Tootfinder

“Web is losing” is returning to my mind more often than I’d like
https://infrequently.org/2024/10/platforms-are-competitions/

Platform Strategy and Its Discontents
Alex Russell on browsers, standards, and the process of progress.

Lol how they had to change Leclerc's #2 billboard #BrazilGP

RE: https://festiverse.de/@marek/114598517248961071
Festiverse nun auch auf Version 4.5.0

🤞
"It’s coming to an end guys. I’ve spoken to a lot of House Republicans this week and they’ve confided that Trump’s movement/support is fading. As one told me, “this Epstein bomb is about to drop and no want wants to defend a pedo-protector. It’s just a matter of time.”" - Rep. Eric Swalwell
https://…

Miguel Ángel Russo passed away yesterday. Besides his sports achievements, he was loved and respected everywhere he go. And he died doing what he loved and being fully conscious about it, I can't think of a better way to leave this life.
Today, football is a little bit worse.
https://www.batimes.…

To appear unconditioned, sometimes even absolute, yet floating in a sea of conditioning, a web of interdependence. Is this noble, or deeply foolish. Who's the fool?

Women On The Verge
Great Australian Pods Podcast Directory: #GreatAusPods

Rund um den Gasthof am #PrebischTor führen #Wanderwege über die Felsen zu verschiedenen #Aussichtspunkt​en. Die

B12 - The Keeper
AVON: True, but let us assume that the keeper of the secret is somewhere down there on the planet Goth, and that the keeper is a royal personage.
JENNA: Lurgen's brain print is on a thong around a chief's neck. That's what Docholli said.
https://blake.torpidity.net/m/212/5

Moody Urbanity - UP 🆙
情绪化城市 - 上面 🆙
📷 Nikon FE
🎞️ Ilford HP5 Plus 400, expired 1993
#filmphotography #Photography #blackandwhite

Federated Split Learning for Resource-Constrained Robots in Industrial IoT: Framework Comparison, Optimization Strategies, and Future Directions
Wanli Ni, Hui Tian, Shuai Wang, Chengyang Li, Lei Sun, Zhaohui Yang
https://arxiv.org/abs/2510.05713

Federated Split Learning for Resource-Constrained Robots in Industrial IoT: Framework Comparison, Optimization Strategies, and Future Directions
Federated split learning (FedSL) has emerged as a promising paradigm for enabling collaborative intelligence in industrial Internet of Things (IoT) systems, particularly in smart factories where data privacy, communication efficiency, and device heterogeneity are critical concerns. In this article, we present a comprehensive study of FedSL frameworks tailored for resource-constrained robots in industrial scenarios. We compare synchronous, asynchronous, hierarchical, and heterogeneous FedSL fram…

Over 1.2 million downloads. How someone can live in that color scheme is beyond me 😂
Nevertheless, upon request, Asterix-Saigon is here.
Taking the NixBook project by Mike Kelly as a base again, it is the KDE spin of the family.
You know what to do at: (https://codeberg.org/thesaigoneer/aste

each month, my building posts a neighborhood events calendar
inexplicably, this month it's Very Incorrect AI Slop that:
- Has droopy typos
- Has times with no event name
- Starts on the wrong day
- Doesn't have a single correct event date
- Really likes Dallas
how did they not notice ???

George Pickens gets new $131 million contract projection for potential Cowboys extension https://www.sportingnews.com/us/nfl/dallas-cowboys/news/george-pickens-gets-new-131-million-…

Principled, yet divinely impersonal

My new hobby: discovering how many mindblowing AI automation wonders are just invoking a command that already existed in that product, except less reliably

Bridging the Synthesizability Gap in Perovskites by Combining Computations, Literature Data, and PU Learning
Rushik Desai, Junyeong Ahn, Alejandro Strachan, Arun Mannodi-Kanakkithodi
https://arxiv.org/abs/2510.06166

Bridging the Synthesizability Gap in Perovskites by Combining Computations, Literature Data, and PU Learning
Among emerging energy materials, halide and chalcogenide perovskites have garnered significant attention over the last decade owing to the abundance of their constituent species, low manufacturing costs, and their highly tunable composition-structure-property space. Navigating the vast perovskite compositional landscape is possible using density functional theory (DFT) computations, but they are not easily extended to predictions of the synthesizability of new materials and their properties. As…

Is this thing on?

WE ARE NOT DOING THIS AGAIN :omega_laugh:

Die #EU und ihre Mitgliesstaaten sollten aufhören, die #USA als befreudete Macht zu betrachten. Sie sind es nicht mehr, sondern Verbündete eines aggressiven #Russland|s.
Daher sollten wir große Anstrengungen machen (wie …

US-Sicherheitsstrategie: Deutsche Geheimdienste sind besorgt und warnen
Der Verfassungsschutz mahnt mehr Befugnisse an, um unabhängiger von amerikanischen Geheimdiensten zu werden. Denkbar sei sogar, dass sich die USA bei Wahlen in Europa stärker einmischen könnten.

Empirical Comparison of Membership Inference Attacks in Deep Transfer Learning
Yuxuan Bai, Gauri Pradhan, Marlon Tobaben, Antti Honkela
https://arxiv.org/abs/2510.05753 https://…

Empirical Comparison of Membership Inference Attacks in Deep Transfer Learning
With the emergence of powerful large-scale foundation models, the training paradigm is increasingly shifting from from-scratch training to transfer learning. This enables high utility training with small, domain-specific datasets typical in sensitive applications.Membership inference attacks (MIAs) provide an empirical estimate of the privacy leakage by machine learning models. Yet, prior assessments of MIAs against models fine-tuned with transfer learning rely on a small subset of possible att…

Crippling case of feddiction

A great article on the actual role of commercial space companies.
In space, nobody can hear you budget by Sinéad O’Sullivan
https://www.ft.com/content/1317155e-9a5e-4099-9a67-407d83bb76fb?sharetype=blocked

It is with great satisfaction that I can notify you all that dd'ing the latest Win11 iso doesn't result in a bootable usb stick.
Gatekeeping at its best!

Cozy, casual, #fediversation & #fediversing

Origin of trapped intralayer Wannier and charge-transfer excitons in moir\'e materials
Indrajit Maity, Johannes Lischner, Arash A. Mostofi, \'Angel Rubio
https://arxiv.org/abs/2510.06137

Origin of trapped intralayer Wannier and charge-transfer excitons in moiré materials
Moiré materials offer a versatile platform for engineering excitons with unprecedented control, promising next-generation optoelectronic applications. While continuum models are widely used to study moiré excitons due to their computational efficiency, they often disagree with ab initio many-body approaches, as seen for intralayer excitons in WS$_2$/WSe$_2$ heterobilayers. Here, we resolve these discrepancies using an atomistic, quantum-mechanical framework based on the Bethe-Salpeter equatio…

Seacreatures
On each episode we chat about a specific seacreature with a guest who has spent time and interacted with this ocean animal...
Great Australian Pods Podcast Directory: https://www.greataustralianpods.com/seacreatures/

That Helium browser is a nice one. Super snappy. Very nice, community efforts to package it in distro formats (and Flatpak) ongoing. Of course appimages run ootb on Slackware ;-). Good tip by @…!
#helium

Java people really are ultimate pretrained vibecoders. Take away their IDE and they’re like vibecoders without LLM.

