Tootfinder

DatasetAgent: A Novel Multi-Agent System for Auto-Constructing Datasets from Real-World Images
Haoran Sun, Haoyu Bian, Shaoning Zeng, Yunbo Rao, Xu Xu, Lin Mei, Jianping Gou
https://arxiv.org/abs/2507.08648

DatasetAgent: A Novel Multi-Agent System for Auto-Constructing Datasets from Real-World Images
Common knowledge indicates that the process of constructing image datasets usually depends on the time-intensive and inefficient method of manual collection and annotation. Large models offer a solution via data generation. Nonetheless, real-world data are obviously more valuable comparing to artificially intelligence generated data, particularly in constructing image datasets. For this reason, we propose a novel method for auto-constructing datasets from real-world images by a multiagent colla…

Compartmentalised Agentic Reasoning for Clinical NLI
Ma\"el Jullien, Lei Xu, Marco Valentino, Andr\'e Freitas
https://arxiv.org/abs/2509.10222 https://

Compartmentalised Agentic Reasoning for Clinical NLI
A common assumption holds that scaling data and parameters yields increasingly structured, generalisable internal representations. We interrogate this assumption in clinical natural language inference (NLI) by adopting a benchmark decomposed into four reasoning families, Causal Attribution, Compositional Grounding, Epistemic Verification, and Risk State Abstraction, and introducing CARENLI, a Compartmentalised Agentic Reasoning for Clinical NLI that separates knowledge access from principled in…

From Nodes to Narratives: Explaining Graph Neural Networks with LLMs and Graph Context
Peyman Baghershahi, Gregoire Fournier, Pranav Nyati, Sourav Medya
https://arxiv.org/abs/2508.07117

From Nodes to Narratives: Explaining Graph Neural Networks with LLMs and Graph Context
Graph Neural Networks (GNNs) have emerged as powerful tools for learning over structured data, including text-attributed graphs, which are common in domains such as citation networks, social platforms, and knowledge graphs. GNNs are not inherently interpretable and thus, many explanation methods have been proposed. However, existing explanation methods often struggle to generate interpretable, fine-grained rationales, especially when node attributes include rich natural language. In this work, …

Optimal Simultaneous Byzantine Agreement, Common Knowledge and Limited Information Exchange
Ron van der Meyden
https://arxiv.org/abs/2508.03418 https://arx…

Optimal Simultaneous Byzantine Agreement, Common Knowledge and Limited Information Exchange
In order to develop solutions that perform actions as early as possible, analysis of distributed algorithms using epistemic logic has generally concentrated on ``full information protocols'', which may be inefficient with respect to space and computation time. The paper reconsiders the epistemic analysis of the problem of Simultaneous Byzantine Agreement with respect to weaker, but more practical, exchanges of information. The paper first clarifies some issues concerning both the specification …

MaLV-OS: Rethinking the Operating System Architecture for Machine Learning in Virtualized Clouds
Stella Bitchebe, Oana Balmau
https://arxiv.org/abs/2508.03676 https://

MaLV-OS: Rethinking the Operating System Architecture for Machine Learning in Virtualized Clouds
A large body of research has employed Machine Learning (ML) models to develop learned operating systems (OSes) and kernels. The latter dynamically adapts to the job load and dynamically adjusts resources (CPU, IO, memory, network bandwidth) allocation to respond to the actual user demand. What this work has in common is that it utilizes ML to improve kernel decisions. To this day, and to the best of our knowledge, no work has taken the opposite direction, i.e., using OS to improve ML. While som…

Is anyone aware of publications or research on what sort of bugs LLM-generated or LLM-assisted code tends to have?
Like, we have a huge body of knowledge in the security community about how to audit human-generated codebases for the types of bugs that human developers commonly write.
But we don't have that kind of data yet (AFAIK) for the vibe-coded monstrosities all of us are going to be pentesting soon.
Gut feelings:
* There are some common threads and patterns …

Prediction is not Explanation: Revisiting the Explanatory Capacity of Mapping Embeddings
Hanna Herasimchyk, Alhassan Abdelhalim, S\"oren Laue, Michaela Regneri
https://arxiv.org/abs/2508.13729

Prediction is not Explanation: Revisiting the Explanatory Capacity of Mapping Embeddings
Understanding what knowledge is implicitly encoded in deep learning models is essential for improving the interpretability of AI systems. This paper examines common methods to explain the knowledge encoded in word embeddings, which are core elements of large language models (LLMs). These methods typically involve mapping embeddings onto collections of human-interpretable semantic features, known as feature norms. Prior work assumes that accurately predicting these semantic features from the wor…

TRUST-VL: An Explainable News Assistant for General Multimodal Misinformation Detection
Zehong Yan, Peng Qi, Wynne Hsu, Mong Li Lee
https://arxiv.org/abs/2509.04448 https://

TRUST-VL: An Explainable News Assistant for General Multimodal Misinformation Detection
Multimodal misinformation, encompassing textual, visual, and cross-modal distortions, poses an increasing societal threat that is amplified by generative AI. Existing methods typically focus on a single type of distortion and struggle to generalize to unseen scenarios. In this work, we observe that different distortion types share common reasoning capabilities while also requiring task-specific skills. We hypothesize that joint training across distortion types facilitates knowledge sharing and …

