering Distorts Data Label Distributions
Eve Fleisig, Matthias Orlikowski, Philipp Cimiano, Dan Klein
https://arxiv.org/abs/2509.08217 h…

Balancing Quality and Variation: Spam Filtering Distorts Data Label Distributions
For machine learning datasets to accurately represent diverse opinions in a population, they must preserve variation in data labels while filtering out spam or low-quality responses. How can we balance annotator reliability and representation? We empirically evaluate how a range of heuristics for annotator filtering affect the preservation of variation on subjective tasks. We find that these methods, designed for contexts in which variation from a single ground-truth label is considered noise, …

Label-Efficient Chest X-ray Diagnosis via Partial CLIP Adaptation
Heet Nitinkumar Dalsania
https://arxiv.org/abs/2507.07254 https://a…

Label-Efficient Chest X-ray Diagnosis via Partial CLIP Adaptation
Modern deep learning implementations for medical imaging usually rely on large labeled datasets. These datasets are often difficult to obtain due to privacy concerns, high costs, and even scarcity of cases. In this paper, a label-efficient strategy is proposed for chest X-ray diagnosis that seeks to reflect real-world hospital scenarios. The experiments use the NIH Chest X-ray14 dataset and a pre-trained CLIP ViT-B/32 model. The model is adapted via partial fine-tuning of its visual encoder and…

Label Inference Attacks against Federated Unlearning
Wei Wang, Xiangyun Tang, Yajie Wang, Yijing Lin, Tao Zhang, Meng Shen, Dusit Niyato, Liehuang Zhu
https://arxiv.org/abs/2508.06789

Label Inference Attacks against Federated Unlearning
Federated Unlearning (FU) has emerged as a promising solution to respond to the right to be forgotten of clients, by allowing clients to erase their data from global models without compromising model performance. Unfortunately, researchers find that the parameter variations of models induced by FU expose clients' data information, enabling attackers to infer the label of unlearning data, while label inference attacks against FU remain unexplored. In this paper, we introduce and analyze a new pr…

Everyday We Stray Further From God's Light

Bernd und Mela diskutieren Docker:
Bernd: „Und Du hast das Label allen Containern hinzugefügt?“
Mela: „Klar.“
Bernd: „Und alle Container neu gestartet?“
*grillenzirpen*
Mela: „Glaubst Du etwa, ich weiß nicht mehr, wie Systemadministration geht?“
Bernd: "Geisteswissenschaftlerin!"
*Poken des Todes*
#SzenenEinerEhe

Label-free microscope for rheological imaging of cells
Nicolas P. Mauranyapin, Marino Lara Alva, Daniel Yan, Zhe Yang, Jackson D. Lucas, Alex Terrasson, Michael A. Taylor, Rohan Teasdale, Yun Chen, Warwick P. Bowen
https://arxiv.org/abs/2507.07470

Label-free microscope for rheological imaging of cells
Many essential cellular functions depend on the viscoelastic properties of the cytoplasm. While techniques such as optical tweezers and atomic force microscopy can measure these properties, their reliance on localized probes prevents intracellular imaging and perturbs native cellular behaviour. Label-free microscopy offers a non-invasive alternative for observing intracellular dynamics. However, limitations in signal-to-noise ratio and imaging speed typically restrict analysis to diffusivity, l…

Acoustic Non-Stationarity Objective Assessment with Hard Label Criteria for Supervised Learning Models
Guilherme Zucatelli, Ricardo Barioni, Gabriela Dantas
https://arxiv.org/abs/2508.06405

Acoustic Non-Stationarity Objective Assessment with Hard Label Criteria for Supervised Learning Models
Objective non-stationarity measures are resource intensive and impose critical limitations for real-time processing solutions. In this paper, a novel Hard Label Criteria (HLC) algorithm is proposed to generate a global non-stationarity label for acoustic signals, enabling supervised learning strategies to be trained as stationarity estimators. The HLC is first evaluated on state-of-the-art general-purpose acoustic models, demonstrating that these models encode stationarity information. Furtherm…

discogs_label: Discogs label affiliations
Two bipartite networks of the affiliations between musical labels and either musical genres or musical "styles," as given in the discogs.com database. Edges represent that a label was involved in a production of a musical release of a given genre or given style. The date of this snapshot is uncertain.
This network has 270786 nodes and 4147665 edges.
Tags: Informational, Relatedness, Unweighted, Multigraph

What Cowboys OT Tyler Guyton must do in Year 2 to avoid the dreaded bust label

https://www.cbssports.com/nfl/news/what-cowboys-ot-tyler-guyt…

Partial Label Learning for Automated Theorem Proving
Zsolt Zombori, Bal\'azs Indruck
https://arxiv.org/abs/2507.03314 https://arx…

Partial Label Learning for Automated Theorem Proving
We formulate learning guided Automated Theorem Proving as Partial Label Learning, building the first bridge across these fields of research and providing a theoretical framework for dealing with alternative proofs during learning. We use the plCoP theorem prover to demonstrate that methods from the Partial Label Learning literature tend to increase the performance of learning assisted theorem provers.

Towards Unveiling Predictive Uncertainty Vulnerabilities in the Context of the Right to Be Forgotten
Wei Qian, Chenxu Zhao, Yangyi Li, Wenqian Ye, Mengdi Huai
https://arxiv.org/abs/2508.07458

Towards Unveiling Predictive Uncertainty Vulnerabilities in the Context of the Right to Be Forgotten
Currently, various uncertainty quantification methods have been proposed to provide certainty and probability estimates for deep learning models' label predictions. Meanwhile, with the growing demand for the right to be forgotten, machine unlearning has been extensively studied as a means to remove the impact of requested sensitive data from a pre-trained model without retraining the model from scratch. However, the vulnerabilities of such generated predictive uncertainties with regard to dedic…

dbpedia_recordlabel: DBpedia artist-label affiliations
Bipartite networks of the affiliations (contractual relations) between artists and the record labels under which they have performed, as extracted from Wikipedia by the DBpedia project.
This network has 186758 nodes and 233286 edges.
Tags: Economic, Employment, Unweighted
http…

OpenStore is scaling back its e-commerce aggregation efforts, closing nearly all of its 40 Shopify stores and rebranding under its Jack Archer menswear label (Annie Palmer/CNBC)
https://www.cnbc.com/2025/08/08/openstore-demise-endga…

OpenStore’s demise marks endgame for once-booming e-commerce aggregator market
OpenStore is rebranding under its Jack Archer menswear label after shuttering many of the Shopify storefronts it acquired and laying off staffers.