Are Heterogeneous Graph Neural Networks Truly Effective? A Causal Perspective
Xiao Yang, Xuejiao Zhao, Zhiqi Shen
https://arxiv.org/abs/2510.05750 https://…

Are Heterogeneous Graph Neural Networks Truly Effective? A Causal Perspective
Graph neural networks (GNNs) have achieved remarkable success in node classification. Building on this progress, heterogeneous graph neural networks (HGNNs) integrate relation types and node and edge semantics to leverage heterogeneous information. Causal analysis for HGNNs is advancing rapidly, aiming to separate genuine causal effects from spurious correlations. However, whether HGNNs are intrinsically effective remains underexamined, and most studies implicitly assume rather than establish t…

Maybe another coffee and then work, but bed feels really nice today.
02:00 bedtime considered harmful 😖

Colorimetry and Tribology of Ultrapure Copper Surface Micromodification
Aleksandra Szczupak, Grzegorz Cios, Benedykt R. Jany
https://arxiv.org/abs/2510.06075 https://

Colorimetry and Tribology of Ultrapure Copper Surface Micromodification
Controlling optical and tribological properties of metal surfaces, like color and wear rate, without altering their chemical composition is a highly desirable process across numerous fields of science and industry. It represents a cost-effective alternative to traditional chemical methods, particularly for copper, one of the most important metals widely used where high electrical and thermal conductivity, alongside resistance to corrosion, are required. We investigated the control of copper sur…

Communication Enables Cooperation in LLM Agents: A Comparison with Curriculum-Based Approaches
Hachem Madmoun, Salem Lahlou
https://arxiv.org/abs/2510.05748 https://

Communication Enables Cooperation in LLM Agents: A Comparison with Curriculum-Based Approaches
Eliciting cooperation in multi-agent LLM systems is critical for AI alignment. We investigate two approaches: direct communication and curriculum learning. In a 4-player Stag Hunt, a one-word "cheap talk" channel increases cooperation from 0% to 48.3%, demonstrating communication as a robust coordination mechanism. In contrast, we find that curriculum learning is highly sensitive to design choices: our pedagogical curriculum through progressively complex games reduced agent payoffs by 27.4% in …

I never use a software store; the cli rules for me. The Cosmic Store though adds community made applets for the desktop environment. A couple of days ago I easily added a theme to the repo. This community-contributing aspect is a bit overlooked, but it makes Cosmic stand out.
#cosmic #nixos

Most probable prediction about OpenAI future I’ve read.
Spoiler: it will be successful and we will not like it.
https://open.substack.com/pub/defragzone/p/welcome-to-cognitive-capitalism

Welcome to Cognitive Capitalism
Or: How Open AI Learned to Stop Worrying and Love Your Data

RE: https://meta.masto.host/@GamingNews/115666975867414391
Terrible, but as @ KaiserBeamz said it on Twitter "It's bad. But after researching the 50 year history of Warner corporate mergers, there's a good chance this will fuck over Netflix…

Spin wave theory for the triaxial magnetic anisotropy 2D van der Waals antiferromagnet CrSBr
Sergio M. Rezende, Byron Freelon, Roberto L. Rodr\'iguez-Su\'arez
https://arxiv.org/abs/2510.06006

Spin wave theory for the triaxial magnetic anisotropy 2D van der Waals antiferromagnet CrSBr
The magnetic properties of two-dimensional (2D) materials have been attracting increasing attention in recent years due to their unique behavior and possible applications in new devices. One material of great interest is the 2D van der Waals (vdW) crystal CrSBr, that exhibits antiferromagnetic (AF) order at low temperatures due to an interlayer AF exchange interaction. Here we present a full quantum spin-wave theory for CrSBr considering three intralayer and one interlayer exchange interactions…

Improving Discrete Diffusion Unmasking Policies Beyond Explicit Reference Policies
Chunsan Hong, Seonho An, Min-Soo Kim, Jong Chul Ye
https://arxiv.org/abs/2510.05725 https://…

Improving Discrete Diffusion Unmasking Policies Beyond Explicit Reference Policies
Masked diffusion models (MDMs) have recently emerged as a novel framework for language modeling. MDMs generate sentences by iteratively denoising masked sequences, filling in [MASK] tokens step by step. Although MDMs support any-order sampling, performance is highly sensitive to the choice of which position to unmask next. Prior work typically relies on rule-based schedules (e.g., max-confidence, max-margin), which provide ad hoc improvements. In contrast, we replace these heuristics with a lea…

Neighborhood-Adaptive Generalized Linear Graph Embedding with Latent Pattern Mining
S. Peng, L. Hu, W. Zhang, B. Jie, Y. Luo
https://arxiv.org/abs/2510.05719 https://

Neighborhood-Adaptive Generalized Linear Graph Embedding with Latent Pattern Mining
Graph embedding has been widely applied in areas such as network analysis, social network mining, recommendation systems, and bioinformatics. However, current graph construction methods often require the prior definition of neighborhood size, limiting the effective revelation of potential structural correlations in the data. Additionally, graph embedding methods using linear projection heavily rely on a singular pattern mining approach, resulting in relative weaknesses in adapting to different …

DiffSDA: Unsupervised Diffusion Sequential Disentanglement Across Modalities
Hedi Zisling, Ilan Naiman, Nimrod Berman, Supasorn Suwajanakorn, Omri Azencot
https://arxiv.org/abs/2510.05717

DiffSDA: Unsupervised Diffusion Sequential Disentanglement Across Modalities
Unsupervised representation learning, particularly sequential disentanglement, aims to separate static and dynamic factors of variation in data without relying on labels. This remains a challenging problem, as existing approaches based on variational autoencoders and generative adversarial networks often rely on multiple loss terms, complicating the optimization process. Furthermore, sequential disentanglement methods face challenges when applied to real-world data, and there is currently no es…

Primal-Dual Direct Preference Optimization for Constrained LLM Alignment
Yihan Du, Seo Taek Kong, R. Srikant
https://arxiv.org/abs/2510.05703 https://arxiv…

