Tootfinder

South Korea's AI textbook program, meant to personalize learning, was rolled back after just four months after complaints about inaccuracies and extra workload (Junhyup Kwon/Rest of World)
https://restofworld.org/2025/south-korea-ai-textbook/

AI-powered textbooks fail to make the grade in South Korea
South Korea’s AI learning program was rolled back after just four months following a backlash from teachers, students, and parents, underlining the challenges in embedding the technology in education.

Whistles have become a popular raid alert tool in cities across the country
– New Yorkers wear them around their necks to warn neighbors,
the people of New Orleans blast them outside ICE facilities
and Charlotte residents used them to ward off Customs and Border Protection officials.
While strongly associated with Chicago, the tactic is actually one that city organizers learned in part from groups in Los Angeles.
Its spread is illustrative of the many ways cit…

No sugarcoating The vOICe learning curve: "It's a mountain, not a molehill" https://nimerblogs.blogspot.com/2025/09/seeing-with-sound-my-adventures-in.html says another congenitally blind user of The vOICe. But compatibility with AI scene de…

'graphviz' is a suite of programs for drawing graphs (In the nodes/edges senses, rather than upwards and to the right sense) - and it uses a file format called 'dot'. Lots of things generate dot output (such as systemd-analyze I mentioned) and it's really easy to generate from scripts and things. 'dotty' is probably the most common program in the suite.
There are some newer formats and programs - but this one is probably the most universal.

Every week, Metacurity delivers our free and paid subscribers a run-down of the top infosec-related long reads we didn't have time for during the daily crush of cyber news.
This week's selection covers
--Massive surveillance in Mexico City leaves crime high,
--Workplace surveillance can harm workers,
--Machine learning privacy attacks are less effective in reality than they are in theory,
--LLMs produce more secure code when trained on flaw-free code,

Best infosec-related long reads for the week of 11/8/25
Massive surveillance in Mexico City leaves crime high, Workplace surveillance can harm workers, Machine learning privacy attacks are less effective in reality than they are in theory, LLMs produce more secure code when trained on flaw-free code, Three major kinds of bots cause web resource headaches

Research in Collaborative Learning Does Not Serve Cross-Silo Federated Learning in Practice
Kevin Kuo, Chhavi Yadav, Virginia Smith
https://arxiv.org/abs/2510.12595 https://

Research in Collaborative Learning Does Not Serve Cross-Silo Federated Learning in Practice
Cross-silo federated learning (FL) is a promising approach to enable cross-organization collaboration in machine learning model development without directly sharing private data. Despite growing organizational interest driven by data protection regulations such as GDPR and HIPAA, the adoption of cross-silo FL remains limited in practice. In this paper, we conduct an interview study to understand the practical challenges associated with cross-silo FL adoption. With interviews spanning a diverse …

Just read this long post on "the current state of Cara" https://cara.app/post/2e0d29d3-a57a-4b70-b0d0-9cefc15176ca
🤔 "Not having an algorithmically recommended feed is the biggest reason why people dropped off from Cara after we went viral. In a chronolog…

Jingna Zhang (@zemotion) | Cara - Artist Social & Portfolio Platform
About the current state of Cara— Hi all, I’d like to address some users' concerns about Cara’s stability, algorithms and reach, and why we don’t actively promote Cara and recruit new users. I have touched on most of these before through other posts, but I’ll like to go over the main points and put them in one place since they often come up as recurring questions: — Cara’s longevity/stability > "A few weeks ago, after learning how much Jingna was struggling with her personal l…

Tyler Booker trending towards return for Cowboys, talks learning during rehab process https://www.dallascowboys.com/news/tyler-booker-trending-towards-return-for-cowboys-talks-learning-during-rehab-process

🌡️ Taking the moon's temperature with beeswax
#moon

Taking the moon's temperature with beeswax
Sometimes space exploration doesn't go as planned. But even in failure, engineers can learn, adapt, and try again. One of the best ways to do that is to share the learning, and allow others to reproduce the work that might not have succeeded, allowing them to try again. A group from MIT's Space Enabled Research Group, part of its Media Lab, recently released a paper in Space Science Reviews that describes the design and testing results of a pair of passive sensors sent to the moon on the ill-fa…

Just learning that Untamed Youth put out a new album. It's been 27 years since their last one. Not that the band members haven't been super busy with other projects. Still, good to see this.
When I worked at a record store in college we had a guy named Derek come work with us for a few months. It wasn't til a few years later I learned he was Deke Dickerson.
#music

ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learning
Hanyang Chen, Mark Zhao, Rui Yang, Qinwei Ma, Ke Yang, Jiarui Yao, Kangrui Wang, Hao Bai, Zhenhailong Wang, Rui Pan, Mengchao Zhang, Jose Barreiros, Aykut Onol, ChengXiang Zhai, Heng Ji, Manling Li, Huan Zhang, Tong Zhang
https://arxiv…

ERA: Transforming VLMs into Embodied Agents via Embodied Prior Learning and Online Reinforcement Learning
Recent advances in embodied AI highlight the potential of vision language models (VLMs) as agents capable of perception, reasoning, and interaction in complex environments. However, top-performing systems rely on large-scale models that are costly to deploy, while smaller VLMs lack the necessary knowledge and skills to succeed. To bridge this gap, we present \textit{Embodied Reasoning Agent (ERA)}, a two-stage framework that integrates prior knowledge learning and online reinforcement learning …

Robot Learning: A Tutorial
Francesco Capuano, Caroline Pascal, Adil Zouitine, Thomas Wolf, Michel Aractingi
https://arxiv.org/abs/2510.12403 https://arxiv.…

Robot Learning: A Tutorial
Robot learning is at an inflection point, driven by rapid advancements in machine learning and the growing availability of large-scale robotics data. This shift from classical, model-based methods to data-driven, learning-based paradigms is unlocking unprecedented capabilities in autonomous systems. This tutorial navigates the landscape of modern robot learning, charting a course from the foundational principles of Reinforcement Learning and Behavioral Cloning to generalist, language-conditione…

The One-Year Jewish Studies Program at Paideia - The European Institute for Jewish Studies in Sweden
https://ift.tt/HxLXogs
Mining the Logs: Sources on Blue Humor URL …
via Input 4 RELCFP ht…

Detection of quantum information masking via machine learning
Sheng-Ao Mao, Lin Zhang, Bo Li
https://arxiv.org/abs/2510.12507 https://arxiv.org/pdf/2510.12…

Detection of quantum information masking via machine learning
Recently, machine learning has been widely applied in the field of quantum information, notably in tasks such as entanglement detection, steering characterization, and nonlocality verification. However, few studies have focused on utilizing machine learning to detect quantum information masking. In this work, we investigate supervised machine learning for detecting quantum information masking in both pure and mixed qubit states. For pure qubit states, we randomly generate the corresponding dens…

"The scene (“Hidden Figures”, 2016) ends with Mr. Stafford famously claiming “that’s old!” as if the Pythagorean theorem was suddenly not useful anymore after 3500 years… Mr. Stafford’s reaction is canonical and very appropriate; it is the same that most devs have upon learning the fact that COBOL is running most credit card transactions, or when frontend engineers discover that static or server-rendered HTML websites do not need 10 MB of JavaScript on the browser."

