Tootfinder

For me, the great @… is the number #1 #Mastodon app on Android.
It also works with #peertube and

"Any tutorial on how to set it up currently?"
I've got you. Just follow these simple instructions.

This season is on fire! 🎸 🖖
#StarTrek #StrangeNewWorlds #FourAndAHalfVulcans

De mythe van de Porsche 911 werkt niet meer - NRC
https://www.nrc.nl/nieuws/2025/06/27/de-mythe-van-de-porsche-911-werkt-niet-meer-a4898301
Aan het eind van het in memoriam ook nog een stukje over de hybride versie.
E…

The RFKJr. situation is generally terrible and all, but apparently CDC managed to keep enough conditions in the "high risk" qualifications to cover just about everyone.
#Covid #Vaccines

"What is Starfleet?" could have been even more cheesy if it was shot like a regular TOS or TNG aliens of the week episode. AND the whole crew had a jolly get-together after they helped the alien to commit suicide. WTF. Classic 😄
#StarTrek #StrangeNewWorlds …

Got out on the OG route on the river today, it's been a minute. Mostly running on the treadmill or park by work, as It's been pretty hot here. I can handle 70's (F) though 😏 #running #runnersofmastodon

SNAP! - Do You See The Light (Looking For) (feat. Niki Haris) [Official Music Video]
https://www.youtube.com/watch?v=Io_B1svrSUw

I feel like something is fundamentally broken with my simulation setup and I have no clue what it is.
Look at stage3_en here. There are no negedge clocked blocks in my RTL.
This is a simple always_ff @(posedge clk) stage3_en <= stage2_en;
How is this even possible???

Marie made pancakes! Egg bacon tea and coffee. Just work today, probably board games at home tonight. #TogetherBreakfast https://photos.app.goo.gl/HWLdc8G1tgRHzmwL7

Das #Rezept des Tages:
Schnelle Champignon-Pfanne mit #Tortelloni – ein Leckerli für Pasta-Liebhaber. 🍝 Und die stopft, kann ich Euch sagen! Mit Spinat-Tortelloni, angebratenen #Champignons …

Schnelle und einfache Champignon-Pfanne mit Tortelloni
Diese Tortelloni-Pfanne ist das ideale Gericht für einen stressfreien Abend. Schnell zubereitet und unglaublich lecker!

"You little commie"
Can't argue with dad 😄
Dad, are you a communist? · Bryan Cranston in · Trumbo
https://www.youtube.com/watch?v=Wp9sc0I6l34

Dad, are you a communist? · Bryan Cranston in · Trumbo · P'sBestBits#4
Brilliant actor... favourite scene from the film, always stuck with me.

Ah, the joy of being #abused for shity #AI training

Oh! 3 More Things
Great Australian Pods Podcast Directory: #GreatAusPods

Respekt, Frau Riniker. Ich hätte es wohl nicht geschafft, der Ork-Vertreterin die Hand zu geben. 🤢
Allenfalls hätte ich vorher meine Hand in Blut getränkt.
#RussiaIsATerrorState

TFW a student enthusiastically thanks you for your one-shot lesson right in front of the professor. May we all have such an auspicious start to the long weekend :).

Today I "fixed" a very weird error in an old vue app (endless recursion when trying some geocoding) by using the correct API key. Could have been easy with a proper error message, but maybe it was hidden by some bungled code we wrote 5 years ago...)

The VHS copy running 5% faster than the Blu-ray copy, resulting in 6 minutes discrepancy by the end credits, is hilarious ->
Why the heck are there two versions of the first Harry Potter movie?
https://www.youtube.com/watch?v=jrvih1gSN4w

Fast Convergence Rates for Subsampled Natural Gradient Algorithms on Quadratic Model Problems
Gil Goldshlager, Jiang Hu, Lin Lin
https://arxiv.org/abs/2508.21022 https://…

Fast Convergence Rates for Subsampled Natural Gradient Algorithms on Quadratic Model Problems
Subsampled natural gradient descent (SNGD) has shown impressive results for parametric optimization tasks in scientific machine learning, such as neural network wavefunctions and physics-informed neural networks, but it has lacked a theoretical explanation. We address this gap by analyzing the convergence of SNGD and its accelerated variant, SPRING, for idealized parametric optimization problems where the model is linear and the loss function is strongly convex and quadratic. In the special cas…

Ooof, yanking a repository backing a package is one hell of a thing to do

Ganz sicher nicht von einem Menschen übersetzt! 🤦🏼‍♂️🙄

Today I managed (with help by a subcontractor) to set up a .NET and a Python API to use (and validate!) JWTs issued by our #Perl OAuth2 server.