Primal-Dual Direct Preference Optimization for Constrained LLM Alignment
The widespread application of Large Language Models (LLMs) imposes increasing demands on safety, such as reducing harmful content and fake information, and avoiding certain forbidden tokens due to rules and laws. While there have been several recent works studying safe alignment of LLMs, these works either require the training of reward and cost models and incur high memory and computational costs, or need prior knowledge about the optimal solution. Motivated by this fact, we study the problem …

vAttention: Verified Sparse Attention
Aditya Desai, Kumar Krishna Agrawal, Shuo Yang, Alejandro Cuadron, Luis Gaspar Schroeder, Matei Zaharia, Joseph E. Gonzalez, Ion Stoica
https://arxiv.org/abs/2510.05688

vAttention: Verified Sparse Attention
State-of-the-art sparse attention methods for reducing decoding latency fall into two main categories: approximate top-$k$ (and its extension, top-$p$) and recently introduced sampling-based estimation. However, these approaches are fundamentally limited in their ability to approximate full attention: they fail to provide consistent approximations across heads and query vectors and, most critically, lack guarantees on approximation quality, limiting their practical deployment. We observe that t…

QGraphLIME - Explaining Quantum Graph Neural Networks
Haribandhu Jena, Jyotirmaya Shivottam, Subhankar Mishra
https://arxiv.org/abs/2510.05683 https://arxi…

QGraphLIME - Explaining Quantum Graph Neural Networks
Quantum graph neural networks offer a powerful paradigm for learning on graph-structured data, yet their explainability is complicated by measurement-induced stochasticity and the combinatorial nature of graph structure. In this paper, we introduce QuantumGraphLIME (QGraphLIME), a model-agnostic, post-hoc framework that treats model explanations as distributions over local surrogates fit on structure-preserving perturbations of a graph. By aggregating surrogate attributions together with their …

Inductive inference of gradient-boosted decision trees on graphs for insurance fraud detection
F\'elix Vandervorst, Bruno Deprez, Wouter Verbeke, Tim Verdonck
https://arxiv.org/abs/2510.05676

Inductive inference of gradient-boosted decision trees on graphs for insurance fraud detection
Graph-based methods are becoming increasingly popular in machine learning due to their ability to model complex data and relations. Insurance fraud is a prime use case, since false claims are often the result of organised criminals that stage accidents or the same persons filing erroneous claims on multiple policies. One challenge is that graph-based approaches struggle to find meaningful representations of the data because of the high class imbalance present in fraud data. Another is that insu…

Quantifying the Accuracy-Interpretability Trade-Off in Concept-Based Sidechannel Models
David Debot, Giuseppe Marra
https://arxiv.org/abs/2510.05670 https://

Quantifying the Accuracy-Interpretability Trade-Off in Concept-Based Sidechannel Models
Concept Bottleneck Models (CBNMs) are deep learning models that provide interpretability by enforcing a bottleneck layer where predictions are based exclusively on human-understandable concepts. However, this constraint also restricts information flow and often results in reduced predictive accuracy. Concept Sidechannel Models (CSMs) address this limitation by introducing a sidechannel that bypasses the bottleneck and carry additional task-relevant information. While this improves accuracy, it …

NEO: No-Optimization Test-Time Adaptation through Latent Re-Centering
Alexander Murphy, Michal Danilowski, Soumyajit Chatterjee, Abhirup Ghosh
https://arxiv.org/abs/2510.05635 h…

NEO: No-Optimization Test-Time Adaptation through Latent Re-Centering
Test-Time Adaptation (TTA) methods are often computationally expensive, require a large amount of data for effective adaptation, or are brittle to hyperparameters. Based on a theoretical foundation of the geometry of the latent space, we are able to significantly improve the alignment between source and distribution-shifted samples by re-centering target data embeddings at the origin. This insight motivates NEO -- a hyperparameter-free fully TTA method, that adds no significant compute compared…

Monte Carlo-Type Neural Operator for Differential Equations
Salah Eddine Choutri, Prajwal Chauhan, Othmane Mazhar, Saif Eddin Jabari
https://arxiv.org/abs/2510.05620 https://

Monte Carlo-Type Neural Operator for Differential Equations
The Monte Carlo-type Neural Operator (MCNO) introduces a framework for learning solution operators of one-dimensional partial differential equations (PDEs) by directly learning the kernel function and approximating the associated integral operator using a Monte Carlo-type approach. Unlike Fourier Neural Operators (FNOs), which rely on spectral representations and assume translation-invariant kernels, MCNO makes no such assumptions. The kernel is represented as a learnable tensor over sampled in…

Riddled basin geometry sets fundamental limits to predictability and reproducibility in deep learning
Andrew Ly, Pulin Gong
https://arxiv.org/abs/2510.05606 https://

Riddled basin geometry sets fundamental limits to predictability and reproducibility in deep learning
Fundamental limits to predictability are central to our understanding of many physical and computational systems. Here we show that, despite its remarkable capabilities, deep learning exhibits such fundamental limits rooted in the fractal, riddled geometry of its basins of attraction: any initialization that leads to one solution lies arbitrarily close to another that leads to a different one. We derive sufficient conditions for the emergence of riddled basins by analytically linking features w…

Deciphering Invariant Feature Decoupling in Source-free Time Series Forecasting with Proxy Denoising
Kangjia Yan, Chenxi Liu, Hao Miao, Xinle Wu, Yan Zhao, Chenjuan Guo, Bin Yang
https://arxiv.org/abs/2510.05589

Deciphering Invariant Feature Decoupling in Source-free Time Series Forecasting with Proxy Denoising
The proliferation of mobile devices generates a massive volume of time series across various domains, where effective time series forecasting enables a variety of real-world applications. This study focuses on a new problem of source-free domain adaptation for time series forecasting. It aims to adapt a pretrained model from sufficient source time series to the sparse target time series domain without access to the source data, embracing data protection regulations. To achieve this, we propose …

When Does Global Attention Help? A Unified Empirical Study on Atomistic Graph Learning
Arindam Chowdhury, Massimiliano Lupo Pasini
https://arxiv.org/abs/2510.05583 https://

When Does Global Attention Help? A Unified Empirical Study on Atomistic Graph Learning
Graph neural networks (GNNs) are widely used as surrogates for costly experiments and first-principles simulations to study the behavior of compounds at atomistic scale, and their architectural complexity is constantly increasing to enable the modeling of complex physics. While most recent GNNs combine more traditional message passing neural networks (MPNNs) layers to model short-range interactions with more advanced graph transformers (GTs) with global attention mechanisms to model long-range …

(Token-Level) \textbf{InfoRMIA}: Stronger Membership Inference and Memorization Assessment for LLMs
Jiashu Tao, Reza Shokri
https://arxiv.org/abs/2510.05582 https://

(Token-Level) \textbf{InfoRMIA}: Stronger Membership Inference and Memorization Assessment for LLMs
Machine learning models are known to leak sensitive information, as they inevitably memorize (parts of) their training data. More alarmingly, large language models (LLMs) are now trained on nearly all available data, which amplifies the magnitude of information leakage and raises serious privacy risks. Hence, it is more crucial than ever to quantify privacy risk before the release of LLMs. The standard method to quantify privacy is via membership inference attacks, where the state-of-the-art ap…