CoIRL-AD: Collaborative-Competitive Imitation-Reinforcement Learning in Latent World Models for Autonomous Driving
Xiaoji Zheng, Ziyuan Yang, Yanhao Chen, Yuhang Peng, Yuanrong Tang, Gengyuan Liu, Bokui Chen, Jiangtao Gong
https://arxiv.org/abs/2510.12560

CoIRL-AD: Collaborative-Competitive Imitation-Reinforcement Learning in Latent World Models for Autonomous Driving
End-to-end autonomous driving models trained solely with imitation learning (IL) often suffer from poor generalization. In contrast, reinforcement learning (RL) promotes exploration through reward maximization but faces challenges such as sample inefficiency and unstable convergence. A natural solution is to combine IL and RL. Moving beyond the conventional two-stage paradigm (IL pretraining followed by RL fine-tuning), we propose CoIRL-AD, a competitive dual-policy framework that enables IL an…

I'm slowly and entirely accidentally working my way through the canon of stuntman Loren Janes. (No relation as far as I've been able to determine.) The first time I saw his name was in the credits for Masters of the Universe leading into a show I'd videotaped; the most recent was in Escape from New York (today). Pretty sure the most famous film he worked in was Back to the Future, which I've seen *many* times, but haven't yet watched again since learning he was involved. …

Just finished "I'm Awful, Thanks" by Lara Pickle. A good story that serves as a guide to managing emotions, although it's actually a cute story too, not just framing for the mental health discussion.
That said, I feel like it doesn't get far enough into the details of accepting self-control as our only form of real control vs. understanding that some events outside our control aren't fair or are others' attacks, and trying to manage our own emotions as our only response is a disservice to ourselves and others. Even further, I suspect that the HR resolution depicted here, while not impossible, is less frequent than much worse outcomes, which is part of a larger pattern of systemic assaults on our mental health that aren't totally solvable with individual emotional regulation.
Sure, leveling up one's control of ones own emotions and learning to accept and manage a range of emotions is super useful and it's a good thing overall, but the systemic problems of late stage capitalism are real, and making it seem like everyone is responsible for managing their own mental health in the face of these problems helps avoid confronting them.
Still, it's a good book overall, with vibrant art and a well-structured plot.
#AmReading #ReadingNow

Artificial Intelligence for Optimal Learning: A Comparative Approach towards AI-Enhanced Learning Environments
Ananth Hariharan
https://arxiv.org/abs/2510.11755 https://

Artificial Intelligence for Optimal Learning: A Comparative Approach towards AI-Enhanced Learning Environments
In the rapidly evolving educational landscape, the integration of technology has shifted from an enhancement to a cornerstone of educational strategy worldwide. This transition is propelled by advancements in digital technology, especially the emergence of artificial intelligence as a crucial tool in learning environments. This research project critically evaluates the impact of three distinct educational settings: traditional educational methods without technological integration, those enhance…

Participants in the Learning for Action fellowship are gaining vital skills as they engage with climate solutions and expert insights, empowering them to tackle climate change effectively. https://www.terra.do/blog/answering-your-lfa-questions/

Answering Your LFA Questions
Terra.do's Learning for Action fellowship (LFA) is our flagship 12-week course. Here, we'll answer some common questions about the program.

Trying very hard to maintain my calm.
☑️ Hollywood stars, politicians pay tribute to Rob Reiner and his wife following their shocking deaths
Reiner, 78, was found dead alongside wife, Michele Singer Reiner, 68, at their home in Los Angeles on Sunday.
https://www.<…

Rob Reiner death: Tributes pour in for filmmaker and his wife, Michele
Hollywood luminaries and political heavyweights expressed their shock and sadness Sunday night upon learning that prolific director Rob Reiner and his wife, Michele Singer Reiner, were found dead in their Los Angeles home.

Coursera plans to acquire rival online education platform Udemy in an all-stock deal valued at $2.5B, combining two of the largest US learning platforms (Akash Sriram/Reuters)
https://www.reuters.com/business/coursera-udemy-merge-deal-v…

Dimension-Free Minimax Rates for Learning Pairwise Interactions in Attention-Style Models
Shai Zucker, Xiong Wang, Fei Lu, Inbar Seroussi
https://arxiv.org/abs/2510.11789 https:…

Dimension-Free Minimax Rates for Learning Pairwise Interactions in Attention-Style Models
We study the convergence rate of learning pairwise interactions in single-layer attention-style models, where tokens interact through a weight matrix and a non-linear activation function. We prove that the minimax rate is $M^{-\frac{2β}{2β+1}}$ with $M$ being the sample size, depending only on the smoothness $β$ of the activation, and crucially independent of token count, ambient dimension, or rank of the weight matrix. These results highlight a fundamental dimension-free statistical efficie…

Learning interpretable closures for thermal radiation transport in optically-thin media using WSINDy
Daniel Messenger, Ben Southworth, Hans Hammer, Luis Chacon
https://arxiv.org/abs/2510.11840

Learning interpretable closures for thermal radiation transport in optically-thin media using WSINDy
We introduce an equation learning framework to identify a closed set of equations for moment quantities in 1D thermal radiation transport (TRT) in optically thin media. While optically thick media admits a well-known diffusive closure, the utility of moment closures in providing accurate low-dimensional surrogates for TRT in optically thin media is unclear, as the mean-free path of photons is large and the radiation flux is far from its Fickean limit. Here, we demonstrate the viability of using…

We have a lot of "home-schooled" children in our neighborhood, and all I hear is constant screams of bloody murder throughout the day.
I'm pretty sure they are learning nothing.

Week 11 NFL player props, picks, odds: Back Matthew Stafford Under 278.5 passing yards in Sunday NFL prop bets

https://www.cbssports.com/nfl/news/week-11-nf…

Demystifying Reinforcement Learning in Agentic Reasoning
Zhaochen Yu, Ling Yang, Jiaru Zou, Shuicheng Yan, Mengdi Wang
https://arxiv.org/abs/2510.11701 https://

Demystifying Reinforcement Learning in Agentic Reasoning
Recently, the emergence of agentic RL has showcased that RL could also effectively improve the agentic reasoning ability of LLMs, yet the key design principles and optimal practices remain unclear. In this work, we conduct a comprehensive and systematic investigation to demystify reinforcement learning in agentic reasoning from three key perspectives: data, algorithm, and reasoning mode. We highlight our key insights: (i) Replacing stitched synthetic trajectories with real end-to-end tool-use t…

FLAMMABLE: A Multi-Model Federated Learning Framework with Multi-Model Engagement and Adaptive Batch Sizes
Shouxu Lin, Zimeng Pan, Yuhang Yao, Haeyoung Noh, Pei Zhang, Carlee Joe-Wong
https://arxiv.org/abs/2510.10380

FLAMMABLE: A Multi-Model Federated Learning Framework with Multi-Model Engagement and Adaptive Batch Sizes
Multi-Model Federated Learning (MMFL) is an emerging direction in Federated Learning (FL) where multiple models are trained in parallel, generally on various datasets. Optimizing the models' accuracies and training times in the MMFL setting requires adapting to data and system heterogeneity across clients as in single-model FL; these challenges are amplified in the MMFL setting due to additional heterogeneity across models. Neither existing solutions nor naïve extensions of single-model FL fra…

Optimal Pair Matching Combined with Machine Learning Predicts a Significant Reduction in Myocardial Infarction Risk in African Americans following Omega-3 Fatty Acid Supplementation
Shudong Sun, Aki Hara, Laurel Johnstone, Brian Hallmark, Joseph C. Watkins, Cynthia A. Thomson, Susan M. Schembre, Susan Sergeant, Jason Umans, Guang Yao, Hao Helen Zhang, Floyd H. Chilton

Optimal Pair Matching Combined with Machine Learning Predicts a Significant Reduction in Myocardial Infarction Risk in African Americans following Omega-3 Fatty Acid Supplementation
Conflicting clinical trial results on omega-3 highly unsaturated fatty acids (n-3 HUFA) have prompted uncertainty about their cardioprotective effects. While the VITAL trial found no overall cardiovascular benefit from n-3 HUFA supplementation, its substantial African American (AfAm) enrollment provided a unique opportunity to explore racial differences in response to n-3 HUFA supplementation. The current observational study aimed to simulate randomized clinical trial (RCT) conditions by matchi…

Attack-Specialized Deep Learning with Ensemble Fusion for Network Anomaly Detection
Nisith Dissanayake (University of Moratuwa), Uthayasanker Thayasivam (University of Moratuwa)
https://arxiv.org/abs/2510.12455

