Tootfinder

AI, AGI, and learning efficiency
An addendum to this: I'm someone who would accurately be called "anti-AI" in the modern age, yet I'm also an "AI researcher" in some ways (have only dabbled in neutral nets).
I don't like:
- AI systems that are the product of labor abuses towards the data workers who curate their training corpora.
- AI systems that use inordinate amounts of water and energy during an intensifying climate catastrophe.
- AI systems that are fundamentally untrustworthy and which reinforce and amplify human biases, *especially* when those systems are exposed in a way that invites harms.
- AI systems which are designed to "save" my attention or brain bandwidth but such my doing so cripple my understating of the things I might use them for when I fact that understanding was the thing I was supposed to be using my time to gain, and where the later lack of such understanding will be costly to me.
- AI systems that are designed by and whose hype fattens the purse of people who materially support genocide and the construction of concentration campus (a.k.a. fascists).
In other words, I do not like and except in very extenuating circumstances I will not use ChatGPT, Claude, Copilot, Gemini, etc.
On the other hand, I do like:
- AI research as an endeavor to discover new technologies.
- Generative AI as a research topic using a spectrum of different methods.
- Speculating about non-human intelligences, including artificial ones, and including how to behave ethically towards them.
- Large language models as a specific technique, and autoencoders and other neural networks, assuming they're used responsibly in terms of both resource costs & presentation to end users.
I write this because I think some people (especially folks without CS backgrounds) may feel that opposing AI for all the harms it's causing runs the risk of opposing technological innovation more broadly, and/or may feel there's a risk that they will be "left behind" as everyone else embraces the hype and these technologies inevitability become ubiquitous and essential (I know I feel this way sometimes). Just know that is entirely possible and logically consistent to both oppose many forms of modern AI while also embracing and even being optimistic about AI research, and that while LLMs are currently all the rage, they're not the endpoint of what AI will look like in the future, and their downsides are not inherent in AI development.

Language learning has been part of me since high school. I'm solid in 2 non-English languages, crappy but survivable in 2 others. I've played with & started learning others many times.
I'm real busy rn, but language learning could be a fun thing to do for myself & make me feel like I'm still me.
But I'm stumped about my language picks. I learnt the obvious European languages in school; later tried key Asian languages. What do I want to do now?
African languages? I won't be getting a chance to use them much in Aus, & I'm unlikely to get to a stage where I can read literature.
I tried Slovenian/Slovene on a whim & really love it, but I'll never go there. Is the practical but unfun answer grind out more kanji/hanzi? Or is whimsically learning a language spoken by only 2.5 million people reasonable? I will continue struggling through with Ukrainian, 'cause I think it's important.
#LanguageLearning

What's going on with this #ICLR paper?
The metareview says that the authors provided a sound rebuttal and update to the paper, but neither are available (rebuttals are shown on other papers).
https://openreview.…

GLoRa: A Benchmark to Evaluate the Ability to Learn Long-Range...
Learning on graphs is one of the most active research topics in machine learning (ML). Among the key challenges in this field, effectively learning long-range dependencies in graphs has been...

Learning new German vocabulary today while working on the PnP (Essemtec Fox so Swiss design)
Bestückung, as in Bestückungskopf ("assembly head")
Fett, as in Spezialfett ("special grease")
Schlauch, as in Silikonschlauch ("silicone hose")

In-Context Learning for Gradient-Free Receiver Adaptation: Principles, Applications, and Theory
Matteo Zecchin, Tomer Raviv, Dileep Kalathil, Krishna Narayanan, Nir Shlezinger, Osvaldo Simeone
https://arxiv.org/abs/2506.15176

In-Context Learning for Gradient-Free Receiver Adaptation: Principles, Applications, and Theory
In recent years, deep learning has facilitated the creation of wireless receivers capable of functioning effectively in conditions that challenge traditional model-based designs. Leveraging programmable hardware architectures, deep learning-based receivers offer the potential to dynamically adapt to varying channel environments. However, current adaptation strategies, including joint training, hypernetwork-based methods, and meta-learning, either demonstrate limited flexibility or necessitate e…

Optimizing Web-Based AI Query Retrieval with GPT Integration in LangChain A CoT-Enhanced Prompt Engineering Approach
Wenqi Guan, Yang Fang
https://arxiv.org/abs/2506.15512

Optimizing Web-Based AI Query Retrieval with GPT Integration in LangChain A CoT-Enhanced Prompt Engineering Approach
Large Language Models have brought a radical change in the process of remote learning students, among other aspects of educative activities. Current retrieval of remote learning resources lacks depth in contextual meaning that provides comprehensive information on complex student queries. This work proposes a novel approach to enhancing remote learning retrieval by integrating GPT-based models within the LangChain framework. We achieve this system in a more intuitive and productive manner using…