Power Mechanism: Private Tabular Representation Release for Model Agnostic Consumption
Praneeth Vepakomma, Kaustubh Ponkshe
https://arxiv.org/abs/2510.05581 https://

Power Mechanism: Private Tabular Representation Release for Model Agnostic Consumption
Traditional collaborative learning approaches are based on sharing of model weights between clients and a server. However, there are advantages to resource efficiency through schemes based on sharing of embeddings (activations) created from the data. Several differentially private methods were developed for sharing of weights while such mechanisms do not exist so far for sharing of embeddings. We propose Ours to learn a privacy encoding network in conjunction with a small utility generation net…

Efficient Learning-based Graph Simulation for Temporal Graphs
Sheng Xiang, Chenhao Xu, Dawei Cheng, Xiaoyang Wang, Ying Zhang
https://arxiv.org/abs/2510.05569 https://

Efficient Learning-based Graph Simulation for Temporal Graphs
Graph simulation has recently received a surge of attention in graph processing and analytics. In real-life applications, e.g. social science, biology, and chemistry, many graphs are composed of a series of evolving graphs (i.e., temporal graphs). While most of the existing graph generators focus on static graphs, the temporal information of the graphs is ignored. In this paper, we focus on simulating temporal graphs, which aim to reproduce the structural and temporal properties of the observed…

Generative Dynamic Graph Representation Learning for Conspiracy Spoofing Detection
Sheng Xiang, Yidong Jiang, Yunting Chen, Dawei Cheng, Guoping Zhao, Changjun Jiang
https://arxiv.org/abs/2510.05562

Generative Dynamic Graph Representation Learning for Conspiracy Spoofing Detection
Spoofing detection in financial trading is crucial, especially for identifying complex behaviors such as conspiracy spoofing. Traditional machine-learning approaches primarily focus on isolated node features, often overlooking the broader context of interconnected nodes. Graph-based techniques, particularly Graph Neural Networks (GNNs), have advanced the field by leveraging relational information effectively. However, in real-world spoofing detection datasets, trading behaviors exhibit dynamic,…

Critical attention scaling in long-context transformers
Shi Chen, Zhengjiang Lin, Yury Polyanskiy, Philippe Rigollet
https://arxiv.org/abs/2510.05554 https://

Critical attention scaling in long-context transformers
As large language models scale to longer contexts, attention layers suffer from a fundamental pathology: attention scores collapse toward uniformity as context length $n$ increases, causing tokens to cluster excessively, a phenomenon known as rank-collapse. While $\textit{attention scaling}$ effectively addresses this deficiency by rescaling attention scores with a polylogarithmic factor $β_n$, theoretical justification for this approach remains lacking. We analyze a simplified yet tractable…

Permutation-Invariant Representation Learning for Robust and Privacy-Preserving Feature Selection
Rui Liu, Tao Zhe, Yanjie Fu, Feng Xia, Ted Senator, Dongjie Wang
https://arxiv.org/abs/2510.05535

Permutation-Invariant Representation Learning for Robust and Privacy-Preserving Feature Selection
Feature selection eliminates redundancy among features to improve downstream task performance while reducing computational overhead. Existing methods often struggle to capture intricate feature interactions and adapt across diverse application scenarios. Recent advances employ generative intelligence to alleviate these drawbacks. However, these methods remain constrained by permutation sensitivity in embedding and reliance on convexity assumptions in gradient-based search. To address these limi…

LATTA: Langevin-Anchored Test-Time Adaptation for Enhanced Robustness and Stability
Harshil Vejendla
https://arxiv.org/abs/2510.05530 https://arxiv.org/pdf…

LATTA: Langevin-Anchored Test-Time Adaptation for Enhanced Robustness and Stability
Test-time adaptation (TTA) aims to adapt a pretrained model to distribution shifts using only unlabeled test data. While promising, existing methods like Tent suffer from instability and can catastrophically forget the source knowledge, especially with small batch sizes or challenging corruptions. We argue that this arises from overly deterministic updates on a complex loss surface. In this paper, we introduce Langevin-Anchored Test-Time Adaptation (LATTA), a novel approach that regularizes ada…

ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization
Lawrence Liu, Alexander Liu, Mengdi Wang, Tuo Zhao, Lin F. Yang
https://arxiv.org/abs/2510.05528

ARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization
Large language models (LLMs) present significant deployment challenges due to their immense computational and memory requirements. While semi-structured pruning, particularly 2:4 sparsity, offers a path to practical hardware acceleration, existing methods often incur substantial performance degradation. To bridge this gap, we introduce ARMOR: (Adaptive Representation with Matrix-factORization), a novel one-shot post-training pruning algorithm. Instead of directly pruning weights, ARMOR factoriz…

Transfer Learning on Edge Connecting Probability Estimation under Graphon Model
Yuyao Wang, Yu-Hung Cheng, Debarghya Mukherjee, Huimin Cheng
https://arxiv.org/abs/2510.05527 htt…

Transfer Learning on Edge Connecting Probability Estimation under Graphon Model
Graphon models provide a flexible nonparametric framework for estimating latent connectivity probabilities in networks, enabling a range of downstream applications such as link prediction and data augmentation. However, accurate graphon estimation typically requires a large graph, whereas in practice, one often only observes a small-sized network. One approach to addressing this issue is to adopt a transfer learning framework, which aims to improve estimation in a small target graph by leveragi…

Provably Mitigating Corruption, Overoptimization, and Verbosity Simultaneously in Offline and Online RLHF/DPO Alignment
Ziyi Chen, Junyi Li, Peiran Yu, Heng Huang
https://arxiv.org/abs/2510.05526

Provably Mitigating Corruption, Overoptimization, and Verbosity Simultaneously in Offline and Online RLHF/DPO Alignment
Reinforcement learning from human feedback (RLHF) and direct preference optimization (DPO) are important techniques to align large language models (LLM) with human preference. However, the quality of RLHF and DPO training is seriously compromised by \textit{\textbf{C}orrupted} preference, reward \textit{\textbf{O}veroptimization}, and bias towards \textit{\textbf{V}erbosity}. To our knowledge, most existing works tackle only one of these important issues, and the few other works require much co…

NeST-BO: Fast Local Bayesian Optimization via Newton-Step Targeting of Gradient and Hessian Information
Wei-Ting Tang, Akshay Kudva, Joel A. Paulson
https://arxiv.org/abs/2510.05516

NeST-BO: Fast Local Bayesian Optimization via Newton-Step Targeting of Gradient and Hessian Information
Bayesian optimization (BO) is effective for expensive black-box problems but remains challenging in high dimensions. We propose NeST-BO, a local BO method that targets the Newton step by jointly learning gradient and Hessian information with Gaussian process surrogates, and selecting evaluations via a one-step lookahead bound on Newton-step error. We show that this bound (and hence the step error) contracts with batch size, so NeST-BO directly inherits inexact-Newton convergence: global progres…