Attack-Specialized Deep Learning with Ensemble Fusion for Network Anomaly Detection
The growing scale and sophistication of cyberattacks pose critical challenges to network security, particularly in detecting diverse intrusion types within imbalanced datasets. Traditional intrusion detection systems (IDS) often struggle to maintain high accuracy across both frequent and rare attacks, leading to increased false negatives for minority classes. To address this, we propose a hybrid anomaly detection framework that integrates specialized deep learning models with an ensemble meta-c…

eye2vec: Learning Distributed Representations of Eye Movement for Program Comprehension Analysis
Haruhiko Yoshioka, Kazumasa Shimari, Hidetake Uwano, Kenichi Matsumoto
https://arxiv.org/abs/2510.11722 …

eye2vec: Learning Distributed Representations of Eye Movement for Program Comprehension Analysis
This paper presents eye2vec, an infrastructure for analyzing software developers' eye movements while reading source code. In common eye-tracking studies in program comprehension, researchers must preselect analysis targets such as control flow or syntactic elements, and then develop analysis methods to extract appropriate metrics from the fixation for source code. Here, researchers can define various levels of AOIs like words, lines, or code blocks, and the difference leads to different result…

Expert or not? assessing data quality in offline reinforcement learning
Arip Asadulaev, Fakhri Karray, Martin Takac
https://arxiv.org/abs/2510.12638 https://

Expert or not? assessing data quality in offline reinforcement learning
Offline reinforcement learning (RL) learns exclusively from static datasets, without further interaction with the environment. In practice, such datasets vary widely in quality, often mixing expert, suboptimal, and even random trajectories. The choice of algorithm therefore depends on dataset fidelity. Behavior cloning can suffice on high-quality data, whereas mixed- or low-quality data typically benefits from offline RL methods that stitch useful behavior across trajectories. Yet in the wild i…

We worry, quite rigthly, about the Gaza Genocide and Trump bombing ships on the high seas yet at the same time Sam Altman is doing systemic harm to the rest of the world unchecked.
"Pupils fear that using artificial intelligence is eroding their ability to study, with many complaining it makes schoolwork “too easy” and others saying it limits their creativity and stops them learning new skills, according to new research.
The report on the use of AI in UK schools, commissione…

A Hierarchical Quantized Tokenization Framework for Task-Adaptive Graph Representation Learning
Yang Xiang, Li Fan, Chenke Yin, Chengtao Ji
https://arxiv.org/abs/2510.12369 http…

A Hierarchical Quantized Tokenization Framework for Task-Adaptive Graph Representation Learning
Recent progress in language and vision foundation models demonstrates the importance of discrete token interfaces that transform complex inputs into compact sequences for large-scale modeling. Extending this paradigm to graphs requires a tokenization scheme that handles non-Euclidean structures and multi-scale dependencies efficiently. Existing approaches to graph tokenization, linearized, continuous, and quantized, remain limited in adaptability and efficiency. In particular, most current quan…

Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning
Simin Li, Zihao Mao, Hanxiao Li, Zonglei Jing, Zhuohang bian, Jun Guo, Li Wang, Zhuoran Han, Ruixiao Xu, Xin Yu, Chengdong Ma, Yuqing Ma, Bo An, Yaodong Yang, Weifeng Lv, Xianglong Liu
https://arxiv.org/abs/2510.11824

Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning
In cooperative Multi-Agent Reinforcement Learning (MARL), it is a common practice to tune hyperparameters in ideal simulated environments to maximize cooperative performance. However, policies tuned for cooperation often fail to maintain robustness and resilience under real-world uncertainties. Building trustworthy MARL systems requires a deep understanding of robustness, which ensures stability under uncertainties, and resilience, the ability to recover from disruptions--a concept extensively …

Based on Deep Neural Networks: A Machine Learning-Assisted Channel Estimation Method for MIMO Systems
Haoran He
https://arxiv.org/abs/2510.11891 https://ar…

Based on Deep Neural Networks: A Machine Learning-Assisted Channel Estimation Method for MIMO Systems
This paper proposes a machine learning-assisted channel estimation approach for massive MIMO systems, leveraging DNNs to outperform traditional LS and MMSE methods. In 5G and beyond, accurate channel estimation mitigates pilot contamination and high mobility issues that harm system reliability. The proposed DNN architecture includes multi-layer perceptrons with ReLU activation, 3 hidden layers (256, 128, 64 neurons respectively), uses Adam optimizer (learning rate 1e-4) and MSE loss function. I…

Data-Model Co-Evolution: Growing Test Sets to Refine LLM Behavior
Minjae Lee, Minsuk Kahng
https://arxiv.org/abs/2510.12728 https://arxiv.org/pdf/2510.1272…

Data-Model Co-Evolution: Growing Test Sets to Refine LLM Behavior
A long-standing challenge in machine learning has been the rigid separation between data work and model refinement, enforced by slow fine-tuning cycles. The rise of Large Language Models (LLMs) overcomes this historical barrier, allowing applications developers to instantly govern model behavior by editing prompt instructions. This shift enables a new paradigm: data-model co-evolution, where a living test set and a model's instructions evolve in tandem. We operationalize this paradigm in an int…

Spectropolarimetric Inversion in Four Dimensions with Deep Learning (SPIn4D): II. A Physics-Informed Machine Learning Method for 3D Solar Photosphere Reconstruction
Kai E. Yang, Xudong Sun, Lucas A. Tarr, Jiayi Liu, Peter Sadowski, S. Curt Dodds, Matthias Rempel, Sarah A. Jaeggli, Thomas A. Schad, Ian Cunnyngham, Yannik Glaser, Linnea Wolniewicz
https://…

Spectropolarimetric Inversion in Four Dimensions with Deep Learning (SPIn4D): II. A Physics-Informed Machine Learning Method for 3D Solar Photosphere Reconstruction
Inferring the three-dimensional (3D) solar atmospheric structures from observations is a critical task for advancing our understanding of the magnetic fields and electric currents that drive solar activity. In this work, we introduce a novel, Physics-Informed Machine Learning method to reconstruct the 3D structure of the lower solar atmosphere based on the output of optical depth sampled spectropolarimetric inversions, wherein both the fully disambiguated vector magnetic fields and the geometri…

The One-Year Jewish Studies Program at Paideia - The European Institute for Jewish Studies in Sweden https://networks.h-net.org/group/announcements/20134939/one-year-jewish-studies-program-paideia-european-institute-jewish

Hybrid Explanation-Guided Learning for Transformer-Based Chest X-Ray Diagnosis
Shelley Zixin Shu, Haozhe Luo, Alexander Poellinger, Mauricio Reyes
https://arxiv.org/abs/2510.12704

Hybrid Explanation-Guided Learning for Transformer-Based Chest X-Ray Diagnosis
Transformer-based deep learning models have demonstrated exceptional performance in medical imaging by leveraging attention mechanisms for feature representation and interpretability. However, these models are prone to learning spurious correlations, leading to biases and limited generalization. While human-AI attention alignment can mitigate these issues, it often depends on costly manual supervision. In this work, we propose a Hybrid Explanation-Guided Learning (H-EGL) framework that combines…

Robust Exploratory Stopping under Ambiguity in Reinforcement Learning
Junyan Ye, Hoi Ying Wong, Kyunghyun Park
https://arxiv.org/abs/2510.10260 https://arx…

Robust Exploratory Stopping under Ambiguity in Reinforcement Learning
We propose and analyze a continuous-time robust reinforcement learning framework for optimal stopping problems under ambiguity. In this framework, an agent chooses a stopping rule motivated by two objectives: robust decision-making under ambiguity and learning about the unknown environment. Here, ambiguity refers to considering multiple probability measures dominated by a reference measure, reflecting the agent's awareness that the reference measure representing her learned belief about the env…

Normalization-equivariant Diffusion Models: Learning Posterior Samplers From Noisy And Partial Measurements
Brett Levac, Jon Tamir, Marcelo Pereyra, Julian Tachella
https://arxiv.org/abs/2510.11964

Normalization-equivariant Diffusion Models: Learning Posterior Samplers From Noisy And Partial Measurements
Diffusion models (DMs) have rapidly emerged as a powerful framework for image generation and restoration. However, existing DMs are primarily trained in a supervised manner by using a large corpus of clean images. This reliance on clean data poses fundamental challenges in many real-world scenarios, where acquiring noise-free data is hard or infeasible, and only noisy and potentially incomplete measurements are available. While some methods can train DMs using noisy data, they are generally eff…

Pretraining in Actor-Critic Reinforcement Learning for Robot Motion Control
Jiale Fan, Andrei Cramariuc, Tifanny Portela, Marco Hutter
https://arxiv.org/abs/2510.12363 https://

Pretraining in Actor-Critic Reinforcement Learning for Robot Motion Control
The pretraining-finetuning paradigm has facilitated numerous transformative advancements in artificial intelligence research in recent years. However, in the domain of reinforcement learning (RL) for robot motion control, individual skills are often learned from scratch despite the high likelihood that some generalizable knowledge is shared across all task-specific policies belonging to a single robot embodiment. This work aims to define a paradigm for pretraining neural network models that enc…

just released liboprf-0.9.3
liboprf is a library implementing the OPRF from https://www.rfc-editor.org/rfc/rfc9497.html and in addition it also provides a threshold variant (tOPRF) and a distributed key generation (DKG) protocol for the tOPRF shared secret, as well as a key update protocol fo…

In other news, today was my first day learning to use a microINR device, intended to monitor my blood anticoagulation levels. The INR, or International Normalized Ratio, is a measure of how long it takes your blood to clot.