SLIP: Soft Label Mechanism and Key-Extraction-Guided CoT-based Defense Against Instruction Backdoor in APIs
Zhengxian Wu, Juan Wen, Wanli Peng, Haowei Chang, Yinghan Zhou, Yiming Xue
https://arxiv.org/abs/2508.06153

SLIP: Soft Label Mechanism and Key-Extraction-Guided CoT-based Defense Against Instruction Backdoor in APIs
With the development of customized large language model (LLM) agents, a new threat of black-box backdoor attacks has emerged, where malicious instructions are injected into hidden system prompts. These attacks easily bypass existing defenses that rely on white-box access, posing a serious security challenge. To address this, we propose SLIP, a Soft Label mechanism and key-extraction-guided CoT-based defense against Instruction backdoors in APIs. SLIP is designed based on two key insights. First…

3D Human Mesh Estimation from Single View RGBD
Ozhan Suat, Bedirhan Uguz, Batuhan Karagoz, Muhammed Can Keles, Emre Akbas
https://arxiv.org/abs/2508.08178 https://

3D Human Mesh Estimation from Single View RGBD
Despite significant progress in 3D human mesh estimation from RGB images; RGBD cameras, offering additional depth data, remain underutilized. In this paper, we present a method for accurate 3D human mesh estimation from a single RGBD view, leveraging the affordability and widespread adoption of RGBD cameras for real-world applications. A fully supervised approach for this problem, requires a dataset with RGBD image and 3D mesh label pairs. However, collecting such a dataset is costly and challe…

Shaping a Profession, Building a Community: A Practitioner-Led Investigation of Public Interest Technologists in Civil Society
Mallory Knodel, Mallika Balakrishnan, Lauren M. Chambers
https://arxiv.org/abs/2508.07230

Shaping a Profession, Building a Community: A Practitioner-Led Investigation of Public Interest Technologists in Civil Society
The label `public interest technology' (PIT) is growing in popularity among those seeking to use `tech for good' - especially among technical practitioners working in civil society and nonprofit organizations. PIT encompasses a broad range of sociotechnical work across professional domains and sectors; however, the trend remains understudied within sociotechnical research. This paper describes a mixed-methods study, designed and conducted by PIT practitioners at the Center for Democracy and Tec…

`aria-label` still does not (consistently) translate.
https://adrianroselli.com/2019/11/aria-label-does-not-translate.html#Update07
Unless you only translate never-hidden content, your `aria-label`s never change, your content is an arbitrary subs…

aria-label Does Not Translate
As of my 25 July 2025 update at the end of this post, aria-label auto-translation support is less spotty than when I first wrote this post, but still unreliable. It does, actually. Sometimes. One of the big risks of using ARIA to define text content is that it often gets…

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…

Ranking-based Fusion Algorithms for Extreme Multi-label Text Classification (XMTC)
Celso Fran\c{c}a, Gestefane Rabbi, Thiago Salles, Washington Cunha, Leonardo Rocha, Marcos Andr\'e Gon\c{c}alves
https://arxiv.org/abs/2507.03761

Ranking-based Fusion Algorithms for Extreme Multi-label Text Classification (XMTC)
In the context of Extreme Multi-label Text Classification (XMTC), where labels are assigned to text instances from a large label space, the long-tail distribution of labels presents a significant challenge. Labels can be broadly categorized into frequent, high-coverage \textbf{head labels} and infrequent, low-coverage \textbf{tail labels}, complicating the task of balancing effectiveness across all labels. To address this, combining predictions from multiple retrieval methods, such as sparse re…

Going from: "I wanted the computer to do this well-defined task, and it did it, and saved me some time because I can verify that what it did is aligned with my intent, and correct."

Going to: "I asked the computer random stuff and I'm 'obeying' without knowing why or how the output came about. I don't care much about understanding my own will anymore as long as the software says 'AI' on the label."

On Legendre Cordial Labeling of Complete Graphs
J. D. Andoyo
https://arxiv.org/abs/2509.09528 https://arxiv.org/pdf/2509.09528

On Legendre Cordial Labeling of Complete Graphs
Let $p$ be an odd prime. For a simple connected graph $G$ of order $n$, a bijective function $f:V(G)\to\{1,2,\ldots,n\}$ is said to be a Legendre cordial labeling modulo $p$ if the induced function $f_p^*:E(G)\to \{0,1\}$, defined by $f_p^* (uv)=0$ whenever $([f(u)+f(v)]/p)=-1$ or $f(u)+f(v)\equiv 0(\text{mod } p)$ and $f_p^* (uv)=1$ whenever $([f(u)+f(v)]/p)=1$, satisfies the condition $|e_{f_p^*}(0)-e_{f_p^*}(1)|\leq 1$ where $e_{f_p^*}(i)$ is the number of edges with label $i$ ($i=…

Periodic reminder to new followers or anyone just swinging by: I have high speed digital design / SI experience and lots of nice lab toys. Most folks can't afford this kind of stuff so I try to share the love.
If your project is open source or generally noncommercial / hobby in nature, there's NO CHARGE for a quick design review or some basic lab measurements. If you send me a board for characterization and want it back, all I ask is that you send me a prepaid label or reimburs…

This is the perfect expression of a theme that never shows up in mass media:
Police are running out of legitimate work and are willing to invent new work solely to keep their jobs.
Crime rates have dropped precipitously over the past few decades, with some spikes around the financial crisis and pandemic. In a sane society, we would have also been reducing police budgets and headcounts
(See also: #Freikorps

Filtered Approximate Nearest Neighbor Search: A Unified Benchmark and Systematic Experimental Study [Experiment, Analysis & Benchmark]
Jiayang Shi, Yuzheng Cai, Weiguo Zheng
https://arxiv.org/abs/2509.07789

Filtered Approximate Nearest Neighbor Search: A Unified Benchmark and Systematic Experimental Study [Experiment, Analysis & Benchmark]
For a given dataset $\mathcal{D}$ and structured label $f$, the goal of Filtered Approximate Nearest Neighbor Search (FANNS) algorithms is to find top-$k$ points closest to a query that satisfy label constraints, while ensuring both recall and QPS (Queries Per Second). In recent years, many FANNS algorithms have been proposed. However, the lack of a systematic investigation makes it difficult to understand their relative strengths and weaknesses. Additionally, we found that: (1) FANNS algorithm…

Nonparametric functional data classification and bandwidth selection in the presence of MNAR class variables
Majid Mojirsheibani
https://arxiv.org/abs/2509.08978 https://…

Nonparametric functional data classification and bandwidth selection in the presence of MNAR class variables
The problem of nonparametric functional data classification and bandwidth selection is considered when the response variable, also called the class label, might be missing but not at random (MNAR). This setup is broadly acknowledged to be more challenging than the simpler case of missing at random setup. With the focus on kernel methods, we develop nonparametric classification rules and also propose bandwidth selection procedures for the proposed estimators. To study the performance of the resu…

Ich bin ja ohnehin kein großer #SharePoint-Freund, aber es gibt eine Sache, die mich mit Abstand am meisten nervt: Die Zeit, die vergehen kann, bevor eine Einstellung auch wirklich in der Oberfläche wirksam wird.
Ich hab das Label für einen Filter angepasst und warte jetzt seit ~15 Minuten, dass das jetzt auch entsprechend angezeigt wird...