Your ATs to Ts: MITRE ATT&CK Attack Technique to P-SSCRM Task Mapping
Sivana Hamer, Jacob Bowen, Md Nazmul Haque, Chris Madden, Laurie Williams
https://arxiv.org/abs/2507.18037

Your ATs to Ts: MITRE ATT&CK Attack Technique to P-SSCRM Task Mapping
The MITRE Adversarial Tactics, Techniques and Common Knowledge (MITRE ATT&CK) Attack Technique to Proactive Software Supply Chain Risk Management Framework (P-SSCRM) Task mapping described in this document helps software organizations to determine how different tasks mitigate the attack techniques of software supply chain attacks. The mapping was created through four independent strategies to find agreed-upon mappings. Because each P-SSCRM task is mapped to one or more tasks from the 10 framewo…

OpticalAging: Real-time Presbyopia Simulation for Inclusive Design via Tunable Lenses
Qing Zhang, Zixiong Su, Yoshihito Kondoh, Kazunori Asada, Thad Starner, Kai Kunze, Yuta Itoh, Jun Rekimoto
https://arxiv.org/abs/2506.19307

OpticalAging: Real-time Presbyopia Simulation for Inclusive Design via Tunable Lenses
Presbyopia, a common age-related vision condition affecting most people as they age, often remains inadequately understood by those unaffected. To help bridge the gap between abstract accessibility knowledge and a more grounded appreciation of perceptual challenges, this study presents OpticalAging, an optical see-through simulation approach. Unlike VR-based methods, OpticalAging uses dynamically controlled tunable lenses to simulate the first-person visual perspective of presbyopia's distance-…

Towards Automated EEG-Based Detection Using Deep Convolutional Autoencoders
Annika Stiehl, Nicolas Weeger, Christian Uhl, Dominic Bechtold, Nicole Ille, Stefan Gei{\ss}els\"oder
https://arxiv.org/abs/2508.20535

Towards Automated EEG-Based Detection Using Deep Convolutional Autoencoders
Epilepsy is one of the most common neurological disorders. This disease requires reliable and efficient seizure detection methods. Electroencephalography (EEG) is the gold standard for seizure monitoring, but its manual analysis is a time-consuming task that requires expert knowledge. In addition, there are no well-defined features that allow fully automated analysis. Existing deep learning-based approaches struggle to achieve high sensitivity while maintaining a low false alarm rate per hour (…

Views: A Hardware-friendly Graph Database Model For Storing Semantic Information
Yanjun Yang, Adrian Wheeldon, Yihan Pan, Alex Serb
https://arxiv.org/abs/2508.18123 https://

Views: A Hardware-friendly Graph Database Model For Storing Semantic Information
The graph database (GDB) is an increasingly common storage model for data involving relationships between entries. Beyond its widespread usage in database industries, the advantages of GDBs indicate a strong potential in constructing symbolic artificial intelligences (AIs) and retrieval-augmented generation (RAG), where knowledge of data inter-relationships takes a critical role in implementation. However, current GDB models are not optimised for hardware acceleration, leading to bottlenecks in…

An Investigation Into Secondary School Students' Debugging Behaviour in Python
Laurie Gale, Sue Sentance
https://arxiv.org/abs/2508.14833 https://arxiv…

An Investigation Into Secondary School Students' Debugging Behaviour in Python
Background and context: Debugging is a common and often frustrating challenge for beginner programmers. Understanding students' debugging processes can help us identify the difficulties and misunderstandings they possess. However, we currently have limited knowledge of how secondary students debug in a text-based language, a medium through which millions of students will learn to program in the future. Objectives: In this paper, we investigate the debugging behaviour of K-12 students learning a…

Architecture is All You Need: Improving LLM Recommenders by Dropping the Text
Kevin Foley, Shaghayegh Agah, Kavya Priyanka Kakinada
https://arxiv.org/abs/2506.15833

Architecture is All You Need: Improving LLM Recommenders by Dropping the Text
In recent years, there has been an explosion of interest in the applications of large pre-trained language models (PLMs) to recommender systems, with many studies showing strong performance of PLMs on common benchmark datasets. PLM-based recommender models benefit from flexible and customizable prompting, an unlimited vocabulary of recommendable items, and general ``world knowledge'' acquired through pre-training on massive text corpora. While PLM-based recommenders show promise in settings whe…

Private Continual Counting of Unbounded Streams
Ben Jacobsen, Kassem Fawaz
https://arxiv.org/abs/2506.15018 https://arxiv.org/pdf/250…

Private Continual Counting of Unbounded Streams
We study the problem of differentially private continual counting in the unbounded setting where the input size $n$ is not known in advance. Current state-of-the-art algorithms based on optimal instantiations of the matrix mechanism cannot be directly applied here because their privacy guarantees only hold when key parameters are tuned to $n$. Using the common `doubling trick' avoids knowledge of $n$ but leads to suboptimal and non-smooth error. We solve this problem by introducing novel matrix…