So basically this is what I do:

1. Wash my hands, make sure they’re warm and dry.
2. Take a chip (or test strip) and insert it into the device.
3. The device powers on and I wait until it is ready (it has to heat up to a certain temperature)
4.…

SDGraph: Multi-Level Sketch Representation Learning by Sparse-Dense Graph Architecture
Xi Cheng, Pingfa Feng, Zhichao Liao, Mingyu Fan, Long Zeng
https://arxiv.org/abs/2510.12192

SDGraph: Multi-Level Sketch Representation Learning by Sparse-Dense Graph Architecture
Freehand sketches exhibit unique sparsity and abstraction, necessitating learning pipelines distinct from those designed for images. For sketch learning methods, the central objective is to fully exploit the effective information embedded in sketches. However, there is limited research on what constitutes effective sketch information, which in turn constrains the performance of existing approaches. To tackle this issue, we first proposed the Multi-Level Sketch Representation Scheme to systemati…

Self-attention enabled quantum path analysis of high-harmonic generation in solids
Cong Zhao, Xiaozhou Zou
https://arxiv.org/abs/2510.12443 https://arxiv.o…

Self-attention enabled quantum path analysis of high-harmonic generation in solids
High-harmonic generation (HHG) in solids provides a powerful platform to probe ultrafast electron dynamics and interband--intraband coupling. However, disentangling the complex many-body contributions in the HHG spectrum remains challenging. Here we introduce a machine-learning approach based on a Transformer encoder to analyze and reconstruct HHG signals computed from a one-dimensional Kronig--Penney model. The self-attention mechanism inherently highlights correlations between temporal dipole…

Beyond the Brightest: A Deep Learning Approach to Identifying Major and Minor Galaxy Mergers in CANDELS at $z \sim 1$
Aimee L. Schechter, Aleksandra \'Ciprijanovi\'c, Xuejian Shen, Rebecca Nevin, Julia M. Comerford, Aaron Stemo, Laura Blecha, Austin Fraley
https://arxiv.org/abs/2510.12173

Beyond the Brightest: A Deep Learning Approach to Identifying Major and Minor Galaxy Mergers in CANDELS at $z \sim 1$
Galaxy mergers play an important role in many aspects of galaxy evolution, therefore, more accurate merger identifications are paramount for achieving a complete understanding of galaxy evolution. As we enter the era of very large imaging surveys, we are able to observe mergers extending to even lower masses and higher redshifts. Despite low-mass galaxies being more common, many previous merger identification methods were mostly calibrated for high-mass, local galaxies, which are easier to iden…

Inclusive Fitness as a Key Step Towards More Advanced Social Behaviors in Multi-Agent Reinforcement Learning Settings
Andries Rosseau, Rapha\"el Avalos, Ann Now\'e
https://arxiv.org/abs/2510.12555

Inclusive Fitness as a Key Step Towards More Advanced Social Behaviors in Multi-Agent Reinforcement Learning Settings
The competitive and cooperative forces of natural selection have driven the evolution of intelligence for millions of years, culminating in nature's vast biodiversity and the complexity of human minds. Inspired by this process, we propose a novel multi-agent reinforcement learning framework where each agent is assigned a genotype and where reward functions are modelled after the concept of inclusive fitness. An agent's genetic material may be shared with other agents, and our inclusive reward f…

Day 22: Yuki Urushibara
I've got a few more mangaka left on my short list, and might very well get to at least one more, but Urushibara is the author of Mushishi and anyone who knows either the manga or anime understands immediately why she appears here.
Mushishi is a "seinen" anime, which means it's written for adults, not children or teenagers (although it's very accessible for all ages). It deals with a vast array of life's circumstances through the lens of a traveling mushi expert and the various whimsical supernatural creatures he is called on to deal with. He's not an exorcist though, instead understanding that humans must live in harmony with the mushi, and working like an ecologist to sort things out. As is probably obvious, Urushibara is an incredible world-builder; she's also a top-notch artist and above all, her stories are overflowing with kindness, humanity, and respect for the natural world.
Besides Mushishi, I've read "Suiiki", and it's one of the few manga I stumbled through in the original Japanese, which says a lot given my limited reading vocabulary (and the fact that it doesn't include rubi). It weaves the supernatural into a story of childhood innocence and curiosity in a lovely way.
Much like Shirahama who I mentioned earlier, Urushibara's stories are full of gentle wisdom for all ages, but Urushibara's work is quieter and less dramatic, with an adult main character confident in his expertise instead of a young-and-learning protagonist.
#30AuthorsNoMen

Statistical Guarantees for High-Dimensional Stochastic Gradient Descent
Jiaqi Li, Zhipeng Lou, Johannes Schmidt-Hieber, Wei Biao Wu
https://arxiv.org/abs/2510.12013 https://

Statistical Guarantees for High-Dimensional Stochastic Gradient Descent
Stochastic Gradient Descent (SGD) and its Ruppert-Polyak averaged variant (ASGD) lie at the heart of modern large-scale learning, yet their theoretical properties in high-dimensional settings are rarely understood. In this paper, we provide rigorous statistical guarantees for constant learning-rate SGD and ASGD in high-dimensional regimes. Our key innovation is to transfer powerful tools from high-dimensional time series to online learning. Specifically, by viewing SGD as a nonlinear autoregres…

PubSub-VFL: Towards Efficient Two-Party Split Learning in Heterogeneous Environments via Publisher/Subscriber Architecture
Yi Liu, Yang Liu, Leqian Zheng, Jue Hong, Junjie Shi, Qingyou Yang, Ye Wu, Cong Wang
https://arxiv.org/abs/2510.12494

PubSub-VFL: Towards Efficient Two-Party Split Learning in Heterogeneous Environments via Publisher/Subscriber Architecture
With the rapid advancement of the digital economy, data collaboration between organizations has become a well-established business model, driving the growth of various industries. However, privacy concerns make direct data sharing impractical. To address this, Two-Party Split Learning (a.k.a. Vertical Federated Learning (VFL)) has emerged as a promising solution for secure collaborative learning. Despite its advantages, this architecture still suffers from low computational resource utilization…

Tracing Multilingual Knowledge Acquisition Dynamics in Domain Adaptation: A Case Study of English-Japanese Biomedical Adaptation
Xin Zhao, Naoki Yoshinaga, Yuma Tsuta, Akiko Aizawa
https://arxiv.org/abs/2510.12115

Tracing Multilingual Knowledge Acquisition Dynamics in Domain Adaptation: A Case Study of English-Japanese Biomedical Adaptation
Multilingual domain adaptation (ML-DA) is widely used to learn new domain knowledge across languages into large language models (LLMs). Although many methods have been proposed to improve domain adaptation, the mechanisms of multilingual knowledge acquisition, how domain knowledge is learned within a language and transferred across languages, remain underexplored. This gap leads to suboptimal performance, particularly in low-resource settings. This work examines the learning dynamics of LLMs du…

PET Head Motion Estimation Using Supervised Deep Learning with Attention
Zhuotong Cai, Tianyi Zeng, Jiazhen Zhang, El\'eonore V. Lieffrig, Kathryn Fontaine, Chenyu You, Enette Mae Revilla, James S. Duncan, Jingmin Xin, Yihuan Lu, John A. Onofrey
https://arxiv.org/abs/2510.12758

PET Head Motion Estimation Using Supervised Deep Learning with Attention
Head movement poses a significant challenge in brain positron emission tomography (PET) imaging, resulting in image artifacts and tracer uptake quantification inaccuracies. Effective head motion estimation and correction are crucial for precise quantitative image analysis and accurate diagnosis of neurological disorders. Hardware-based motion tracking (HMT) has limited applicability in real-world clinical practice. To overcome this limitation, we propose a deep-learning head motion correction a…

The whole app is a blob
... character driven UI as a path to language learning, a different kind of "gamification"
#software

The Whole App is a Blob
I tried to prepare for life in French-speaking Canada by turning language drills into a Tamagotchi. It worked, as long as you don't ask me whether my coffee is for here or to go.