Inference-Time Alignment Control for Diffusion Models with Reinforcement Learning Guidance
Luozhijie Jin, Zijie Qiu, Jie Liu, Zijie Diao, Lifeng Qiao, Ning Ding, Alex Lamb, Xipeng Qiu
https://arxiv.org/abs/2508.21016

Inference-Time Alignment Control for Diffusion Models with Reinforcement Learning Guidance
Denoising-based generative models, particularly diffusion and flow matching algorithms, have achieved remarkable success. However, aligning their output distributions with complex downstream objectives, such as human preferences, compositional accuracy, or data compressibility, remains challenging. While reinforcement learning (RL) fine-tuning methods, inspired by advances in RL from human feedback (RLHF) for large language models, have been adapted to these generative frameworks, current RL ap…

Today I improved our old OAuth2 server by adding a `/.well-known/openid-configuration` endpoint (and a few other minor improvements to make it work with a new client). But if anybody knows how to generate a JWKS from a ES512 public key (in #Perl) I'd appreciate a hint...

@… @… @… Maybe it's two parts in one? I'd swear there is a rounded 2x3 :crabrave:

InSQuAD: In-Context Learning for Efficient Retrieval via Submodular Mutual Information to Enforce Quality and Diversity
Souradeep Nanda, Anay Majee, Rishabh Iyer
https://arxiv.org/abs/2508.21003

InSQuAD: In-Context Learning for Efficient Retrieval via Submodular Mutual Information to Enforce Quality and Diversity
In this paper, we introduce InSQuAD, designed to enhance the performance of In-Context Learning (ICL) models through Submodular Mutual Information} (SMI) enforcing Quality and Diversity among in-context exemplars. InSQuAD achieves this through two principal strategies: First, we model the ICL task as a targeted selection problem and introduce a unified selection strategy based on SMIs which mines relevant yet diverse in-context examples encapsulating the notions of quality and diversity. Second…

#potd Today we played a round of CO₂ in competitive mode and lost in 2050 with 500ppm CO₂. But a fun game anyway, I wonder if the coop mode is in fact easier. http://domm.plix.at/potd/2025-06-28.h…

@… @… @… The eyes, and the PHP brick on the side, are custom. They are also the only two pieces on the list without a …

Train-Once Plan-Anywhere Kinodynamic Motion Planning via Diffusion Trees
Yaniv Hassidof, Tom Jurgenson, Kiril Solovey
https://arxiv.org/abs/2508.21001 https://

Train-Once Plan-Anywhere Kinodynamic Motion Planning via Diffusion Trees
Kinodynamic motion planning is concerned with computing collision-free trajectories while abiding by the robot's dynamic constraints. This critical problem is often tackled using sampling-based planners (SBPs) that explore the robot's high-dimensional state space by constructing a search tree via action propagations. Although SBPs can offer global guarantees on completeness and solution quality, their performance is often hindered by slow exploration due to uninformed action sampling. Learning-…

#potd Today I harvested a few Ribisel (redcurrant) & Stachelbeeren (gooseberry) in our community garden. http://domm.plix.at/potd/2025-06-29.html

@… 🎬

Finite-Time Guarantees for Multi-Agent Combinatorial Bandits with Nonstationary Rewards
Katherine B. Adams, Justin J. Boutilier, Qinyang He, Yonatan Mintz
https://arxiv.org/abs/2508.20923

Finite-Time Guarantees for Multi-Agent Combinatorial Bandits with Nonstationary Rewards
We study a sequential resource allocation problem where a decision maker selects subsets of agents at each period to maximize overall outcomes without prior knowledge of individual-level effects. Our framework applies to settings such as community health interventions, targeted digital advertising, and workforce retention programs, where intervention effects evolve dynamically. Agents may exhibit habituation (diminished response from frequent selection) or recovery (enhanced response from infre…

@… was that a low key pun?