Crosslisted article(s) found for q-bio.NC. https://arxiv.org/list/q-bio.NC/new
[1/1]:
- ArtifactGen: Benchmarking WGAN-GP vs Diffusion for Label-Aware EEG Artifact Synthesis
Hritik Arasu, Faisal R Jahangiri

Global attractor of chemotaxis system with weak degradation and density-dependent motion
Lin Guo, Dan Li
https://arxiv.org/abs/2507.07554 https://

Global attractor of chemotaxis system with weak degradation and density-dependent motion
This paper investigates the following chemotaxis system featuring weak degradation and nonlinear motility functions \begin{equation}\label{Model1} \begin{cases} u_{t} = (γ(v)u)_{xx} + r - μu, & x \in [0,L],\ t > 0, v_{t} = v_{xx} - v + u, & x \in [0,L],\ t > 0, \end{cases} \end{equation} defined on the bounded interval $[0,L]$ with homogeneous Neumann boundary conditions. The motility function $γ(v)$ satisfies the regularity conditions $γ\in C^{2}[0,\infty)$ with $γ(v) > 0$ for…

Continuous scanning full-field OCT for fast volumetric imaging of multi-cellular aggregates
Charlie Kersuzan, Anirban Jana, Amaury Badon
https://arxiv.org/abs/2509.08101 https:/…

Continuous scanning full-field OCT for fast volumetric imaging of multi-cellular aggregates
Full-field optical coherence tomography (FF-OCT) offers label-free, high-resolution imaging of biological samples but remains limited by slow acquisition due to piezoelectric mirror modulation. We present a continuous-scanning FF-OCT method that eliminates piezoelectric displacement and synchronization by continuously translating the sample with a motorized stage while recording images on the fly. Depth-resolved information is retrieved via Fourier analysis of the temporal signal at each pixel.…

Pro & Contra: Sind die Energie-Label für iPhone & Co. hilfreich?
Smartphones und Tablets tragen in der EU seit Juni ein Ökodesign-Label. Sind die Angaben für iPhones und iPads ein Fortschritt oder Augenwischerei?

SCoRE: Streamlined Corpus-based Relation Extraction using Multi-Label Contrastive Learning and Bayesian kNN
Luca Mariotti, Veronica Guidetti, Federica Mandreoli
https://arxiv.org/abs/2507.06895

SCoRE: Streamlined Corpus-based Relation Extraction using Multi-Label Contrastive Learning and Bayesian kNN
The growing demand for efficient knowledge graph (KG) enrichment leveraging external corpora has intensified interest in relation extraction (RE), particularly under low-supervision settings. To address the need for adaptable and noise-resilient RE solutions that integrate seamlessly with pre-trained large language models (PLMs), we introduce SCoRE, a modular and cost-effective sentence-level RE system. SCoRE enables easy PLM switching, requires no finetuning, and adapts smoothly to diverse cor…

So I'm trying to make a Drum & Bass mix (first time ever wish me luck lol) and by misplacing one of the tracks I accidentally made this extended buildup thing and I think I cooked hard???

Eine ranzige Eckkneipe mit dem Label "Neueröffnung" wirft die Frage auf, wie viele Jahrzehnte genau eine Neueröffnung eigentlich her sein darf, oder ob Eckkneipen bei Neueröffnungen auch bewusst im ranzigen Zustand belassen bzw. möglicherweise sogar gezielt im ranzigen Schick neu gestaltet werden.

A novel approach for classifying Monoamine Neurotransmitters by applying Machine Learning on UV plasmonic-engineered Auto Fluorescence Time Decay Series (AFTDS)
Mohammad Mohammadi, Sima Najafzadehkhoei, George Vega Yon, Yunshan Wang
https://arxiv.org/abs/2507.07227

A novel approach for classifying Monoamine Neurotransmitters by applying Machine Learning on UV plasmonic-engineered Auto Fluorescence Time Decay Series (AFTDS)
This study introduces a hybrid approach integrating advanced plasmonic nanomaterials and machine learning (ML) for high-precision biomolecule detection. We leverage aluminum concave nanocubes (AlCNCs) as an innovative plasmonic substrate to enhance the native fluorescence of neurotransmitters, including dopamine (DA), norepinephrine (NE), and 3,4-Dihydroxyphenylacetic acid (DOPAC). AlCNCs amplify weak fluorescence signals, enabling probe-free, label-free detection and differentiation of these m…

Improving AI-Based Canine Heart Disease Diagnosis with Expert-Consensus Auscultation Labeling
Pinar Bisgin, Tom Strube, Niklas Tschorn, Michael Pantf\"order, Maximilian Fecke, Ingrid Ljungvall, Jens H\"aggstr\"om, Gerhard Wess, Christoph Schummer, Sven Meister, Falk M. Howar
https://arxiv.org/abs/2507.05950…

Improving AI-Based Canine Heart Disease Diagnosis with Expert-Consensus Auscultation Labeling
Noisy labels pose significant challenges for AI model training in veterinary medicine. This study examines expert assessment ambiguity in canine auscultation data, highlights the negative impact of label noise on classification performance, and introduces methods for label noise reduction. To evaluate whether label noise can be minimized by incorporating multiple expert opinions, a dataset of 140 heart sound recordings (HSR) was annotated regarding the intensity of holosystolic heart murmurs ca…

"Beschriftungen müssen immer so gestaltet sein, dass man möglichst schnell erfassen kann worum es geht"
Me: Say no more.

Quantum Spectral Clustering: Comparing Parameterized and Neuromorphic Quantum Kernels
Donovan Slabbert, Dean Brand, Francesco Petruccione
https://arxiv.org/abs/2507.07018

Quantum Spectral Clustering: Comparing Parameterized and Neuromorphic Quantum Kernels
We compare a parameterized quantum kernel (pQK) with a quantum leaky integrate-and-fire (QLIF) neuromorphic computing approach that employs either the Victor-Purpura or van Rossum kernel in a spectral clustering task, as well as the classical radial basis function (RBF) kernel. Performance evaluation includes label-based classification and clustering metrics, as well as optimal number of clusters predictions for each dataset based on an elbow-like curve as is typically used in $K$-means cluster…

DART: Dual Adaptive Refinement Transfer for Open-Vocabulary Multi-Label Recognition
Haijing Liu, Tao Pu, Hefeng Wu, Keze Wang, Liang Lin
https://arxiv.org/abs/2508.05585 https:/…