EEG-Based Acute Pain Classification: Machine Learning Model Comparison and Real-Time Clinical Feasibility
Aavid Mathrawala, Dhruv Kurup, Josie Lau
https://arxiv.org/abs/2510.05511

EEG-Based Acute Pain Classification: Machine Learning Model Comparison and Real-Time Clinical Feasibility
Current pain assessment within hospitals often relies on self-reporting or non-specific EKG vital signs. This system leaves critically ill, sedated, and cognitively impaired patients vulnerable to undertreated pain and opioid overuse. Electroencephalography (EEG) offers a noninvasive method of measuring brain activity. This technology could potentially be applied as an assistive tool to highlight nociceptive processing in order to mitigate this issue. In this study, we compared machine learning…

Fundamental Limits of Crystalline Equivariant Graph Neural Networks: A Circuit Complexity Perspective
Yang Cao, Zhao Song, Jiahao Zhang, Jiale Zhao
https://arxiv.org/abs/2510.05494

Fundamental Limits of Crystalline Equivariant Graph Neural Networks: A Circuit Complexity Perspective
Graph neural networks (GNNs) have become a core paradigm for learning on relational data. In materials science, equivariant GNNs (EGNNs) have emerged as a compelling backbone for crystalline-structure prediction, owing to their ability to respect Euclidean symmetries and periodic boundary conditions. Despite strong empirical performance, their expressive power in periodic, symmetry-constrained settings remains poorly understood. This work characterizes the intrinsic computational and expressive…

High-Fidelity Synthetic ECG Generation via Mel-Spectrogram Informed Diffusion Training
Zhuoyi Huang, Nutan Sahoo, Anamika Kumari, Girish Kumar, Kexuan Cai, Shixing Cao, Yue Kang, Tian Xia, Somya Chatterjee, Nicholas Hausman, Aidan Jay, Eric S. Rosenthal, Soundar Srinivasan, Sadid Hasan, Alex Fedorov, Sulaiman Vesal, Soundar Srinivasan, Sadid Hasan, Alex Fedorov, Sulaiman Vesal

High-Fidelity Synthetic ECG Generation via Mel-Spectrogram Informed Diffusion Training
The development of machine learning for cardiac care is severely hampered by privacy restrictions on sharing real patient electrocardiogram (ECG) data. Although generative AI offers a promising solution, the real-world use of existing model-synthesized ECGs is limited by persistent gaps in trustworthiness and clinical utility. In this work, we address two major shortcomings of current generative ECG methods: insufficient morphological fidelity and the inability to generate personalized, patient…

NorMuon: Making Muon more efficient and scalable
Zichong Li, Liming Liu, Chen Liang, Weizhu Chen, Tuo Zhao
https://arxiv.org/abs/2510.05491 https://arxiv.o…

NorMuon: Making Muon more efficient and scalable
The choice of optimizer significantly impacts the training efficiency and computational costs of large language models (LLMs). Recently, the Muon optimizer has demonstrated promising results by orthogonalizing parameter updates, improving optimization geometry through better conditioning. Despite Muon's emergence as a candidate successor to Adam, the potential for jointly leveraging their strengths has not been systematically explored. In this work, we bridge this gap by proposing NorMuon (Neur…

The Method of Infinite Descent
Reza T. Batley, Sourav Saha
https://arxiv.org/abs/2510.05489 https://arxiv.org/pdf/2510.05489…

The Method of Infinite Descent
Training - the optimisation of complex models - is traditionally performed through small, local, iterative updates [D. E. Rumelhart, G. E. Hinton, R. J. Williams, Nature 323, 533-536 (1986)]. Approximating solutions through truncated gradients is a paradigm dating back to Cauchy [A.-L. Cauchy, Comptes Rendus Mathématique 25, 536-538 (1847)] and Newton [I. Newton, The Method of Fluxions and Infinite Series (Henry Woodfall, London, 1736)]. This work introduces the Method of Infinite Descent, a s…

ATOM: A Pretrained Neural Operator for Multitask Molecular Dynamics
Luke Thompson, Davy Guan, Dai Shi, Slade Matthews, Junbin Gao, Andi Han
https://arxiv.org/abs/2510.05482 http…

ATOM: A Pretrained Neural Operator for Multitask Molecular Dynamics
Molecular dynamics (MD) simulations underpin modern computational drug dis- covery, materials science, and biochemistry. Recent machine learning models provide high-fidelity MD predictions without the need to repeatedly solve quantum mechanical forces, enabling significant speedups over conventional pipelines. Yet many such methods typically enforce strict equivariance and rely on sequential rollouts, thus limiting their flexibility and simulation efficiency. They are also com- monly single-tas…

AMAQ: Adaptive Mixed-bit Activation Quantization for Collaborative Parameter Efficient Fine-tuning
Yurun Song, Zhuoyi Yang, Ian G. Harris, Sangeetha Abdu Jyothi
https://arxiv.org/abs/2510.05468

AMAQ: Adaptive Mixed-bit Activation Quantization for Collaborative Parameter Efficient Fine-tuning
Large Language Models (LLMs) are scaling rapidly, creating significant challenges for collaborative server client distributed training, particularly in terms of communication efficiency and computational overheads. To address these challenges, we implement Parameter-efficient Split Learning, which effectively balances efficiency and performance for collaborative training on low-resource devices. To reduce communication overhead in collaborative training, we introduce Adaptive Mixed bit Activa…

QDeepGR4J: Quantile-based ensemble of deep learning and GR4J hybrid rainfall-runoff models for extreme flow prediction with uncertainty quantification
Arpit Kapoor, Rohitash Chandra
https://arxiv.org/abs/2510.05453

QDeepGR4J: Quantile-based ensemble of deep learning and GR4J hybrid rainfall-runoff models for extreme flow prediction with uncertainty quantification
Conceptual rainfall-runoff models aid hydrologists and climate scientists in modelling streamflow to inform water management practices. Recent advances in deep learning have unravelled the potential for combining hydrological models with deep learning models for better interpretability and improved predictive performance. In our previous work, we introduced DeepGR4J, which enhanced the GR4J conceptual rainfall-runoff model using a deep learning model to serve as a surrogate for the routing comp…

Prior-Aligned Meta-RL: Thompson Sampling with Learned Priors and Guarantees in Finite-Horizon MDPs
Runlin Zhou, Chixiang Chen, Elynn Chen
https://arxiv.org/abs/2510.05446 https:…