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

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

LeMat-Traj: A Scalable and Unified Dataset of Materials Trajectories for Atomistic Modeling
Ali Ramlaoui, Martin Siron, Inel Djafar, Joseph Musielewicz, Amandine Rossello, Victor Schmidt, Alexandre Duval
https://arxiv.org/abs/2508.20875

LeMat-Traj: A Scalable and Unified Dataset of Materials Trajectories for Atomistic Modeling
The development of accurate machine learning interatomic potentials (MLIPs) is limited by the fragmented availability and inconsistent formatting of quantum mechanical trajectory datasets derived from Density Functional Theory (DFT). These datasets are expensive to generate yet difficult to combine due to variations in format, metadata, and accessibility. To address this, we introduce LeMat-Traj, a curated dataset comprising over 120 million atomic configurations aggregated from large-scale rep…

Practical Physical Layer Authentication for Mobile Scenarios Using a Synthetic Dataset Enhanced Deep Learning Approach
Yijia Guo, Junqing Zhang, Y. -W. Peter Hong
https://arxiv.org/abs/2508.20861

Practical Physical Layer Authentication for Mobile Scenarios Using a Synthetic Dataset Enhanced Deep Learning Approach
The Internet of Things (IoT) is ubiquitous thanks to the rapid development of wireless technologies. However, the broadcast nature of wireless transmissions results in great vulnerability to device authentication. Physical layer authentication emerges as a promising approach by exploiting the unique channel characteristics. However, a practical scheme applicable to dynamic channel variations is still missing. In this paper, we proposed a deep learning-based physical layer channel state informat…

ATM-GAD: Adaptive Temporal Motif Graph Anomaly Detection for Financial Transaction Networks
Zeyue Zhang, Lin Song, Erkang Bao, Xiaoling Lv, Xinyue Wang
https://arxiv.org/abs/2508.20829

ATM-GAD: Adaptive Temporal Motif Graph Anomaly Detection for Financial Transaction Networks
Financial fraud detection is essential to safeguard billions of dollars, yet the intertwined entities and fast-changing transaction behaviors in modern financial systems routinely defeat conventional machine learning models. Recent graph-based detectors make headway by representing transactions as networks, but they still overlook two fraud hallmarks rooted in time: (1) temporal motifs--recurring, telltale subgraphs that reveal suspicious money flows as they unfold--and (2) account-specific int…

GPT-FT: An Efficient Automated Feature Transformation Using GPT for Sequence Reconstruction and Performance Enhancement
Yang Gao, Dongjie Wang, Scott Piersall, Ye Zhang, Liqiang Wang
https://arxiv.org/abs/2508.20824

GPT-FT: An Efficient Automated Feature Transformation Using GPT for Sequence Reconstruction and Performance Enhancement
Feature transformation plays a critical role in enhancing machine learning model performance by optimizing data representations. Recent state-of-the-art approaches address this task as a continuous embedding optimization problem, converting discrete search into a learnable process. Although effective, these methods often rely on sequential encoder-decoder structures that cause high computational costs and parameter requirements, limiting scalability and efficiency. To address these limitations,…

cMALC-D: Contextual Multi-Agent LLM-Guided Curriculum Learning with Diversity-Based Context Blending
Anirudh Satheesh, Keenan Powell, Hua Wei
https://arxiv.org/abs/2508.20818 ht…

cMALC-D: Contextual Multi-Agent LLM-Guided Curriculum Learning with Diversity-Based Context Blending
Many multi-agent reinforcement learning (MARL) algorithms are trained in fixed simulation environments, making them brittle when deployed in real-world scenarios with more complex and uncertain conditions. Contextual MARL (cMARL) addresses this by parameterizing environments with context variables and training a context-agnostic policy that performs well across all environment configurations. Existing cMARL methods attempt to use curriculum learning to help train and evaluate context-agnostic p…

Unleashing Uncertainty: Efficient Machine Unlearning for Generative AI
Christoforos N. Spartalis, Theodoros Semertzidis, Petros Daras, Efstratios Gavves
https://arxiv.org/abs/2508.20773

Unleashing Uncertainty: Efficient Machine Unlearning for Generative AI
We introduce SAFEMax, a novel method for Machine Unlearning in diffusion models. Grounded in information-theoretic principles, SAFEMax maximizes the entropy in generated images, causing the model to generate Gaussian noise when conditioned on impermissible classes by ultimately halting its denoising process. Also, our method controls the balance between forgetting and retention by selectively focusing on the early diffusion steps, where class-specific information is prominent. Our results demon…

Provable Benefits of In-Tool Learning for Large Language Models
Sam Houliston, Ambroise Odonnat, Charles Arnal, Vivien Cabannes
https://arxiv.org/abs/2508.20755 https://