Prismo: A Decision Support System for Privacy-Preserving ML Framework Selection
Nges Brian Njungle, Eric Jahns, Luigi Mastromauro, Edwin P. Kayang, Milan Stojkov, Michel A. Kinsy
https://arxiv.org/abs/2510.09985

Prismo: A Decision Support System for Privacy-Preserving ML Framework Selection
Machine learning has become a crucial part of our lives, with applications spanning nearly every aspect of our daily activities. However, using personal information in machine learning applications has sparked significant security and privacy concerns about user data. To address these challenges, different privacy-preserving machine learning (PPML) frameworks have been developed to protect sensitive information in machine learning applications. These frameworks generally attempt to balance desi…

Generative Data Augmentation in Graph Contrastive Learning for Recommendation
Yansong Wang, Qihui Lin, Junjie Huang, Tao Jia
https://arxiv.org/abs/2510.09129 https://

Generative Data Augmentation in Graph Contrastive Learning for Recommendation
Recommendation systems have become indispensable in various online platforms, from e-commerce to streaming services. A fundamental challenge in this domain is learning effective embeddings from sparse user-item interactions. While contrastive learning has recently emerged as a promising solution to this issue, generating augmented views for contrastive learning through most existing random data augmentation methods often leads to the alteration of original semantic information. In this paper, w…

GlobalizeEd: A Multimodal Translation System that Preserves Speaker Identity in Academic Lectures
Hoang-Son Vo, Karina Kolmogortseva, Ngumimi Karen Iyortsuun, Hong-Duyen Vo, Soo-Hyung Kim
https://arxiv.org/abs/2510.11596

GlobalizeEd: A Multimodal Translation System that Preserves Speaker Identity in Academic Lectures
A large amount of valuable academic content is only available in its original language, creating a significant access barrier for the global student community. This is a challenge for translating in several subjects, such as history, culture, and the arts, where current automated subtitle tools fail to convey the appropriate pedagogical tone and specialized meaning. In addition, reading traditional automated subtitles increases cognitive load and leads to a disconnected learning experience. Thr…

Hierarchical Federated Learning for Crop Yield Prediction in Smart Agricultural Production Systems
Anas Abouaomar, Mohammed El hanjri, Abdellatif Kobbane, Anis Laouiti, Khalid Nafil
https://arxiv.org/abs/2510.12727

Hierarchical Federated Learning for Crop Yield Prediction in Smart Agricultural Production Systems
In this paper, we presents a novel hierarchical federated learning architecture specifically designed for smart agricultural production systems and crop yield prediction. Our approach introduces a seasonal subscription mechanism where farms join crop-specific clusters at the beginning of each agricultural season. The proposed three-layer architecture consists of individual smart farms at the client level, crop-specific aggregators at the middle layer, and a global model aggregator at the top le…

$\mathbf{T^3}$: Reducing Belief Deviation in Reinforcement Learning for Active Reasoning
Deyu Zou, Yongqiang Chen, Jianxiang Wang, Haochen Yang, Mufei Li, James Cheng, Pan Li, Yu Gong
https://arxiv.org/abs/2510.12264

$\mathbf{T^3}$: Reducing Belief Deviation in Reinforcement Learning for Active Reasoning
Active reasoning requires large language models (LLMs) to interact with external sources and strategically gather information to solve problems. Central to this process is belief tracking: maintaining a coherent understanding of the problem state and the missing information toward the solution. However, due to limited reasoning capabilities, LLM-based agents often suffer from belief deviation: they struggle to correctly model beliefs, lose track of problem states, and fall into uninformative or…

Can Representation Gaps Be the Key to Enhancing Robustness in Graph-Text Alignment?
Heng Zhang, Tianyi Zhang, Yuling Shi, Xiaodong Gu, Yaomin Shen, Zijian Zhang, Yilei Yuan, Hao Zhang, Jin Huang
https://arxiv.org/abs/2510.12087

Can Representation Gaps Be the Key to Enhancing Robustness in Graph-Text Alignment?
Representation learning on text-attributed graphs (TAGs) integrates structural connectivity with rich textual semantics, enabling applications in diverse domains. Current methods largely rely on contrastive learning to maximize cross-modal similarity, assuming tighter coupling between graph and text representations improves transfer performance. However, our empirical analysis reveals that both natural gap expansion and forced gap reduction result in performance degradation by disrupting pre-tr…

Wireless Channel Modeling for Machine Learning -- A Critical View on Standardized Channel Models
Benedikt B\"ock, Amar Kasibovic, Wolfgang Utschick
https://arxiv.org/abs/2510.12279

Wireless Channel Modeling for Machine Learning -- A Critical View on Standardized Channel Models
Standardized (link-level) channel models such as the 3GPP TDL and CDL models are frequently used to evaluate machine learning (ML)-based physical-layer methods. However, in this work, we argue that a link-level perspective incorporates limiting assumptions, causing unwanted distributional shifts or necessitating impractical online training. An additional drawback is that this perspective leads to (near-)Gaussian channel characteristics. Thus, ML-based models, trained on link-level channel data,…

Learning Latent Energy-Based Models via Interacting Particle Langevin Dynamics
Joanna Marks, Tim Y. J. Wang, O. Deniz Akyildiz
https://arxiv.org/abs/2510.12311 https://

Learning Latent Energy-Based Models via Interacting Particle Langevin Dynamics
We develop interacting particle algorithms for learning latent variable models with energy-based priors. To do so, we leverage recent developments in particle-based methods for solving maximum marginal likelihood estimation (MMLE) problems. Specifically, we provide a continuous-time framework for learning latent energy-based models, by defining stochastic differential equations (SDEs) that provably solve the MMLE problem. We obtain a practical algorithm as a discretisation of these SDEs and pro…

A Task-Efficient Reinforcement Learning Task-Motion Planner for Safe Human-Robot Cooperation
Gaoyuan Liu, Joris de Winter, Kelly Merckaert, Denis Steckelmacher, Ann Nowe, Bram Vanderborght
https://arxiv.org/abs/2510.12477

A Task-Efficient Reinforcement Learning Task-Motion Planner for Safe Human-Robot Cooperation
In a Human-Robot Cooperation (HRC) environment, safety and efficiency are the two core properties to evaluate robot performance. However, safety mechanisms usually hinder task efficiency since human intervention will cause backup motions and goal failures of the robot. Frequent motion replanning will increase the computational load and the chance of failure. In this paper, we present a hybrid Reinforcement Learning (RL) planning framework which is comprised of an interactive motion planner and …

EReLiFM: Evidential Reliability-Aware Residual Flow Meta-Learning for Open-Set Domain Generalization under Noisy Labels
Kunyu Peng, Di Wen, Kailun Yang, Jia Fu, Yufan Chen, Ruiping Liu, Jiamin Wu, Junwei Zheng, M. Saquib Sarfraz, Luc Van Gool, Danda Pani Paudel, Rainer Stiefelhagen
https://arxiv.org/abs/2510.12687

EReLiFM: Evidential Reliability-Aware Residual Flow Meta-Learning for Open-Set Domain Generalization under Noisy Labels
Open-Set Domain Generalization (OSDG) aims to enable deep learning models to recognize unseen categories in new domains, which is crucial for real-world applications. Label noise hinders open-set domain generalization by corrupting source-domain knowledge, making it harder to recognize known classes and reject unseen ones. While existing methods address OSDG under Noisy Labels (OSDG-NL) using hyperbolic prototype-guided meta-learning, they struggle to bridge domain gaps, especially with limited…