DART: Dual Adaptive Refinement Transfer for Open-Vocabulary Multi-Label Recognition
Open-Vocabulary Multi-Label Recognition (OV-MLR) aims to identify multiple seen and unseen object categories within an image, requiring both precise intra-class localization to pinpoint objects and effective inter-class reasoning to model complex category dependencies. While Vision-Language Pre-training (VLP) models offer a strong open-vocabulary foundation, they often struggle with fine-grained localization under weak supervision and typically fail to explicitly leverage structured relational …

DINA: A Dual Defense Framework Against Internal Noise and External Attacks in Natural Language Processing
Ko-Wei Chuang, Hen-Hsen Huang, Tsai-Yen Li
https://arxiv.org/abs/2508.05671

DINA: A Dual Defense Framework Against Internal Noise and External Attacks in Natural Language Processing
As large language models (LLMs) and generative AI become increasingly integrated into customer service and moderation applications, adversarial threats emerge from both external manipulations and internal label corruption. In this work, we identify and systematically address these dual adversarial threats by introducing DINA (Dual Defense Against Internal Noise and Adversarial Attacks), a novel unified framework tailored specifically for NLP. Our approach adapts advanced noisy-label learning me…

Automated Label Placement on Maps via Large Language Models
Harry Shomer, Jiejun Xu
https://arxiv.org/abs/2507.22952 https://arxiv.org/pdf/2507.22952

Automated Label Placement on Maps via Large Language Models
Label placement is a critical aspect of map design, serving as a form of spatial annotation that directly impacts clarity and interpretability. Despite its importance, label placement remains largely manual and difficult to scale, as existing automated systems struggle to integrate cartographic conventions, adapt to context, or interpret labeling instructions. In this work, we introduce a new paradigm for automatic label placement (ALP) that formulates the task as a data editing problem and lev…

discogs_label: Discogs label affiliations
Two bipartite networks of the affiliations between musical labels and either musical genres or musical "styles," as given in the discogs.com database. Edges represent that a label was involved in a production of a musical release of a given genre or given style. The date of this snapshot is uncertain.
This network has 270786 nodes and 4147665 edges.
Tags: Informational, Relatedness, Unweighted, Multigraph

Designing Parallel Algorithms for Community Detection using Arachne
Fuhuan Li, Zhihui Du, David A. Bader
https://arxiv.org/abs/2507.06471 https://

Designing Parallel Algorithms for Community Detection using Arachne
The rise of graph data in various fields calls for efficient and scalable community detection algorithms. In this paper, we present parallel implementations of two widely used algorithms: Label Propagation and Louvain, specifically designed to leverage the capabilities of Arachne which is a Python-accessible, open-source framework for large-scale graph analysis. Our implementations achieve substantial speedups over existing Python-based tools like NetworkX and igraph, which lack efficient paral…

Benchmarking Uncertainty and its Disentanglement in multi-label Chest X-Ray Classification
Simon Baur, Wojciech Samek, Jackie Ma
https://arxiv.org/abs/2508.04457 https://…

Benchmarking Uncertainty and its Disentanglement in multi-label Chest X-Ray Classification
Reliable uncertainty quantification is crucial for trustworthy decision-making and the deployment of AI models in medical imaging. While prior work has explored the ability of neural networks to quantify predictive, epistemic, and aleatoric uncertainties using an information-theoretical approach in synthetic or well defined data settings like natural image classification, its applicability to real life medical diagnosis tasks remains underexplored. In this study, we provide an extensive uncerta…

🇺🇦 #NowPlaying on KEXP's #StreetSounds
Ivan Ave prod. Mndsgn:
🎵 Find Me
#IvanAveprodMndsgn
https://jakartarecords-label.bandcamp.com/track/find-me-prod-mndsgn

So, el trombino anaranjado wants to use the US military to do law enforcement against anything that he labels as a terrorist organization.
Apart from the violation of US Federal law and the enormous power that can come from aiming the US military at anything el-presidente slaps a label on, we certainly have a very large, well funded terrorist organization in the US: ICE. It's leaders - named Miller and Noem - should be taken into custody immediately.
Consider if el-cheeto we…

Beyond Single Labels: Improving Conversational Recommendation through LLM-Powered Data Augmentation
Haozhe Xu, Xiaohua Wang, Changze Lv, Xiaoqing Zheng
https://arxiv.org/abs/2508.05657

Beyond Single Labels: Improving Conversational Recommendation through LLM-Powered Data Augmentation
Conversational recommender systems (CRSs) enhance recommendation quality by engaging users in multi-turn dialogues, capturing nuanced preferences through natural language interactions. However, these systems often face the false negative issue, where items that a user might like are incorrectly labeled as negative during training, leading to suboptimal recommendations.Expanding the label set through data augmentation presents an intuitive solution but faces the challenge of balancing two key as…

Interesting early version release of iconclass-vlm, a specialised small vision language model that automatically generates ICONCLASS metadata for cultural heritage collections by Daniel van Strien
iconclass-vlm: https://huggingface.co/davanstrien/iconclass-vlm
model evaluatio…

Dieses Projekt von Phew, Erika Kobayashi und Dieter Moebius, veranlasst durch Fukushima 2011, war mir bisher entgangen. Das Album, das 2012 unter einem anderen Titel erschienen war, wurde nun vom Label Bureau B als "Radium Girls" wiederaufgelegt,, aus chronologisch naheliegendem Grund. #sound

#Requiescat For John Whitson, founder of Holy Mountain, who released essential albums by Six Organs of Admittance, Davis Redford Triad, Wooden Shjips, Zdrastvootie, Residual Echoes, OM, Daniel Higgs, Mammatus, and so many others. Here’s an interview from 2018.

Astroboter Asks: John Whitson (Holy Mountain Records // USA)
This interview with record label owner John Whitson from Holy Mountain Records is part of my ongoing series “Astroboter Asks”, in which I interview artists, creators and people who inspire me. Enjoy…

discogs_label: Discogs label affiliations
Two bipartite networks of the affiliations between musical labels and either musical genres or musical "styles," as given in the discogs.com database. Edges represent that a label was involved in a production of a musical release of a given genre or given style. The date of this snapshot is uncertain.
This network has 270786 nodes and 4147665 edges.
Tags: Informational, Relatedness, Unweighted, Multigraph

More #sliceoflife -- I took this water bottle after nobody claimed it after 24 hours; I think people might have been afraid it was contaminated with PFAS or something; it's made of metal and coated with enamel, but when I opened it I used my hand to waff smells towards my nose like I would in a chemical lab -- the square in the background is poyo_party's Lana from Pokémon Sun and …

Archaic Podcast 572 - Dave Black
Bio.
Dave black is a Spanish electronic musician and dj specializing in techno. His sound is deeply influenced by both past and present electronic music, blending hypnotic rhythms with raw energy. throughout his career, he has been affiliated with renowned labels such as Illegal Alien, IuminalRecordings, Involve, Utopia, and his own label, Philia Records.
[…]