Prior-Aligned Meta-RL: Thompson Sampling with Learned Priors and Guarantees in Finite-Horizon MDPs
We study meta-reinforcement learning in finite-horizon MDPs where related tasks share similar structures in their optimal action-value functions. Specifically, we posit a linear representation $Q^*_h(s,a)=Φ_h(s,a)\,θ^{(k)}_h$ and place a Gaussian meta-prior $ \mathcal{N}(θ^*_h,Σ^*_h)$ over the task-specific parameters $θ^{(k)}_h$. Building on randomized value functions, we propose two Thompson-style algorithms: (i) MTSRL, which learns only the prior mean and performs posterior sampling wit…

Adversarial Reinforcement Learning for Large Language Model Agent Safety
Zizhao Wang, Dingcheng Li, Vaishakh Keshava, Phillip Wallis, Ananth Balashankar, Peter Stone, Lukas Rutishauser
https://arxiv.org/abs/2510.05442

Adversarial Reinforcement Learning for Large Language Model Agent Safety
Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, where malicious instructions hidden in tool outputs can manipulate the agent, posing security risks like data leakage. Current defense strategies typically rely on fine-tuning LLM agents on datasets of known attacks. However, the generation of these datasets relies on manually crafted attack patterns, which limits their…

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

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

Draft, Verify, and Improve: Toward Training-Aware Speculative Decoding
Shrenik Bhansali, Larry Heck
https://arxiv.org/abs/2510.05421 https://arxiv.org/pdf/…

Draft, Verify, and Improve: Toward Training-Aware Speculative Decoding
Autoregressive (AR) decoding is a major latency bottleneck for large language models. Speculative decoding (SD) accelerates AR by letting a drafter propose multi-token blocks that a verifier accepts or rejects. However, many SD systems require heavy offline training or extra components. These choices raise data/compute cost and can yield brittle drafters under distribution drift. We introduce \emph{Draft, Verify, \& Improve (DVI)}, a training-aware self-speculative framework that combines infer…

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature
Xin Gu, Yingtai Xiao, Guanlin He, Jiamu Bai, Daniel Kifer, Kiwan Maeng
https://arxiv.org/abs/2510.05416 https:…

Correlating Cross-Iteration Noise for DP-SGD using Model Curvature
Differentially private stochastic gradient descent (DP-SGD) offers the promise of training deep learning models while mitigating many privacy risks. However, there is currently a large accuracy gap between DP-SGD and normal SGD training. This has resulted in different lines of research investigating orthogonal ways of improving privacy-preserving training. One such line of work, known as DP-MF, correlates the privacy noise across different iterations of stochastic gradient descent -- allowing l…

Stratified GRPO: Handling Structural Heterogeneity in Reinforcement Learning of LLM Search Agents
Mingkang Zhu, Xi Chen, Bei Yu, Hengshuang Zhao, Jiaya Jia
https://arxiv.org/abs/2510.06214

Stratified GRPO: Handling Structural Heterogeneity in Reinforcement Learning of LLM Search Agents
Large language model (LLM) agents increasingly rely on external tools such as search engines to solve complex, multi-step problems, and reinforcement learning (RL) has become a key paradigm for training them. However, the trajectories of search agents are structurally heterogeneous, where variations in the number, placement, and outcomes of search calls lead to fundamentally different answer directions and reward distributions. Standard policy gradient methods, which use a single global baselin…

Training Dynamics Impact Post-Training Quantization Robustness
Albert Catalan-Tatjer, Niccol\`o Ajroldi, Jonas Geiping
https://arxiv.org/abs/2510.06213 https://

Training Dynamics Impact Post-Training Quantization Robustness
While post-training quantization is widely adopted for efficient deployment of large language models, the mechanisms underlying quantization robustness remain unclear. We conduct a comprehensive analysis of quantization degradation across open-source language model training trajectories up to 32B parameters and 15T training tokens to accurately assess the relationship between training dynamics and quantization performance. Our key finding is that quantization errors in large-scale training runs…

Reference Grounded Skill Discovery
Seungeun Rho, Aaron Trinh, Danfei Xu, Sehoon Ha
https://arxiv.org/abs/2510.06203 https://arxiv.org/pdf/2510.06203…

Reference Grounded Skill Discovery
Scaling unsupervised skill discovery algorithms to high-DoF agents remains challenging. As dimensionality increases, the exploration space grows exponentially, while the manifold of meaningful skills remains limited. Therefore, semantic meaningfulness becomes essential to effectively guide exploration in high-dimensional spaces. In this work, we present Reference-Grounded Skill Discovery (RGSD), a novel algorithm that grounds skill discovery in a semantically meaningful latent space using refer…

On Powerful Ways to Generate: Autoregression, Diffusion, and Beyond
Chenxiao Yang, Cai Zhou, David Wipf, Zhiyuan Li
https://arxiv.org/abs/2510.06190 https://

On Powerful Ways to Generate: Autoregression, Diffusion, and Beyond
This paper formally studies generation processes, including auto-regressive next-token prediction and masked diffusion, that abstract beyond architectural specifics. At this level of abstraction, we quantify their benefits and limitations through measurable criteria such as computational hardness and learnability. In particular, we demonstrate that allowing generation to proceed beyond autoregression and current masked diffusion, with capabilities to rewrite and length-variable edit, can bring …

Conformalized Gaussian processes for online uncertainty quantification over graphs
Jinwen Xu, Qin Lu, Georgios B. Giannakis
https://arxiv.org/abs/2510.06181 https://

Conformalized Gaussian processes for online uncertainty quantification over graphs
Uncertainty quantification (UQ) over graphs arises in a number of safety-critical applications in network science. The Gaussian process (GP), as a classical Bayesian framework for UQ, has been developed to handle graph-structured data by devising topology-aware kernel functions. However, such GP-based approaches are limited not only by the prohibitive computational complexity, but also the strict modeling assumptions that might yield poor coverage, especially with labels arriving on the fly. To…

Thermodynamic Performance Limits for Score-Based Diffusion Models
Nathan X. Kodama, Michael Hinczewski
https://arxiv.org/abs/2510.06174 https://arxiv.org/p…

Thermodynamic Performance Limits for Score-Based Diffusion Models
We establish a fundamental connection between score-based diffusion models and non-equilibrium thermodynamics by deriving performance limits based on entropy rates. Our main theoretical contribution is a lower bound on the negative log-likelihood of the data that relates model performance to entropy rates of diffusion processes. We numerically validate this bound on a synthetic dataset and investigate its tightness. By building a bridge to entropy rates - system, intrinsic, and exchange entropy…

Higher-Order Feature Attribution: Bridging Statistics, Explainable AI, and Topological Signal Processing
Kurt Butler, Guanchao Feng, Petar Djuric
https://arxiv.org/abs/2510.06165

Higher-Order Feature Attribution: Bridging Statistics, Explainable AI, and Topological Signal Processing
Feature attributions are post-training analysis methods that assess how various input features of a machine learning model contribute to an output prediction. Their interpretation is straightforward when features act independently, but becomes less direct when the predictive model involves interactions such as multiplicative relationships or joint feature contributions. In this work, we propose a general theory of higher-order feature attribution, which we develop on the foundation of Integrate…