Provable Benefits of In-Tool Learning for Large Language Models
Tool-augmented language models, equipped with retrieval, memory, or external APIs, are reshaping AI, yet their theoretical advantages remain underexplored. In this paper, we address this question by demonstrating the benefits of in-tool learning (external retrieval) over in-weight learning (memorization) for factual recall. We show that the number of facts a model can memorize solely in its weights is fundamentally limited by its parameter count. In contrast, we prove that tool-use enables unbo…

EEGDM: Learning EEG Representation with Latent Diffusion Model
Shaocong Wang, Tong Liu, Ming Li, Minjing Yu, Yong-Jin Liu
https://arxiv.org/abs/2508.20705 https://

EEGDM: Learning EEG Representation with Latent Diffusion Model
While electroencephalography (EEG) signal analysis using deep learning has shown great promise, existing approaches still face significant challenges in learning generalizable representations that perform well across diverse tasks, particularly when training data is limited. Current EEG representation learning methods including EEGPT and LaBraM typically rely on simple masked reconstruction objective, which may not fully capture the rich semantic information and complex patterns inherent in EEG…

Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning
Weitao Feng, Lixu Wang, Tianyi Wei, Jie Zhang, Chongyang Gao, Sinong Zhan, Peizhuo Lv, Wei Dong
https://arxiv.org/abs/2508.20697

Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning
As large language models (LLMs) continue to grow in capability, so do the risks of harmful misuse through fine-tuning. While most prior studies assume that attackers rely on supervised fine-tuning (SFT) for such misuse, we systematically demonstrate that reinforcement learning (RL) enables adversaries to more effectively break safety alignment and facilitate advanced harmful task assistance, under matched computational budgets. To counter this emerging threat, we propose TokenBuncher, the first…

Compositionality in Time Series: A Proof of Concept using Symbolic Dynamics and Compositional Data Augmentation
Michael Hagmann, Michael Staniek, Stefan Riezler
https://arxiv.org/abs/2508.20656

Compositionality in Time Series: A Proof of Concept using Symbolic Dynamics and Compositional Data Augmentation
This work investigates whether time series of natural phenomena can be understood as being generated by sequences of latent states which are ordered in systematic and regular ways. We focus on clinical time series and ask whether clinical measurements can be interpreted as being generated by meaningful physiological states whose succession follows systematic principles. Uncovering the underlying compositional structure will allow us to create synthetic data to alleviate the notorious problem of…

Self-Composing Neural Operators with Depth and Accuracy Scaling via Adaptive Train-and-Unroll Approach
Juncai He, Xinliang Liu, Jinchao Xu
https://arxiv.org/abs/2508.20650 https…

Self-Composing Neural Operators with Depth and Accuracy Scaling via Adaptive Train-and-Unroll Approach
In this work, we propose a novel framework to enhance the efficiency and accuracy of neural operators through self-composition, offering both theoretical guarantees and practical benefits. Inspired by iterative methods in solving numerical partial differential equations (PDEs), we design a specific neural operator by repeatedly applying a single neural operator block, we progressively deepen the model without explicitly adding new blocks, improving the model's capacity. To train these models ef…

Physics-Constrained Machine Learning for Chemical Engineering
Angan Mukherjee (Department of Chemical,Biological Engineering, University of Wisconsin-Madison, Madison, USA), Victor M. Zavala (Department of Chemical,Biological Engineering, University of Wisconsin-Madison, Madison, USA)
https://arxiv.org/abs/2508.20649

Physics-Constrained Machine Learning for Chemical Engineering
Physics-constrained machine learning (PCML) combines physical models with data-driven approaches to improve reliability, generalizability, and interpretability. Although PCML has shown significant benefits in diverse scientific and engineering domains, technical and intellectual challenges hinder its applicability in complex chemical engineering applications. Key difficulties include determining the amount and type of physical knowledge to embed, designing effective fusion strategies with ML, s…

VarDiU: A Variational Diffusive Upper Bound for One-Step Diffusion Distillation
Leyang Wang, Mingtian Zhang, Zijing Ou, David Barber
https://arxiv.org/abs/2508.20646 https://

VarDiU: A Variational Diffusive Upper Bound for One-Step Diffusion Distillation
Recently, diffusion distillation methods have compressed thousand-step teacher diffusion models into one-step student generators while preserving sample quality. Most existing approaches train the student model using a diffusive divergence whose gradient is approximated via the student's score function, learned through denoising score matching (DSM). Since DSM training is imperfect, the resulting gradient estimate is inevitably biased, leading to sub-optimal performance. In this paper, we propo…