From Few-Label to Zero-Label: An Approach for Cross-System Log-Based Anomaly Detection with Meta-Learning
Xinlong Zhao, Tong Jia, Minghua He, Yihan Wu, Ying Li, Gang Huang
https://arxiv.org/abs/2507.19806

From Few-Label to Zero-Label: An Approach for Cross-System Log-Based Anomaly Detection with Meta-Learning
Log anomaly detection plays a critical role in ensuring the stability and reliability of software systems. However, existing approaches rely on large amounts of labeled log data, which poses significant challenges in real-world applications. To address this issue, cross-system transfer has been identified as a key research direction. State-of-the-art cross-system approaches achieve promising performance with only a few labels from the target system. However, their reliance on labeled target log…

Nondegeneracy of positive solutions for critical Hartree equation on Heisenberg group and it's applications
Minbo Yang, Shuijin Zhang
https://arxiv.org/abs/2508.07719 https:…

Nondegeneracy of positive solutions for critical Hartree equation on Heisenberg group and it's applications
We study the uniqueness and nondegeneracy of positive bubble solutions for the generalized energy-critical Hartree equation on the Heisenberg group $\mathbb{H}^{n}$, \begin{equation}\label{0.1} -Δ_{\mathbb{H}}u=\left(\int_{\mathbb{H}^{n}}\frac{|u(η)|^{Q^{\ast}_μ}}{|η^{-1}ξ|^μ}\mathrm{d}η\right)|u|^{Q^{\ast}_μ-2}u,~~~ξ,η\in\mathbb{H}^{n}, \end{equation} where $Δ_{\mathbb{H}}$ represents the Kohn Laplacian, $u(η)$ is a real-valued function, $Q=2n+2$ is …

I was told that `aria-label` now always auto-translates in browsers. The evidence was meh. So I tested and updated:
https://adrianroselli.com/2019/11/aria-label-does-not-translate.html#Update07
Still nope.
Safari only knows 21 la…

aria-label Does Not Translate
As of my 25 July 2025 update at the end of this post, aria-label auto-translation support is less spotty than when I first wrote this post, but still unreliable. It does, actually. Sometimes. One of the big risks of using ARIA to define text content is that it often gets…

revisiting my old fav combi, and like when it comes to describing the bond they have to each other, one is "not family nor friends nor companions, but something else entirely that is special", and the other is "it's family and friends and companions, all in one that it becomes something special" and I love this... idk diametry? but what they're saying is basically the same thing, even if it feels like opposites. both refuse to use an existing label. I don't know if this makes sense to anyone else, I like this kind of thing.

MCANet: A Multi-Scale Class-Specific Attention Network for Multi-Label Post-Hurricane Damage Assessment using UAV Imagery
Zhangding Liu, Neda Mohammadi, John E. Taylor
https://arxiv.org/abs/2509.04757 …

MCANet: A Multi-Scale Class-Specific Attention Network for Multi-Label Post-Hurricane Damage Assessment using UAV Imagery
Rapid and accurate post-hurricane damage assessment is vital for disaster response and recovery. Yet existing CNN-based methods struggle to capture multi-scale spatial features and to distinguish visually similar or co-occurring damage types. To address these issues, we propose MCANet, a multi-label classification framework that learns multi-scale representations and adaptively attends to spatially relevant regions for each damage category. MCANet employs a Res2Net-based hierarchical backbone t…

Do LLMs Adhere to Label Definitions? Examining Their Receptivity to External Label Definitions
Seyedali Mohammadi, Bhaskara Hanuma Vedula, Hemank Lamba, Edward Raff, Ponnurangam Kumaraguru, Francis Ferraro, Manas Gaur
https://arxiv.org/abs/2509.02452

Do LLMs Adhere to Label Definitions? Examining Their Receptivity to External Label Definitions
Do LLMs genuinely incorporate external definitions, or do they primarily rely on their parametric knowledge? To address these questions, we conduct controlled experiments across multiple explanation benchmark datasets (general and domain-specific) and label definition conditions, including expert-curated, LLM-generated, perturbed, and swapped definitions. Our results reveal that while explicit label definitions can enhance accuracy and explainability, their integration into an LLM's task-solvin…

Label-Free Whole Slide Virtual Multi-Staining Using Dual-Excitation Photon Absorption Remote Sensing Microscopy
James E. D. Tweel, Benjamin R. Ecclestone, James A. Tummon Simmons, Parsin Haji Reza
https://arxiv.org/abs/2509.05085

Label-Free Whole Slide Virtual Multi-Staining Using Dual-Excitation Photon Absorption Remote Sensing Microscopy
Histochemical staining is essential for visualizing tissue architecture and cellular morphology but is destructive and limited by the availability of tissue for multiple stains. Virtual staining with label-free microscopy offers a non-destructive alternative, enabling multiple stains to be generated from the same section while reducing stain variability and preserving tissue for downstream assays. Here, a new dual-excitation Photon Absorption Remote Sensing (PARS) system is presented, represent…

Learning from Majority Label: A Novel Problem in Multi-class Multiple-Instance Learning
Shiku Kaito, Shinnosuke Matsuo, Daiki Suehiro, Ryoma Bise
https://arxiv.org/abs/2509.04023

Learning from Majority Label: A Novel Problem in Multi-class Multiple-Instance Learning
The paper proposes a novel multi-class Multiple-Instance Learning (MIL) problem called Learning from Majority Label (LML). In LML, the majority class of instances in a bag is assigned as the bag-level label. The goal of LML is to train a classification model that estimates the class of each instance using the majority label. This problem is valuable in a variety of applications, including pathology image segmentation, political voting prediction, customer sentiment analysis, and environmental m…

Reliable Programmatic Weak Supervision with Confidence Intervals for Label Probabilities
Ver\'onica \'Alvarez, Santiago Mazuelas, Steven An, Sanjoy Dasgupta
https://arxiv.org/abs/2508.03896

Reliable Programmatic Weak Supervision with Confidence Intervals for Label Probabilities
The accurate labeling of datasets is often both costly and time-consuming. Given an unlabeled dataset, programmatic weak supervision obtains probabilistic predictions for the labels by leveraging multiple weak labeling functions (LFs) that provide rough guesses for labels. Weak LFs commonly provide guesses with assorted types and unknown interdependences that can result in unreliable predictions. Furthermore, existing techniques for programmatic weak supervision cannot provide assessments for t…

Scalable Controllable Accented TTS
Henry Li Xinyuan, Zexin Cai, Ashi Garg, Kevin Duh, Leibny Paola Garc\'ia-Perera, Sanjeev Khudanpur, Nicholas Andrews, Matthew Wiesner
https://arxiv.org/abs/2508.07426