TabPFN-Wide: Continued Pre-Training for Extreme Feature Counts
Christopher Kolberg, Katharina Eggensperger, Nico Pfeifer
https://arxiv.org/abs/2510.06162 https://

TabPFN-Wide: Continued Pre-Training for Extreme Feature Counts
Revealing novel insights from the relationship between molecular measurements and pathology remains a very impactful application of machine learning in biomedicine. Data in this domain typically contain only a few observations but thousands of potentially noisy features, posing challenges for conventional machine learning approaches. While prior-data fitted networks emerge as foundation models for tabular data, they are currently not suited to handle large feature counts (>500). Although featur…

LLMs as Policy-Agnostic Teammates: A Case Study in Human Proxy Design for Heterogeneous Agent Teams
Aju Ani Justus, Chris Baber
https://arxiv.org/abs/2510.06151 https://

LLMs as Policy-Agnostic Teammates: A Case Study in Human Proxy Design for Heterogeneous Agent Teams
A critical challenge in modelling Heterogeneous-Agent Teams is training agents to collaborate with teammates whose policies are inaccessible or non-stationary, such as humans. Traditional approaches rely on expensive human-in-the-loop data, which limits scalability. We propose using Large Language Models (LLMs) as policy-agnostic human proxies to generate synthetic data that mimics human decision-making. To evaluate this, we conduct three experiments in a grid-world capture game inspired by Sta…

Improved High-probability Convergence Guarantees of Decentralized SGD
Aleksandar Armacki, Ali H. Sayed
https://arxiv.org/abs/2510.06141 https://arxiv.org/p…

Improved High-probability Convergence Guarantees of Decentralized SGD
Convergence in high-probability (HP) has been receiving increasing interest, due to its attractive properties, such as exponentially decaying tail bounds and strong guarantees for each individual run of an algorithm. While HP guarantees are extensively studied in centralized settings, much less is understood in the decentralized, networked setup. Existing HP studies in decentralized settings impose strong assumptions, like uniformly bounded gradients, or asymptotically vanishing noise, resultin…

Multi-Task Reinforcement Learning with Language-Encoded Gated Policy Networks
Rushiv Arora
https://arxiv.org/abs/2510.06138 https://arxiv.org/pdf/2510.0613…

Multi-Task Reinforcement Learning with Language-Encoded Gated Policy Networks
Multi-task reinforcement learning often relies on task metadata -- such as brief natural-language descriptions -- to guide behavior across diverse objectives. We present Lexical Policy Networks (LEXPOL), a language-conditioned mixture-of-policies architecture for multi-task RL. LEXPOL encodes task metadata with a text encoder and uses a learned gating module to select or blend among multiple sub-policies, enabling end-to-end training across tasks. On MetaWorld benchmarks, LEXPOL matches or exce…

lm-Meter: Unveiling Runtime Inference Latency for On-Device Language Models
Haoxin Wang, Xiaolong Tu, Hongyu Ke, Huirong Chai, Dawei Chen, Kyungtae Han
https://arxiv.org/abs/2510.06126

lm-Meter: Unveiling Runtime Inference Latency for On-Device Language Models
Large Language Models (LLMs) are increasingly integrated into everyday applications, but their prevalent cloud-based deployment raises growing concerns around data privacy and long-term sustainability. Running LLMs locally on mobile and edge devices (on-device LLMs) offers the promise of enhanced privacy, reliability, and reduced communication costs. However, realizing this vision remains challenging due to substantial memory and compute demands, as well as limited visibility into performance-e…

Downsized and Compromised?: Assessing the Faithfulness of Model Compression
Moumita Kamal, Douglas A. Talbert
https://arxiv.org/abs/2510.06125 https://arxi…

Downsized and Compromised?: Assessing the Faithfulness of Model Compression
In real-world applications, computational constraints often require transforming large models into smaller, more efficient versions through model compression. While these techniques aim to reduce size and computational cost without sacrificing performance, their evaluations have traditionally focused on the trade-off between size and accuracy, overlooking the aspect of model faithfulness. This limited view is insufficient for high-stakes domains like healthcare, finance, and criminal justice, w…

PolyGraph Discrepancy: a classifier-based metric for graph generation
Markus Krimmel, Philip Hartout, Karsten Borgwardt, Dexiong Chen
https://arxiv.org/abs/2510.06122 https://…

PolyGraph Discrepancy: a classifier-based metric for graph generation
Existing methods for evaluating graph generative models primarily rely on Maximum Mean Discrepancy (MMD) metrics based on graph descriptors. While these metrics can rank generative models, they do not provide an absolute measure of performance. Their values are also highly sensitive to extrinsic parameters, namely kernel and descriptor parametrization, making them incomparable across different graph descriptors. We introduce PolyGraph Discrepancy (PGD), a new evaluation framework that addresses…

Influence Functions for Efficient Data Selection in Reasoning
Prateek Humane, Paolo Cudrano, Daniel Z. Kaplan, Matteo Matteucci, Supriyo Chakraborty, Irina Rish
https://arxiv.org/abs/2510.06108

Influence Functions for Efficient Data Selection in Reasoning
Fine-tuning large language models (LLMs) on chain-of-thought (CoT) data shows that a small amount of high-quality data can outperform massive datasets. Yet, what constitutes "quality" remains ill-defined. Existing reasoning methods rely on indirect heuristics such as problem difficulty or trace length, while instruction-tuning has explored a broader range of automated selection strategies, but rarely in the context of reasoning. We propose to define reasoning data quality using influence functi…

The Physics of Data and Tasks: Theories of Locality and Compositionality in Deep Learning
Alessandro Favero
https://arxiv.org/abs/2510.06106 https://arxiv.…

The Physics of Data and Tasks: Theories of Locality and Compositionality in Deep Learning
Deep neural networks have achieved remarkable success, yet our understanding of how they learn remains limited. These models can learn high-dimensional tasks, which is generally statistically intractable due to the curse of dimensionality. This apparent paradox suggests that learnable data must have an underlying latent structure. What is the nature of this structure? How do neural networks encode and exploit it, and how does it quantitatively impact performance - for instance, how does general…

The Alignment Auditor: A Bayesian Framework for Verifying and Refining LLM Objectives
Matthieu Bou, Nyal Patel, Arjun Jagota, Satyapriya Krishna, Sonali Parbhoo
https://arxiv.org/abs/2510.06096

The Alignment Auditor: A Bayesian Framework for Verifying and Refining LLM Objectives
The objectives that Large Language Models (LLMs) implicitly optimize remain dangerously opaque, making trustworthy alignment and auditing a grand challenge. While Inverse Reinforcement Learning (IRL) can infer reward functions from behaviour, existing approaches either produce a single, overconfident reward estimate or fail to address the fundamental ambiguity of the task (non-identifiability). This paper introduces a principled auditing framework that re-frames reward inference from a simple e…