A Hybrid Stochastic Gradient Tracking Method for Distributed Online Optimization Over Time-Varying Directed Networks
Xinli Shi, Xingxing Yuan, Longkang Zhu, Guanghui Wen
https://arxiv.org/abs/2508.20645

A Hybrid Stochastic Gradient Tracking Method for Distributed Online Optimization Over Time-Varying Directed Networks
With the increasing scale and dynamics of data, distributed online optimization has become essential for real-time decision-making in various applications. However, existing algorithms often rely on bounded gradient assumptions and overlook the impact of stochastic gradients, especially in time-varying directed networks. This study proposes a novel Time-Varying Hybrid Stochastic Gradient Tracking algorithm named TV-HSGT, based on hybrid stochastic gradient tracking and variance reduction mechan…

GDS Agent: A Graph Algorithmic Reasoning Agent
Borun Shi, Ioannis Panagiotas
https://arxiv.org/abs/2508.20637 https://arxiv.org/pdf/2508.20637

GDS Agent: A Graph Algorithmic Reasoning Agent
Large language models (LLMs) have shown remarkable multimodal information processing and reasoning ability. When equipped with tools through function calling and enhanced with retrieval-augmented techniques, compound LLM-based systems can access closed data sources and answer questions about them. However, they still struggle to process and reason over large-scale graph-structure data. We introduce the GDS (Graph Data Science) agent in this technical report. The GDS agent introduces a comprehen…

Masked Autoencoders for Ultrasound Signals: Robust Representation Learning for Downstream Applications
Immanuel Ro{\ss}teutscher, Klaus S. Drese, Thorsten Uphues
https://arxiv.org/abs/2508.20622

Masked Autoencoders for Ultrasound Signals: Robust Representation Learning for Downstream Applications
We investigated the adaptation and performance of Masked Autoencoders (MAEs) with Vision Transformer (ViT) architectures for self-supervised representation learning on one-dimensional (1D) ultrasound signals. Although MAEs have demonstrated significant success in computer vision and other domains, their use for 1D signal analysis, especially for raw ultrasound data, remains largely unexplored. Ultrasound signals are vital in industrial applications such as non-destructive testing (NDT) and stru…

Supervised Stochastic Gradient Algorithms for Multi-Trial Source Separation
Ronak Mehta, Mateus Piovezan Otto, Noah Stanis, Azadeh Yazdan-Shahmorad, Zaid Harchaoui
https://arxiv.org/abs/2508.20618

Supervised Stochastic Gradient Algorithms for Multi-Trial Source Separation
We develop a stochastic algorithm for independent component analysis that incorporates multi-trial supervision, which is available in many scientific contexts. The method blends a proximal gradient-type algorithm in the space of invertible matrices with joint learning of a prediction model through backpropagation. We illustrate the proposed algorithm on synthetic and real data experiments. In particular, owing to the additional supervision, we observe an increased success rate of the non-convex…

Dimension Agnostic Testing of Survey Data Credibility through the Lens of Regression
Debabrota Basu, Sourav Chakraborty, Debarshi Chanda, Buddha Dev Das, Arijit Ghosh, Arnab Ray
https://arxiv.org/abs/2508.20616

Dimension Agnostic Testing of Survey Data Credibility through the Lens of Regression
Assessing whether a sample survey credibly represents the population is a critical question for ensuring the validity of downstream research. Generally, this problem reduces to estimating the distance between two high-dimensional distributions, which typically requires a number of samples that grows exponentially with the dimension. However, depending on the model used for data analysis, the conclusions drawn from the data may remain consistent across different underlying distributions. In this…

Local Virtual Nodes for Alleviating Over-Squashing in Graph Neural Networks
Tu\u{g}rul Hasan Karabulut, \.Inci M. Bayta\c{s}
https://arxiv.org/abs/2508.20597 https://

Local Virtual Nodes for Alleviating Over-Squashing in Graph Neural Networks
Over-squashing is a challenge in training graph neural networks for tasks involving long-range dependencies. In such tasks, a GNN's receptive field should be large enough to enable communication between distant nodes. However, gathering information from a wide range of neighborhoods and squashing its content into fixed-size node representations makes message-passing vulnerable to bottlenecks. Graph rewiring and adding virtual nodes are commonly studied remedies that create additional pathways a…