The Ramon Llull's Thinking Machine for Automated Ideation
Xinran Zhao, Boyuan Zheng, Chenglei Si, Haofei Yu, Ken Liu, Runlong Zhou, Ruochen Li, Tong Chen, Xiang Li, Yiming Zhang, Tongshuang Wu
https://arxiv.org/abs/2508.19200

The Ramon Llull's Thinking Machine for Automated Ideation
This paper revisits Ramon Llull's Ars combinatoria - a medieval framework for generating knowledge through symbolic recombination - as a conceptual foundation for building a modern Llull's thinking machine for research ideation. Our approach defines three compositional axes: Theme (e.g., efficiency, adaptivity), Domain (e.g., question answering, machine translation), and Method (e.g., adversarial training, linear attention). These elements represent high-level abstractions common in scientific …

Learning from nature: insights into GraphDOP's representations of the Earth System
Peter Lean, Mihai Alexe, Eulalie Boucher, Ewan Pinnington, Simon Lang, Patrick Laloyaux, Niels Bormann, Anthony McNally
https://arxiv.org/abs/2508.18018

Learning from nature: insights into GraphDOP's representations of the Earth System
Through a series of experiments, we provide evidence that the GraphDOP model - trained solely on meteorological observations, using no prior knowledge - develops internal representations of the Earth System state, structure and dynamics as well as the characteristics of different observing systems. Firstly, we demonstrate that the network constructs a unified latent representation of the Earth System state which is common across different observation types. For example, cloud structures maintai…

Identifiability in Unlinked Linear Regression: Some Results and Open Problems
Fadoua Balabdaoui, Martin Slawski, Jonathan Steffani
https://arxiv.org/abs/2507.14986

Identifiability in Unlinked Linear Regression: Some Results and Open Problems
A tacit assumption in classical linear regression problems is the full knowledge of the existing link between the covariates and responses. In Unlinked Linear Regression (ULR) this link is either partially or completely missing. While the reasons causing such missingness can be different, a common challenge in statistical inference is the potential non-identifiability of the regression parameter. In this note, we review the existing literature on identifiability when the $d \ge 2$ components of…

Finance Language Model Evaluation (FLaME)
Glenn Matlin, Mika Okamoto, Huzaifa Pardawala, Yang Yang, Sudheer Chava
https://arxiv.org/abs/2506.15846 https://…

Finance Language Model Evaluation (FLaME)
Language Models (LMs) have demonstrated impressive capabilities with core Natural Language Processing (NLP) tasks. The effectiveness of LMs for highly specialized knowledge-intensive tasks in finance remains difficult to assess due to major gaps in the methodologies of existing evaluation frameworks, which have caused an erroneous belief in a far lower bound of LMs' performance on common Finance NLP (FinNLP) tasks. To demonstrate the potential of LMs for these FinNLP tasks, we present the first…

Boosting Pathology Foundation Models via Few-shot Prompt-tuning for Rare Cancer Subtyping
Dexuan He, Xiao Zhou, Wenbin Guan, Liyuan Zhang, Xiaoman Zhang, Sinuo Xu, Ge Wang, Lifeng Wang, Xiaojun Yuan, Xin Sun, Yanfeng Wang, Kun Sun, Ya Zhang, Weidi Xie
https://arxiv.org/abs/2508.15904

Boosting Pathology Foundation Models via Few-shot Prompt-tuning for Rare Cancer Subtyping
Rare cancers comprise 20-25% of all malignancies but face major diagnostic challenges due to limited expert availability-especially in pediatric oncology, where they represent over 70% of cases. While pathology vision-language (VL) foundation models show promising zero-shot capabilities for common cancer subtyping, their clinical performance for rare cancers remains limited. Existing multi-instance learning (MIL) methods rely only on visual features, overlooking cross-modal knowledge and compro…

Quantum-assisted Gaussian process regression using random Fourier features
Cristian A. Galvis-Florez, Ahmad Farooq, Simo S\"arkk\"a
https://arxiv.org/abs/2507.22629 ht…

Quantum-assisted Gaussian process regression using random Fourier features
Probabilistic machine learning models are distinguished by their ability to integrate prior knowledge of noise statistics, smoothness parameters, and training data uncertainty. A common approach involves modeling data with Gaussian processes; however, their computational complexity quickly becomes intractable as the training dataset grows. To address this limitation, we introduce a quantum-assisted algorithm for sparse Gaussian process regression based on the random Fourier feature kernel appro…

Tabularis Formatus: Predictive Formatting for Tables
Mukul Singh, Jos\'e Cambronero, Sumit Gulwani, Vu Le, Gust Verbruggen
https://arxiv.org/abs/2508.11121 https://

Tabularis Formatus: Predictive Formatting for Tables
Spreadsheet manipulation software are widely used for data management and analysis of tabular data, yet the creation of conditional formatting (CF) rules remains a complex task requiring technical knowledge and experience with specific platforms. In this paper we present TaFo, a neuro-symbolic approach to generating CF suggestions for tables, addressing common challenges such as user unawareness, difficulty in rule creation, and inadequate user interfaces. TaFo takes inspiration from component …