Learning from Failures: Understanding LLM Alignment through Failure-Aware Inverse RL
Nyal Patel, Matthieu Bou, Arjun Jagota, Satyapriya Krishna, Sonali Parbhoo
https://arxiv.org/abs/2510.06092

Learning from Failures: Understanding LLM Alignment through Failure-Aware Inverse RL
Reinforcement Learning from Human Feedback (RLHF) aligns Large Language Models (LLMs) with human preferences, yet the underlying reward signals they internalize remain hidden, posing a critical challenge for interpretability and safety. Existing approaches attempt to extract these latent incentives using Inverse Reinforcement Learning (IRL), but treat all preference pairs equally, often overlooking the most informative signals: those examples the extracted reward model misclassifies or assigns …

Learning Mixtures of Linear Dynamical Systems (MoLDS) via Hybrid Tensor-EM Method
Lulu Gong, Shreya Saxena
https://arxiv.org/abs/2510.06091 https://arxiv.o…

Learning Mixtures of Linear Dynamical Systems (MoLDS) via Hybrid Tensor-EM Method
Mixtures of linear dynamical systems (MoLDS) provide a path to model time-series data that exhibit diverse temporal dynamics across trajectories. However, its application remains challenging in complex and noisy settings, limiting its effectiveness for neural data analysis. Tensor-based moment methods can provide global identifiability guarantees for MoLDS, but their performance degrades under noise and complexity. Commonly used expectation-maximization (EM) methods offer flexibility in fitting…

Benchmark It Yourself (BIY): Preparing a Dataset and Benchmarking AI Models for Scatterplot-Related Tasks
Jo\~ao Palmeiro, Diogo Duarte, Rita Costa, Pedro Bizarro
https://arxiv.org/abs/2510.06071

Benchmark It Yourself (BIY): Preparing a Dataset and Benchmarking AI Models for Scatterplot-Related Tasks
AI models are increasingly used for data analysis and visualization, yet benchmarks rarely address scatterplot-specific tasks, limiting insight into performance. To address this gap for one of the most common chart types, we introduce a synthetic, annotated dataset of over 18,000 scatterplots from six data generators and 17 chart designs, and a benchmark based on it. We evaluate proprietary models from OpenAI and Google using N-shot prompting on five distinct tasks derived from annotations of c…

Analyzing the Effect of Embedding Norms and Singular Values to Oversmoothing in Graph Neural Networks
Dimitrios Kelesis, Dimitris Fotakis, Georgios Paliouras
https://arxiv.org/abs/2510.06066

Analyzing the Effect of Embedding Norms and Singular Values to Oversmoothing in Graph Neural Networks
In this paper, we study the factors that contribute to the effect of oversmoothing in deep Graph Neural Networks (GNNs). Specifically, our analysis is based on a new metric (Mean Average Squared Distance - $MASED$) to quantify the extent of oversmoothing. We derive layer-wise bounds on $MASED$, which aggregate to yield global upper and lower distance bounds. Based on this quantification of oversmoothing, we further analyze the importance of two different properties of the model; namely the norm…

Edit-Based Flow Matching for Temporal Point Processes
David L\"udke, Marten Lienen, Marcel Kollovieh, Stephan G\"unnemann
https://arxiv.org/abs/2510.06050 https://

Edit-Based Flow Matching for Temporal Point Processes
Temporal point processes (TPPs) are a fundamental tool for modeling event sequences in continuous time, but most existing approaches rely on autoregressive parameterizations that are limited by their sequential sampling. Recent non-autoregressive, diffusion-style models mitigate these issues by jointly interpolating between noise and data through event insertions and deletions in a discrete Markov chain. In this work, we generalize this perspective and introduce an Edit Flow process for TPPs th…

BLISS: A Lightweight Bilevel Influence Scoring Method for Data Selection in Language Model Pretraining
Jie Hao, Rui Yu, Wei Zhang, Huixia Wang, Jie Xu, Mingrui Liu
https://arxiv.org/abs/2510.06048

BLISS: A Lightweight Bilevel Influence Scoring Method for Data Selection in Language Model Pretraining
Effective data selection is essential for pretraining large language models (LLMs), enhancing efficiency and improving generalization to downstream tasks. However, existing approaches often require leveraging external pretrained models, making it difficult to disentangle the effects of data selection from those of the external pretrained models. In addition, they often overlook the long-term impact of selected data if the model is trained to convergence, primarily due to the prohibitive cost of…

From Learning to Mastery: Achieving Safe and Efficient Real-World Autonomous Driving with Human-In-The-Loop Reinforcement Learning
Li Zeqiao, Wang Yijing, Wang Haoyu, Li Zheng, Li Peng, Liu Wenfei, Zuo Zhiqiang
https://arxiv.org/abs/2510.06038

From Learning to Mastery: Achieving Safe and Efficient Real-World Autonomous Driving with Human-In-The-Loop Reinforcement Learning
Autonomous driving with reinforcement learning (RL) has significant potential. However, applying RL in real-world settings remains challenging due to the need for safe, efficient, and robust learning. Incorporating human expertise into the learning process can help overcome these challenges by reducing risky exploration and improving sample efficiency. In this work, we propose a reward-free, active human-in-the-loop learning method called Human-Guided Distributional Soft Actor-Critic (H-DSAC). …

Fast Leave-One-Out Approximation from Fragment-Target Prevalence Vectors (molFTP) : From Dummy Masking to Key-LOO for Leakage-Free Feature Construction
Guillaume Godin
https://arxiv.org/abs/2510.06029 …

Fast Leave-One-Out Approximation from Fragment-Target Prevalence Vectors (molFTP) : From Dummy Masking to Key-LOO for Leakage-Free Feature Construction
We introduce molFTP (molecular fragment-target prevalence), a compact representation that delivers strong predictive performance. To prevent feature leakage across cross-validation folds, we implement a dummy-masking procedure that removes information about fragments present in the held-out molecules. We further show that key leave-one-out (key-loo) closely approximates true molecule-level leave-one-out (LOO), with deviation below 8% on our datasets. This enables near full data training while p…

Generalization of Gibbs and Langevin Monte Carlo Algorithms in the Interpolation Regime
Andreas Maurer, Erfan Mirzaei, Massimiliano Pontil
https://arxiv.org/abs/2510.06028 https…

Generalization of Gibbs and Langevin Monte Carlo Algorithms in the Interpolation Regime
The paper provides data-dependent bounds on the test error of the Gibbs algorithm in the overparameterized interpolation regime, where low training errors are also obtained for impossible data, such as random labels in classification. The bounds are stable under approximation with Langevin Monte Carlo algorithms. Experiments on the MNIST and CIFAR-10 datasets verify that the bounds yield nontrivial predictions on true labeled data and correctly upper bound the test error for random labels. Our …