Learning-To-Measure: In-context Active Feature Acquisition
Yuta Kobayashi, Zilin Jing, Jiayu Yao, Hongseok Namkoong, Shalmali Joshi
https://arxiv.org/abs/2510.12624 https://

Learning-To-Measure: In-context Active Feature Acquisition
Active feature acquisition (AFA) is a sequential decision-making problem where the goal is to improve model performance for test instances by adaptively selecting which features to acquire. In practice, AFA methods often learn from retrospective data with systematic missingness in the features and limited task-specific labels. Most prior work addresses acquisition for a single predetermined task, limiting scalability. To address this limitation, we formalize the meta-AFA problem, where the goal…

The One-Year Jewish Studies Program at Paideia - The European Institute for Jewish Studies in Sweden
https://ift.tt/paWSE3r
Mining the Logs: Sources on Blue Humor URL …
via Input 4 RELCFP ht…

DPO-Tuned Large Language Models for Segmentation in Simultaneous Speech Translation
Zeyu Yang, Satoshi Nakamura
https://arxiv.org/abs/2510.12195 https://ar…

DPO-Tuned Large Language Models for Segmentation in Simultaneous Speech Translation
Simultaneous speech translation requires accurate segmentation to balance translation quality and latency. Recent studies such as SHAS have introduced pretrained segmentation models, achieving stronger performance than heuristic rules. However, segmentation models such as SHAS, though pretrained and more robust than heuristic methods, are still constrained by supervised learning objectives and do not incorporate human preference alignment, which is crucial for natural real-time interpretation. …

Towards Robust Artificial Intelligence: Self-Supervised Learning Approach for Out-of-Distribution Detection
Wissam Salhab, Darine Ameyed, Hamid Mcheick, Fehmi Jaafar
https://arxiv.org/abs/2510.12713

Towards Robust Artificial Intelligence: Self-Supervised Learning Approach for Out-of-Distribution Detection
Robustness in AI systems refers to their ability to maintain reliable and accurate performance under various conditions, including out-of-distribution (OOD) samples, adversarial attacks, and environmental changes. This is crucial in safety-critical systems, such as autonomous vehicles, transportation, or healthcare, where malfunctions could have severe consequences. This paper proposes an approach to improve OOD detection without the need of labeled data, thereby increasing the AI systems' robu…

Universal Adaptive Environment Discovery
Madi Matymov, Ba-Hien Tran, Maurizio Filippone
https://arxiv.org/abs/2510.12547 https://arxiv.org/pdf/2510.12547…

Universal Adaptive Environment Discovery
An open problem in Machine Learning is how to avoid models to exploit spurious correlations in the data; a famous example is the background-label shortcut in the Waterbirds dataset. A common remedy is to train a model across multiple environments; in the Waterbirds dataset, this corresponds to training by randomizing the background. However, selecting the right environments is a challenging problem, given that these are rarely known a priori. We propose Universal Adaptive Environment Discovery …

Autonomous Legged Mobile Manipulation for Lunar Surface Operations via Constrained Reinforcement Learning
Alvaro Belmonte-Baeza, Miguel Cazorla, Gabriel J. Garc\'ia, Carlos J. P\'erez-Del-Pulgar, Jorge Pomares
https://arxiv.org/abs/2510.12684

Autonomous Legged Mobile Manipulation for Lunar Surface Operations via Constrained Reinforcement Learning
Robotics plays a pivotal role in planetary science and exploration, where autonomous and reliable systems are crucial due to the risks and challenges inherent to space environments. The establishment of permanent lunar bases demands robotic platforms capable of navigating and manipulating in the harsh lunar terrain. While wheeled rovers have been the mainstay for planetary exploration, their limitations in unstructured and steep terrains motivate the adoption of legged robots, which offer super…

How Reinforcement Learning After Next-Token Prediction Facilitates Learning
Nikolaos Tsilivis, Eran Malach, Karen Ullrich, Julia Kempe
https://arxiv.org/abs/2510.11495 https://

How Reinforcement Learning After Next-Token Prediction Facilitates Learning
Recent advances in reasoning domains with neural networks have primarily been enabled by a training recipe that optimizes Large Language Models, previously trained to predict the next-token in a sequence, with reinforcement learning algorithms. We introduce a framework to study the success of this paradigm, and we theoretically expose the optimization mechanisms by which reinforcement learning improves over next-token prediction in this setting. We study learning from mixture distributions of s…

E-MoFlow: Learning Egomotion and Optical Flow from Event Data via Implicit Regularization
Wenpu Li, Bangyan Liao, Yi Zhou, Qi Xu, Pian Wan, Peidong Liu
https://arxiv.org/abs/2510.12753

E-MoFlow: Learning Egomotion and Optical Flow from Event Data via Implicit Regularization
The estimation of optical flow and 6-DoF ego-motion, two fundamental tasks in 3D vision, has typically been addressed independently. For neuromorphic vision (e.g., event cameras), however, the lack of robust data association makes solving the two problems separately an ill-posed challenge, especially in the absence of supervision via ground truth. Existing works mitigate this ill-posedness by either enforcing the smoothness of the flow field via an explicit variational regularizer or leveraging…

Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory
Einar Urdshals, Edmund Lau, Jesse Hoogland, Stan van Wingerden, Daniel Murfet
https://arxiv.org/abs/2510.12077

Compressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory
We study neural network compressibility by using singular learning theory to extend the minimum description length (MDL) principle to singular models like neural networks. Through extensive experiments on the Pythia suite with quantization, factorization, and other compression techniques, we find that complexity estimates based on the local learning coefficient (LLC) are closely, and in some cases, linearly correlated with compressibility. Our results provide a path toward rigorously evaluating…

The Robustness of Differentiable Causal Discovery in Misspecified Scenarios
Huiyang Yi, Yanyan He, Duxin Chen, Mingyu Kang, He Wang, Wenwu Yu
https://arxiv.org/abs/2510.12503 ht…

The Robustness of Differentiable Causal Discovery in Misspecified Scenarios
Causal discovery aims to learn causal relationships between variables from targeted data, making it a fundamental task in machine learning. However, causal discovery algorithms often rely on unverifiable causal assumptions, which are usually difficult to satisfy in real-world data, thereby limiting the broad application of causal discovery in practical scenarios. Inspired by these considerations, this work extensively benchmarks the empirical performance of various mainstream causal discovery a…

Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers
Wenhan Ma, Hailin Zhang, Liang Zhao, Yifan Song, Yudong Wang, Zhifang Sui, Fuli Luo
https://arxiv.org/abs/2510.11370

Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers
Reinforcement learning (RL) has emerged as a crucial approach for enhancing the capabilities of large language models. However, in Mixture-of-Experts (MoE) models, the routing mechanism often introduces instability, even leading to catastrophic RL training collapse. We analyze the training-inference consistency of MoE models and identify a notable discrepancy in routing behaviors between the two phases. Moreover, even under identical conditions, the routing framework can yield divergent expert …

Learning Robust Agile Flight Control with Stability Guarantees
Lukas Pries, Markus Ryll
https://arxiv.org/abs/2510.12611 https://arxiv.org/pdf/2510.12611…

Learning Robust Agile Flight Control with Stability Guarantees
In the evolving landscape of high-speed agile quadrotor flight, achieving precise trajectory tracking at the platform's operational limits is paramount. Controllers must handle actuator constraints, exhibit robustness to disturbances, and remain computationally efficient for safety-critical applications. In this work, we present a novel neural-augmented feedback controller for agile flight control. The controller addresses individual limitations of existing state-of-the-art control paradigms an…

ProtoSiTex: Learning Semi-Interpretable Prototypes for Multi-label Text Classification
Utsav Kumar Nareti, Suraj Kumar, Soumya Pandey, Soumi Chattopadhyay, Chandranath Adak
https://arxiv.org/abs/2510.12534

ProtoSiTex: Learning Semi-Interpretable Prototypes for Multi-label Text Classification
The surge in user-generated reviews has amplified the need for interpretable models that can provide fine-grained insights. Existing prototype-based models offer intuitive explanations but typically operate at coarse granularity (sentence or document level) and fail to address the multi-label nature of real-world text classification. We propose ProtoSiTex, a semi-interpretable framework designed for fine-grained multi-label text classification. ProtoSiTex employs a dual-phase alternating traini…