Scalable Controllable Accented TTS
We tackle the challenge of scaling accented TTS systems, expanding their capabilities to include much larger amounts of training data and a wider variety of accent labels, even for accents that are poorly represented or unlabeled in traditional TTS datasets. To achieve this, we employ two strategies: 1. Accent label discovery via a speech geolocation model, which automatically infers accent labels from raw speech data without relying solely on human annotation; 2. Timbre augmentation through kN…

A Novel Active Learning Approach to Label One Million Unknown Malware Variants
Ahmed Bensaoud, Jugal Kalita
https://arxiv.org/abs/2507.02959 https://

A Novel Active Learning Approach to Label One Million Unknown Malware Variants
Active learning for classification seeks to reduce the cost of labeling samples by finding unlabeled examples about which the current model is least certain and sending them to an annotator/expert to label. Bayesian theory can provide a probabilistic view of deep neural network models by asserting a prior distribution over model parameters and estimating the uncertainties by posterior distribution over these parameters. This paper proposes two novel active learning approaches to label one milli…

Exploring AR Label Placements in Visually Cluttered Scenarios
Ji Hwan Park, Braden Roper, Amirhossein Arezoumand, Tien Tran
https://arxiv.org/abs/2507.00198

Exploring AR Label Placements in Visually Cluttered Scenarios
We investigate methods for placing labels in AR environments that have visually cluttered scenes. As the number of items increases in a scene within the user' FOV, it is challenging to effectively place labels based on existing label placement guidelines. To address this issue, we implemented three label placement techniques for in-view objects for AR applications. We specifically target a scenario, where various items of different types are scattered within the user's field of view, and multip…

discogs_label: Discogs label affiliations
Two bipartite networks of the affiliations between musical labels and either musical genres or musical "styles," as given in the discogs.com database. Edges represent that a label was involved in a production of a musical release of a given genre or given style. The date of this snapshot is uncertain.
This network has 270786 nodes and 4147665 edges.
Tags: Informational, Relatedness, Unweighted, Multigraph

Survival analysis under label shift
Yuxiang Zong, Yanyuan Ma, Ingrid Van Keilegom
https://arxiv.org/abs/2506.21190 https://arxiv.org/…

Survival analysis under label shift
Let P represent the source population with complete data, containing covariate $\mathbf{Z}$ and response $T$, and Q the target population, where only the covariate $\mathbf{Z}$ is available. We consider a setting with both label shift and label censoring. Label shift assumes that the marginal distribution of $T$ differs between $P$ and $Q$, while the conditional distribution of $\mathbf{Z}$ given $T$ remains the same. Label censoring refers to the case where the response $T$ in $P$ is subject t…

Eagles players bristle 'defending champions' label https://www.espn.com/nfl/story/_/id/45805459/eagles-focused-2025-bristle-defending-champions-label

Optimizing Small Transformer-Based Language Models for Multi-Label Sentiment Analysis in Short Texts
Julius Neumann, Robert Lange, Yuni Susanti, Michael F\"arber
https://arxiv.org/abs/2509.04982

Optimizing Small Transformer-Based Language Models for Multi-Label Sentiment Analysis in Short Texts
Sentiment classification in short text datasets faces significant challenges such as class imbalance, limited training samples, and the inherent subjectivity of sentiment labels -- issues that are further intensified by the limited context in short texts. These factors make it difficult to resolve ambiguity and exacerbate data sparsity, hindering effective learning. In this paper, we evaluate the effectiveness of small Transformer-based models (i.e., BERT and RoBERTa, with fewer than 1 billion …

TigAug: Data Augmentation for Testing Traffic Light Detection in Autonomous Driving Systems
You Lu, Dingji Wang, Kaifeng Huang, Bihuan Chen, Xin Peng
https://arxiv.org/abs/2507.05932

TigAug: Data Augmentation for Testing Traffic Light Detection in Autonomous Driving Systems
Autonomous vehicle technology has been developed in the last decades with recent advances in sensing and computing technology. There is an urgent need to ensure the reliability and robustness of autonomous driving systems (ADSs). Despite the recent achievements in testing various ADS modules, little attention has been paid on the automated testing of traffic light detection models in ADSs. A common practice is to manually collect and label traffic light data. However, it is labor-intensive, and…

Federated Learning with Heterogeneous and Private Label Sets
Adam Breitholtz, Edvin Listo Zec, Fredrik D. Johansson
https://arxiv.org/abs/2508.18774 https://

Federated Learning with Heterogeneous and Private Label Sets
Although common in real-world applications, heterogeneous client label sets are rarely investigated in federated learning (FL). Furthermore, in the cases they are, clients are assumed to be willing to share their entire label sets with other clients. Federated learning with private label sets, shared only with the central server, adds further constraints on learning algorithms and is, in general, a more difficult problem to solve. In this work, we study the effects of label set heterogeneity on…

Multi-modal Representations for Fine-grained Multi-label Critical View of Safety Recognition
Britty Baby, Vinkle Srivastav, Pooja P. Jain, Kun Yuan, Pietro Mascagni, Nicolas Padoy
https://arxiv.org/abs/2507.05007

Multi-modal Representations for Fine-grained Multi-label Critical View of Safety Recognition
The Critical View of Safety (CVS) is crucial for safe laparoscopic cholecystectomy, yet assessing CVS criteria remains a complex and challenging task, even for experts. Traditional models for CVS recognition depend on vision-only models learning with costly, labor-intensive spatial annotations. This study investigates how text can be harnessed as a powerful tool for both training and inference in multi-modal surgical foundation models to automate CVS recognition. Unlike many existing multi-moda…

discogs_label: Discogs label affiliations
Two bipartite networks of the affiliations between musical labels and either musical genres or musical "styles," as given in the discogs.com database. Edges represent that a label was involved in a production of a musical release of a given genre or given style. The date of this snapshot is uncertain.
This network has 270786 nodes and 4147665 edges.
Tags: Informational, Relatedness, Unweighted, Multigraph

Revisiting Active Learning under (Human) Label Variation
Cornelia Gruber, Helen Alber, Bernd Bischl, G\"oran Kauermann, Barbara Plank, Matthias A{\ss}enmacher
https://arxiv.org/abs/2507.02593

Revisiting Active Learning under (Human) Label Variation
Access to high-quality labeled data remains a limiting factor in applied supervised learning. While label variation (LV), i.e., differing labels for the same instance, is common, especially in natural language processing, annotation frameworks often still rest on the assumption of a single ground truth. This overlooks human label variation (HLV), the occurrence of plausible differences in annotations, as an informative signal. Similarly, active learning (AL), a popular approach to optimizing th…

From Coarse to Fine-Grained Emotion Annotation: An Immediate Recall Paradigm with Validation through Physiological Evidence and Recognition Performance
Hao Tang, Songyun Xie, Xinzhou Xie, Can Liao, Xin Zhang, Bohan Li, Zhongyu Tian, Dalu Zheng
https://arxiv.org/abs/2507.02350