Unbiased Stochastic Optimization for Gaussian Processes on Finite Dimensional RKHS
Neta Shoham, Haim Avron
https://arxiv.org/abs/2508.20588 https://arxiv.o…

Unbiased Stochastic Optimization for Gaussian Processes on Finite Dimensional RKHS
Current methods for stochastic hyperparameter learning in Gaussian Processes (GPs) rely on approximations, such as computing biased stochastic gradients or using inducing points in stochastic variational inference. However, when using such methods we are not guaranteed to converge to a stationary point of the true marginal likelihood. In this work, we propose algorithms for exact stochastic inference of GPs with kernels that induce a Reproducing Kernel Hilbert Space (RKHS) of moderate finite di…

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training
Yang Luo, Zangwei Zheng, Ziheng Qin, Zirui Zhu, Yong Liu, Yang You
https://arxiv.org/abs/2508.20577

MERIT: Maximum-normalized Element-wise Ratio for Language Model Large-batch Training
Large-batch training has become a cornerstone in accelerating the training of deep neural networks, yet it poses challenges in optimization and generalization. Existing optimizers like AdamW present performance degradation during language models' large-batch training, due to the information bottleneck in attention layers caused by the sharp increase of max attention logit. While the LAMB optimizer partially addresses this issue, some attention layers still face this issue. The reason is that $l…

Theoretical foundations of the integral indicator application in hyperparametric optimization
Roman S. Kulshin, Anatoly A. Sidorov
https://arxiv.org/abs/2508.20550 https://

Theoretical foundations of the integral indicator application in hyperparametric optimization
The article discusses the concept of hyperparametric optimization of recommendation algorithms using an integral assessment that combines various performance indicators into a single consolidated criterion. This approach is opposed to traditional methods of setting up a single metric and allows you to achieve a balance between accuracy, ranking quality, variety of output and the resource intensity of algorithms. The theoretical significance of the research lies in the development of a universal…

MedGR$^2$: Breaking the Data Barrier for Medical Reasoning via Generative Reward Learning
Weihai Zhi, Jiayan Guo, Shangyang Li
https://arxiv.org/abs/2508.20549 https://

MedGR$^2$: Breaking the Data Barrier for Medical Reasoning via Generative Reward Learning
The application of Vision-Language Models (VLMs) in medicine is critically hampered by the scarcity of high-quality, expert-annotated data. Supervised Fine-Tuning (SFT) on existing datasets often leads to poor generalization on unseen modalities and tasks, while Reinforcement Learning (RL), a promising alternative, is stymied by the lack of reliable reward signals in this data-scarce domain. To break this impasse, we introduce Generative Reward Learning for Medical Reasoning (MedGR$^2$), a nove…

Khiops: An End-to-End, Frugal AutoML and XAI Machine Learning Solution for Large, Multi-Table Databases
Marc Boull\'e, Nicolas Voisine, Bruno Guerraz, Carine Hue, Felipe Olmos, Vladimir Popescu, St\'ephane Gouache, St\'ephane Bouget, Alexis Bondu, Luc Aurelien Gauthier, Yassine Nair Benrekia, Fabrice Cl\'erot, Vincent Lemaire
https://

Khiops: An End-to-End, Frugal AutoML and XAI Machine Learning Solution for Large, Multi-Table Databases
Khiops is an open source machine learning tool designed for mining large multi-table databases. Khiops is based on a unique Bayesian approach that has attracted academic interest with more than 20 publications on topics such as variable selection, classification, decision trees and co-clustering. It provides a predictive measure of variable importance using discretisation models for numerical data and value clustering for categorical data. The proposed classification/regression model is a naive…

Structure-aware Hypergraph Transformer for Diagnosis Prediction in Electronic Health Records
Haiyan Wang, Ye Yuan
https://arxiv.org/abs/2508.20500 https://…

Structure-aware Hypergraph Transformer for Diagnosis Prediction in Electronic Health Records
Electronic Health Records (EHR) systematically organize patient health data through standardized medical codes, serving as a comprehensive and invaluable source for predictive modeling. Graph neural networks (GNNs) have demonstrated effectiveness in modeling interactions between medical codes within EHR. However, existing GNN-based methods are inadequate due to: a) their reliance on pairwise relations fails to capture the inherent higher-order dependencies in clinical data, and b) the localized…