CuMPerLay: Learning Cubical Multiparameter Persistence Vectorizations
Caner Korkmaz, Brighton Nuwagira, Bar{\i}\c{s} Co\c{s}kunuzer, Tolga Birdal
https://arxiv.org/abs/2510.12795

CuMPerLay: Learning Cubical Multiparameter Persistence Vectorizations
We present CuMPerLay, a novel differentiable vectorization layer that enables the integration of Cubical Multiparameter Persistence (CMP) into deep learning pipelines. While CMP presents a natural and powerful way to topologically work with images, its use is hindered by the complexity of multifiltration structures as well as the vectorization of CMP. In face of these challenges, we introduce a new algorithm for vectorizing MP homologies of cubical complexes. Our CuMPerLay decomposes the CMP in…

DiffEM: Learning from Corrupted Data with Diffusion Models via Expectation Maximization
Danial Hosseintabar, Fan Chen, Giannis Daras, Antonio Torralba, Constantinos Daskalakis
https://arxiv.org/abs/2510.12691

DiffEM: Learning from Corrupted Data with Diffusion Models via Expectation Maximization
Diffusion models have emerged as powerful generative priors for high-dimensional inverse problems, yet learning them when only corrupted or noisy observations are available remains challenging. In this work, we propose a new method for training diffusion models with Expectation-Maximization (EM) from corrupted data. Our proposed method, DiffEM, utilizes conditional diffusion models to reconstruct clean data from observations in the E-step, and then uses the reconstructed data to refine the cond…

Residual MPC: Blending Reinforcement Learning with GPU-Parallelized Model Predictive Control
Se Hwan Jeon, Ho Jae Lee, Seungwoo Hong, Sangbae Kim
https://arxiv.org/abs/2510.12717

Residual MPC: Blending Reinforcement Learning with GPU-Parallelized Model Predictive Control
Model Predictive Control (MPC) provides interpretable, tunable locomotion controllers grounded in physical models, but its robustness depends on frequent replanning and is limited by model mismatch and real-time computational constraints. Reinforcement Learning (RL), by contrast, can produce highly robust behaviors through stochastic training but often lacks interpretability, suffers from out-of-distribution failures, and requires intensive reward engineering. This work presents a GPU-paralleli…

Leading the Follower: Learning Persuasive Agents in Social Deduction Games
Zhang Zheng, Deheng Ye, Peilin Zhao, Hao Wang
https://arxiv.org/abs/2510.09087 https://

Leading the Follower: Learning Persuasive Agents in Social Deduction Games
Large language model (LLM) agents have shown remarkable progress in social deduction games (SDGs). However, existing approaches primarily focus on information processing and strategy selection, overlooking the significance of persuasive communication in influencing other players' beliefs and responses. In SDGs, success depends not only on making correct deductions but on convincing others to response in alignment with one's intent. To address this limitation, we formalize turn-based dialogue in…

MammoDINO: Anatomically Aware Self-Supervision for Mammographic Images
Sicheng Zhou, Lei Wu, Cao Xiao, Parminder Bhatia, Taha Kass-Hout
https://arxiv.org/abs/2510.11883 https://…

MammoDINO: Anatomically Aware Self-Supervision for Mammographic Images
Self-supervised learning (SSL) has transformed vision encoder training in general domains but remains underutilized in medical imaging due to limited data and domain specific biases. We present MammoDINO, a novel SSL framework for mammography, pretrained on 1.4 million mammographic images. To capture clinically meaningful features, we introduce a breast tissue aware data augmentation sampler for both image-level and patch-level supervision and a cross-slice contrastive learning objective that l…

Adversarial Robustness in One-Stage Learning-to-Defer
Yannis Montreuil, Letian Yu, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi
https://arxiv.org/abs/2510.10988 https://

Adversarial Robustness in One-Stage Learning-to-Defer
Learning-to-Defer (L2D) enables hybrid decision-making by routing inputs either to a predictor or to external experts. While promising, L2D is highly vulnerable to adversarial perturbations, which can not only flip predictions but also manipulate deferral decisions. Prior robustness analyses focus solely on two-stage settings, leaving open the end-to-end (one-stage) case where predictor and allocation are trained jointly. We introduce the first framework for adversarial robustness in one-stage …

SG-XDEAT: Sparsity-Guided Cross-Dimensional and Cross-Encoding Attention with Target-Aware Conditioning in Tabular Learning
Chih-Chuan Cheng, Yi-Ju Tseng
https://arxiv.org/abs/2510.12659

SG-XDEAT: Sparsity-Guided Cross-Dimensional and Cross-Encoding Attention with Target-Aware Conditioning in Tabular Learning
We propose SG-XDEAT (Sparsity-Guided Cross Dimensional and Cross-Encoding Attention with Target Aware Conditioning), a novel framework designed for supervised learning on tabular data. At its core, SG-XDEAT employs a dual-stream encoder that decomposes each input feature into two parallel representations: a raw value stream and a target-conditioned (label-aware) stream. These dual representations are then propagated through a hierarchical stack of attention-based modules. SG-XDEAT integrates th…

Improving Generative Behavior Cloning via Self-Guidance and Adaptive Chunking
Junhyuk So, Chiwoong Lee, Shinyoung Lee, Jungseul Ok, Eunhyeok Park
https://arxiv.org/abs/2510.12392

Improving Generative Behavior Cloning via Self-Guidance and Adaptive Chunking
Generative Behavior Cloning (GBC) is a simple yet effective framework for robot learning, particularly in multi-task settings. Recent GBC methods often employ diffusion policies with open-loop (OL) control, where actions are generated via a diffusion process and executed in multi-step chunks without replanning. While this approach has demonstrated strong success rates and generalization, its inherent stochasticity can result in erroneous action sampling, occasionally leading to unexpected task …

Tight Regret Upper and Lower Bounds for Optimistic Hedge in Two-Player Zero-Sum Games
Taira Tsuchiya
https://arxiv.org/abs/2510.11691 https://arxiv.org/pdf…

Tight Regret Upper and Lower Bounds for Optimistic Hedge in Two-Player Zero-Sum Games
In two-player zero-sum games, the learning dynamic based on optimistic Hedge achieves one of the best-known regret upper bounds among strongly-uncoupled learning dynamics. With an appropriately chosen learning rate, the social and individual regrets can be bounded by $O(\log(mn))$ in terms of the numbers of actions $m$ and $n$ of the two players. This study investigates the optimality of the dependence on $m$ and $n$ in the regret of optimistic Hedge. To this end, we begin by refining existing …

AnyUp: Universal Feature Upsampling
Thomas Wimmer, Prune Truong, Marie-Julie Rakotosaona, Michael Oechsle, Federico Tombari, Bernt Schiele, Jan Eric Lenssen
https://arxiv.org/abs/2510.12764

AnyUp: Universal Feature Upsampling
We introduce AnyUp, a method for feature upsampling that can be applied to any vision feature at any resolution, without encoder-specific training. Existing learning-based upsamplers for features like DINO or CLIP need to be re-trained for every feature extractor and thus do not generalize to different feature types at inference time. In this work, we propose an inference-time feature-agnostic upsampling architecture to alleviate this limitation and improve upsampling quality. In our experiment…

Ontolearn-A Framework for Large-scale OWL Class Expression Learning in Python
Caglar Demir, Alkid Baci, N'Dah Jean Kouagou, Leonie Nora Sieger, Stefan Heindorf, Simon Bin, Lukas Bl\"ubaum, Alexander Bigerl, Axel-Cyrille Ngonga Ngomo
https://arxiv.org/abs/2510.11561

Ontolearn-A Framework for Large-scale OWL Class Expression Learning in Python
In this paper, we present Ontolearn-a framework for learning OWL class expressions over large knowledge graphs. Ontolearn contains efficient implementations of recent stateof-the-art symbolic and neuro-symbolic class expression learners including EvoLearner and DRILL. A learned OWL class expression can be used to classify instances in the knowledge graph. Furthermore, Ontolearn integrates a verbalization module based on an LLM to translate complex OWL class expressions into natural language sen…