From Coarse to Fine-Grained Emotion Annotation: An Immediate Recall Paradigm with Validation through Physiological Evidence and Recognition Performance
Traditional video-induced emotion physiological datasets often use whole-trial annotation, assigning a single emotion label to all data collected during an entire trial. This coarse-grained annotation approach misaligns with the dynamic and temporally localized nature of emotional responses as they unfold with video narratives, introducing label noise that limits emotion recognition algorithm evaluation and performance. To solve the label noise problem caused by coarse-grained annotation, we pr…

discogs_label: Discogs label affiliations
Two bipartite networks of the affiliations between musical labels and either musical genres or musical "styles," as given in the discogs.com database. Edges represent that a label was involved in a production of a musical release of a given genre or given style. The date of this snapshot is uncertain.
This network has 270786 nodes and 4147665 edges.
Tags: Informational, Relatedness, Unweighted, Multigraph

A standardized file format and open-source analysis framework for Brillouin microscopy data
Carlo Bevilacqua, Sebastian Hambura, Pierre Bouvet, Salvatore La Cavera III, Kareem Elsayad, Robert Prevedel
https://arxiv.org/abs/2509.07566

A standardized file format and open-source analysis framework for Brillouin microscopy data
Brillouin microscopy is rapidly emerging as a powerful technique for imaging the mechanical properties of biological specimens in a label-free, non-contact manner. We present a standardized file format and open-source tools to facilitate the uptake and analysis of Brillouin microscopy related data and to unify this growing field.

Reason to Rote: Rethinking Memorization in Reasoning
Yupei Du, Philipp Mondorf, Silvia Casola, Yuekun Yao, Robert Litschko, Barbara Plank
https://arxiv.org/abs/2507.04782

Reason to Rote: Rethinking Memorization in Reasoning
Large language models readily memorize arbitrary training instances, such as label noise, yet they perform strikingly well on reasoning tasks. In this work, we investigate how language models memorize label noise, and why such memorization in many cases does not heavily affect generalizable reasoning capabilities. Using two controllable synthetic reasoning datasets with noisy labels, four-digit addition (FDA) and two-hop relational reasoning (THR), we discover a reliance of memorization on gene…

Learning to Detect Label Errors by Making Them: A Method for Segmentation and Object Detection Datasets
Sarina Penquitt, Tobias Riedlinger, Timo Heller, Markus Reischl, Matthias Rottmann
https://arxiv.org/abs/2508.17930

Learning to Detect Label Errors by Making Them: A Method for Segmentation and Object Detection Datasets
Recently, detection of label errors and improvement of label quality in datasets for supervised learning tasks has become an increasingly important goal in both research and industry. The consequences of incorrectly annotated data include reduced model performance, biased benchmark results, and lower overall accuracy. Current state-of-the-art label error detection methods often focus on a single computer vision task and, consequently, a specific type of dataset, containing, for example, either …

AI for the Routine, Humans for the Complex: Accuracy-Driven Data Labelling with Mixed Integer Linear Programming
Mohammad Hossein Amini, Mehrdad Sabetzadeh, Shiva Nejati
https://arxiv.org/abs/2507.04990

AI for the Routine, Humans for the Complex: Accuracy-Driven Data Labelling with Mixed Integer Linear Programming
The scarcity of accurately labelled data remains a major challenge in deep learning (DL). Many DL approaches rely on semi-supervised methods, which focus on constructing large datasets that require only a minimal amount of human-labelled data. Since DL training algorithms can tolerate moderate label noise, it has generally been acceptable for the accuracy of labels in large training datasets to fall well short of a perfect 100%. However, when it comes to testing DL models, achieving high label …

Circulating tumor cell detection in cancer patients using in-flow deep learning holography
Kevin Mallery, Nathaniel R. Bristow, Nicholas Heller, Yash Travadi, Ali Arafa, Kaylee Kamalanathan, Catalina Galeano-Garces, Mahdi Ahmadi, Grant Schaap, Alexa Hesch, Olivia Hedeen, Zikora Izuora, Joel Hapke, Jeffrey Miller, Arjun Viswanathan, Ivo Babris, Songyi Bae, Tuan Le, Tony Clacko, Emmanuel S. Antonarakis, Badrinath R. Konety, Justin M. Drake, Jiarong Hong

Circulating tumor cell detection in cancer patients using in-flow deep learning holography
Circulating tumor cells (CTCs) are cancer cells found in the bloodstream that serve as biomarkers for early cancer detection, prognostication, and disease monitoring. However, CTC detection remains challenging due to low cell abundance and heterogeneity. Digital holographic microscopy (DHM) offers a promising, label-free method for high-throughput CTC identification by capturing superior morphological information compared to traditional imaging methods, while remaining compatible with in-flow d…

UniMLR: Modeling Implicit Class Significance for Multi-Label Ranking
V. Bugra Yesilkaynak, Emine Dari, Alican Mertan, Gozde Unal
https://arxiv.org/abs/2508.21772 https://…

UniMLR: Modeling Implicit Class Significance for Multi-Label Ranking
Existing multi-label ranking (MLR) frameworks only exploit information deduced from the bipartition of labels into positive and negative sets. Therefore, they do not benefit from ranking among positive labels, which is the novel MLR approach we introduce in this paper. We propose UniMLR, a new MLR paradigm that models implicit class relevance/significance values as probability distributions using the ranking among positive labels, rather than treating them as equally important. This approach un…

discogs_label: Discogs label affiliations
Two bipartite networks of the affiliations between musical labels and either musical genres or musical "styles," as given in the discogs.com database. Edges represent that a label was involved in a production of a musical release of a given genre or given style. The date of this snapshot is uncertain.
This network has 270786 nodes and 4147665 edges.
Tags: Informational, Relatedness, Unweighted, Multigraph

Noisy Label Refinement with Semantically Reliable Synthetic Images
Yingxuan Li, Jiafeng Mao, Yusuke Matsui
https://arxiv.org/abs/2509.04298 https://arxiv.o…

Noisy Label Refinement with Semantically Reliable Synthetic Images
Semantic noise in image classification datasets, where visually similar categories are frequently mislabeled, poses a significant challenge to conventional supervised learning approaches. In this paper, we explore the potential of using synthetic images generated by advanced text-to-image models to address this issue. Although these high-quality synthetic images come with reliable labels, their direct application in training is limited by domain gaps and diversity constraints. Unlike convention…

Hierarchical Multi-Label Contrastive Learning for Protein-Protein Interaction Prediction Across Organisms
Shiyi Liu, Buwen Liang, Yuetong Fang, Zixuan Jiang, Renjing Xu
https://arxiv.org/abs/2507.02724

Hierarchical Multi-Label Contrastive Learning for Protein-Protein Interaction Prediction Across Organisms
Recent advances in AI for science have highlighted the power of contrastive learning in bridging heterogeneous biological data modalities. Building on this paradigm, we propose HIPPO (HIerarchical Protein-Protein interaction prediction across Organisms), a hierarchical contrastive framework for protein-protein interaction(PPI) prediction, where protein sequences and their hierarchical attributes are aligned through multi-tiered biological representation matching. The proposed approach incorpora…

Will Annotators Disagree? Identifying Subjectivity in Value-Laden Arguments
Amir Homayounirad, Enrico Liscio, Tong Wang, Catholijn M. Jonker, Luciano C. Siebert
https://arxiv.org/abs/2509.06704

Will Annotators Disagree? Identifying Subjectivity in Value-Laden Arguments
Aggregating multiple annotations into a single ground truth label may hide valuable insights into annotator disagreement, particularly in tasks where subjectivity plays a crucial role. In this work, we explore methods for identifying subjectivity in recognizing the human values that motivate arguments. We evaluate two main approaches: inferring subjectivity through value prediction vs. directly identifying subjectivity. Our experiments show that direct subjectivity identification significantly …

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

Should We Always Train Models on Fine-Grained Classes?
Davide Pirovano, Federico Milanesio, Michele Caselle, Piero Fariselli, Matteo Osella
https://arxiv.org/abs/2509.05130 http…

Should We Always Train Models on Fine-Grained Classes?
In classification problems, models must predict a class label based on the input data features. However, class labels are organized hierarchically in many datasets. While a classification task is often defined at a specific level of this hierarchy, training can utilize a finer granularity of labels. Empirical evidence suggests that such fine-grained training can enhance performance. In this work, we investigate the generality of this observation and explore its underlying causes using both real…

dbpedia_recordlabel: DBpedia artist-label affiliations
Bipartite networks of the affiliations (contractual relations) between artists and the record labels under which they have performed, as extracted from Wikipedia by the DBpedia project.
This network has 186758 nodes and 233286 edges.
Tags: Economic, Employment, Unweighted
http…

Quantifying Label-Induced Bias in Large Language Model Self- and Cross-Evaluations
Muskan Saraf, Sajjad Rezvani Boroujeni, Justin Beaudry, Hossein Abedi, Tom Bush
https://arxiv.org/abs/2508.21164

Quantifying Label-Induced Bias in Large Language Model Self- and Cross-Evaluations
Large language models (LLMs) are increasingly used to evaluate outputs, yet their judgments may be influenced. This study examines bias in self- and cross-model evaluations by ChatGPT, Gemini, and Claude under four conditions: no labels, true labels, and two false-label scenarios. Blog posts authored by each model were evaluated by all three using both overall preference voting and quality ratings for Coherence, Informativeness, and Conciseness, with all scores expressed as percentages for dire…

Strategic Sample Selection for Improved Clean-Label Backdoor Attacks in Text Classification
Onur Alp Kirci, M. Emre Gursoy
https://arxiv.org/abs/2508.15934 https://

Strategic Sample Selection for Improved Clean-Label Backdoor Attacks in Text Classification
Backdoor attacks pose a significant threat to the integrity of text classification models used in natural language processing. While several dirty-label attacks that achieve high attack success rates (ASR) have been proposed, clean-label attacks are inherently more difficult. In this paper, we propose three sample selection strategies to improve attack effectiveness in clean-label scenarios: Minimum, Above50, and Below50. Our strategies identify those samples which the model predicts incorrectl…

Pose-Free 3D Quantitative Phase Imaging of Flowing Cellular Populations
Enze Ye, Wei Lin, Shaochi Ren, Yakun Liu, Xiaoping Li, Hao Wang, He Sun, Feng Pan
https://arxiv.org/abs/2509.04848

Pose-Free 3D Quantitative Phase Imaging of Flowing Cellular Populations
High-throughput 3D quantitative phase imaging (QPI) in flow cytometry enables label-free, volumetric characterization of individual cells by reconstructing their refractive index (RI) distributions from multiple viewing angles during flow through microfluidic channels. However, current imaging methods assume that cells undergo uniform, single-axis rotation, which require their poses to be known at each frame. This assumption restricts applicability to near-spherical cells and prevents accurate …

discogs_label: Discogs label affiliations
Two bipartite networks of the affiliations between musical labels and either musical genres or musical "styles," as given in the discogs.com database. Edges represent that a label was involved in a production of a musical release of a given genre or given style. The date of this snapshot is uncertain.
This network has 270786 nodes and 4147665 edges.
Tags: Informational, Relatedness, Unweighted, Multigraph

Adapt in the Wild: Test-Time Entropy Minimization with Sharpness and Feature Regularization
Shuaicheng Niu, Guohao Chen, Deyu Chen, Yifan Zhang, Jiaxiang Wu, Zhiquan Wen, Yaofo Chen, Peilin Zhao, Chunyan Miao, Mingkui Tan
https://arxiv.org/abs/2509.04977

Adapt in the Wild: Test-Time Entropy Minimization with Sharpness and Feature Regularization
Test-time adaptation (TTA) may fail to improve or even harm the model performance when test data have: 1) mixed distribution shifts, 2) small batch sizes, 3) online imbalanced label distribution shifts. This is often a key obstacle preventing existing TTA methods from being deployed in the real world. In this paper, we investigate the unstable reasons and find that the batch norm layer is a crucial factor hindering TTA stability. Conversely, TTA can perform more stably with batch-agnostic norm …

discogs_label: Discogs label affiliations
Two bipartite networks of the affiliations between musical labels and either musical genres or musical "styles," as given in the discogs.com database. Edges represent that a label was involved in a production of a musical release of a given genre or given style. The date of this snapshot is uncertain.
This network has 270786 nodes and 4147665 edges.
Tags: Informational, Relatedness, Unweighted, Multigraph

discogs_label: Discogs label affiliations
Two bipartite networks of the affiliations between musical labels and either musical genres or musical "styles," as given in the discogs.com database. Edges represent that a label was involved in a production of a musical release of a given genre or given style. The date of this snapshot is uncertain.
This network has 270786 nodes and 4147665 edges.
Tags: Informational, Relatedness, Unweighted, Multigraph

dbpedia_recordlabel: DBpedia artist-label affiliations
Bipartite networks of the affiliations (contractual relations) between artists and the record labels under which they have performed, as extracted from Wikipedia by the DBpedia project.
This network has 186758 nodes and 233286 edges.
Tags: Economic, Employment, Unweighted
http…

slashdot_zoo: Slashdot Zoo friend-foe network (2009)
A network of interactions among users on Slashdot (slashdot.org), a technology news website. Users name each other as friends or foe. The friend label increases the scores of post, and the foe label decreases the score.
This network has 79120 nodes and 515397 edges.
Tags: Social, Online, Signed