Learning Social Navigation from Positive and Negative Demonstrations and Rule-Based Specifications
Chanwoo Kim, Jihwan Yoon, Hyeonseong Kim, Taemoon Jeong, Changwoo Yoo, Seungbeen Lee, Soohwan Byeon, Hoon Chung, Matthew Pan, Jean Oh, Kyungjae Lee, Sungjoon Choi
https://arxiv.org/abs/2510.12215

Learning Social Navigation from Positive and Negative Demonstrations and Rule-Based Specifications
Mobile robot navigation in dynamic human environments requires policies that balance adaptability to diverse behaviors with compliance to safety constraints. We hypothesize that integrating data-driven rewards with rule-based objectives enables navigation policies to achieve a more effective balance of adaptability and safety. To this end, we develop a framework that learns a density-based reward from positive and negative demonstrations and augments it with rule-based objectives for obstacle a…

Few Shot Semi-Supervised Learning for Abnormal Stop Detection from Sparse GPS Trajectories
Muhammad Ayub Sabir, Junbiao Pang, Jiaqi Wu, Fatima Ashraf
https://arxiv.org/abs/2510.12686

Few Shot Semi-Supervised Learning for Abnormal Stop Detection from Sparse GPS Trajectories
Abnormal stop detection (ASD) in intercity coach transportation is critical for ensuring passenger safety, operational reliability, and regulatory compliance. However, two key challenges hinder ASD effectiveness: sparse GPS trajectories, which obscure short or unauthorized stops, and limited labeled data, which restricts supervised learning. Existing methods often assume dense sampling or regular movement patterns, limiting their applicability. To address data sparsity, we propose a Sparsity-Aw…

Model-Based Lookahead Reinforcement Learning for in-hand manipulation
Alexandre Lopes, Catarina Barata, Plinio Moreno
https://arxiv.org/abs/2510.08884 https://

Model-Based Lookahead Reinforcement Learning for in-hand manipulation
In-Hand Manipulation, as many other dexterous tasks, remains a difficult challenge in robotics by combining complex dynamic systems with the capability to control and manoeuvre various objects using its actuators. This work presents the application of a previously developed hybrid Reinforcement Learning (RL) Framework to In-Hand Manipulation task, verifying that it is capable of improving the performance of the task. The model combines concepts of both Model-Free and Model-Based Reinforcement L…

Evaluation of Real-Time Preprocessing Methods in AI-Based ECG Signal Analysis
Jasmin Freudenberg, Kai Hahn, Christian Weber, Madjid Fathi
https://arxiv.org/abs/2510.12541 https:…

Evaluation of Real-Time Preprocessing Methods in AI-Based ECG Signal Analysis
The increasing popularity of portable ECG systems and the growing demand for privacy-compliant, energy-efficient real-time analysis require new approaches to signal processing at the point of data acquisition. In this context, the edge domain is acquiring increasing importance, as it not only reduces latency times, but also enables an increased level of data security. The FACE project aims to develop an innovative machine learning solution for analysing long-term electrocardiograms that synergi…

Knowledge-Guided Machine Learning Models to Upscale Evapotranspiration in the U.S. Midwest
Aleksei Rozanov, Samikshya Subedi, Vasudha Sharma, Bryan C. Runck
https://arxiv.org/abs/2510.11505

Knowledge-Guided Machine Learning Models to Upscale Evapotranspiration in the U.S. Midwest
Evapotranspiration (ET) plays a critical role in the land-atmosphere interactions, yet its accurate quantification across various spatiotemporal scales remains a challenge. In situ measurement approaches, like eddy covariance (EC) or weather station-based ET estimation, allow for measuring ET at a single location. Agricultural uses of ET require estimates for each field over broad areas, making it infeasible to deploy sensing systems at each location. This study integrates tree-based and knowle…

FM-IRL: Flow-Matching for Reward Modeling and Policy Regularization in Reinforcement Learning
Zhenglin Wan, Jingxuan Wu, Xingrui Yu, Chubin Zhang, Mingcong Lei, Bo An, Ivor Tsang
https://arxiv.org/abs/2510.09222

FM-IRL: Flow-Matching for Reward Modeling and Policy Regularization in Reinforcement Learning
Flow Matching (FM) has shown remarkable ability in modeling complex distributions and achieves strong performance in offline imitation learning for cloning expert behaviors. However, despite its behavioral cloning expressiveness, FM-based policies are inherently limited by their lack of environmental interaction and exploration. This leads to poor generalization in unseen scenarios beyond the expert demonstrations, underscoring the necessity of online interaction with environment. Unfortunately…

Learning to Make MISTAKEs: Modeling Incorrect Student Thinking And Key Errors
Alexis Ross, Jacob Andreas
https://arxiv.org/abs/2510.11502 https://arxiv.org…

Learning to Make MISTAKEs: Modeling Incorrect Student Thinking And Key Errors
Research on reasoning in language models (LMs) predominantly focuses on improving the correctness of their outputs. But some important applications require modeling reasoning patterns that are incorrect. For example, automated systems that can reason about and simulate student errors are useful for providing real-time feedback in the classroom or offline practice for educators-in-training. This paper presents a new method, MISTAKE, that (1) constructs high-quality synthetic examples of reasonin…

What Do Temporal Graph Learning Models Learn?
Abigail J. Hayes, Tobias Schumacher, Markus Strohmaier
https://arxiv.org/abs/2510.09416 https://arxiv.org/pdf…

What Do Temporal Graph Learning Models Learn?
Learning on temporal graphs has become a central topic in graph representation learning, with numerous benchmarks indicating the strong performance of state-of-the-art models. However, recent work has raised concerns about the reliability of benchmark results, noting issues with commonly used evaluation protocols and the surprising competitiveness of simple heuristics. This contrast raises the question of which properties of the underlying graphs temporal graph learning models actually use to f…

Performance Analysis of Machine Learning Algorithms in Chronic Kidney Disease Prediction
Iftekhar Ahmed, Tanzil Ebad Chowdhury, Biggo Bushon Routh, Nafisa Tasmiya, Shadman Sakib, Adil Ahmed Chowdhury
https://arxiv.org/abs/2510.09493

Performance Analysis of Machine Learning Algorithms in Chronic Kidney Disease Prediction
Kidneys are the filter of the human body. About 10% of the global population is thought to be affected by Chronic Kidney Disease (CKD), which causes kidney function to decline. To protect in danger patients from additional kidney damage, effective risk evaluation of CKD and appropriate CKD monitoring are crucial. Due to quick and precise detection capabilities, Machine Learning models can help practitioners accomplish this goal efficiently; therefore, an enormous number of diagnosis systems and…

Incentivizing Time-Aware Fairness in Data Sharing
Jiangwei Chen, Kieu Thao Nguyen Pham, Rachael Hwee Ling Sim, Arun Verma, Zhaoxuan Wu, Chuan-Sheng Foo, Bryan Kian Hsiang Low
https://arxiv.org/abs/2510.09240

Incentivizing Time-Aware Fairness in Data Sharing
In collaborative data sharing and machine learning, multiple parties aggregate their data resources to train a machine learning model with better model performance. However, as the parties incur data collection costs, they are only willing to do so when guaranteed incentives, such as fairness and individual rationality. Existing frameworks assume that all parties join the collaboration simultaneously, which does not hold in many real-world scenarios. Due to the long processing time for data cle…

Mitigating Model Drift in Developing Economies Using Synthetic Data and Outliers
Ilyas Varshavskiy, Bonu Boboeva, Shuhrat Khalilbekov, Azizjon Azimi, Sergey Shulgin, Akhlitdin Nizamitdinov, Haitz Saez de Ocariz Borde
https://arxiv.org/abs/2510.09294

Mitigating Model Drift in Developing Economies Using Synthetic Data and Outliers
Machine Learning models in finance are highly susceptible to model drift, where predictive performance declines as data distributions shift. This issue is especially acute in developing economies such as those in Central Asia and the Caucasus - including Tajikistan, Uzbekistan, Kazakhstan, and Azerbaijan - where frequent and unpredictable macroeconomics shocks destabilize financial data. To the best of our knowledge, this is among the first studies to examine drift mitigation methods on financi…