Double Machine Learning for Conditional Moment Restrictions: IV regression, Proximal Causal Learning and Beyond
Daqian Shao, Ashkan Soleymani, Francesco Quinzan, Marta Kwiatkowska
https://arxiv.org/abs/2506.14950

Double Machine Learning for Conditional Moment Restrictions: IV regression, Proximal Causal Learning and Beyond
Solving conditional moment restrictions (CMRs) is a key problem considered in statistics, causal inference, and econometrics, where the aim is to solve for a function of interest that satisfies some conditional moment equalities. Specifically, many techniques for causal inference, such as instrumental variable (IV) regression and proximal causal learning (PCL), are CMR problems. Most CMR estimators use a two-stage approach, where the first-stage estimation is directly plugged into the second st…

A Comparative Evaluation of Deep Learning Models for Speech Enhancement in Real-World Noisy Environments
Md Jahangir Alam Khondkar, Ajan Ahmed, Masudul Haider Imtiaz, Stephanie Schuckers
https://arxiv.org/abs/2506.15000

A Comparative Evaluation of Deep Learning Models for Speech Enhancement in Real-World Noisy Environments
Speech enhancement, particularly denoising, is vital in improving the intelligibility and quality of speech signals for real-world applications, especially in noisy environments. While prior research has introduced various deep learning models for this purpose, many struggle to balance noise suppression, perceptual quality, and speaker-specific feature preservation, leaving a critical research gap in their comparative performance evaluation. This study benchmarks three state-of-the-art models W…

Inspired by the ever-creative, innovative and connected guru / Yoda of #edtech, @… Alan Levine, I started by own Pinboard collection of bookmarks:
https://

Extending Spike-Timing Dependent Plasticity to Learning Synaptic Delays
Marissa Dominijanni, Alexander Ororbia, Kenneth W. Regan
https://arxiv.org/abs/2506.14984

Extending Spike-Timing Dependent Plasticity to Learning Synaptic Delays
Synaptic delays play a crucial role in biological neuronal networks, where their modulation has been observed in mammalian learning processes. In the realm of neuromorphic computing, although spiking neural networks (SNNs) aim to emulate biology more closely than traditional artificial neural networks do, synaptic delays are rarely incorporated into their simulation. We introduce a novel learning rule for simultaneously learning synaptic connection strengths and delays, by extending spike-timin…

Demonstrating Superresolution in Radar Range Estimation Using a Denoising Autoencoder
Robert Czupryniak, Abhishek Chakraborty, Andrew N. Jordan, John C. Howell
https://arxiv.org/abs/2506.14906

Demonstrating Superresolution in Radar Range Estimation Using a Denoising Autoencoder
We apply machine learning methods to demonstrate range superresolution in remote sensing radar detection. Specifically, we implement a denoising autoencoder to estimate the distance between two equal intensity scatterers in the subwavelength regime. The machine learning models are trained on waveforms subject to a bandlimit constraint such that ranges much smaller than the inverse bandlimit are optimized in their precision. The autoencoder achieves effective dimensionality reduction, with the b…

A Data-Integrated Framework for Learning Fractional-Order Nonlinear Dynamical Systems
Bahram Yaghooti, Chengyu Li, Bruno Sinopoli
https://arxiv.org/abs/2506.15665

A Data-Integrated Framework for Learning Fractional-Order Nonlinear Dynamical Systems
This paper presents a data-integrated framework for learning the dynamics of fractional-order nonlinear systems in both discrete-time and continuous-time settings. The proposed framework consists of two main steps. In the first step, input-output experiments are designed to generate the necessary datasets for learning the system dynamics, including the fractional order, the drift vector field, and the control vector field. In the second step, these datasets, along with the memory-dependent prop…

Causality in the human niche: lessons for machine learning
Richard D. Lange, Konrad P. Kording
https://arxiv.org/abs/2506.13803 https://

Causality in the human niche: lessons for machine learning
Humans interpret the world around them in terms of cause and effect and communicate their understanding of the world to each other in causal terms. These causal aspects of human cognition are thought to underlie humans' ability to generalize and learn efficiently in new domains, an area where current machine learning systems are weak. Building human-like causal competency into machine learning systems may facilitate the construction of effective and interpretable AI. Indeed, the machine learnin…

GCN-Driven Reinforcement Learning for Probabilistic Real-Time Guarantees in Industrial URLLC
Eman Alqudah, Ashfaq Khokhar
https://arxiv.org/abs/2506.15011 …

GCN-Driven Reinforcement Learning for Probabilistic Real-Time Guarantees in Industrial URLLC
Ensuring packet-level communication quality is vital for ultra-reliable, low-latency communications (URLLC) in large-scale industrial wireless networks. We enhance the Local Deadline Partition (LDP) algorithm by introducing a Graph Convolutional Network (GCN) integrated with a Deep Q-Network (DQN) reinforcement learning framework for improved interference coordination in multi-cell, multi-channel networks. Unlike LDP's static priorities, our approach dynamically learns link priorities based on …

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[4/7]:
- A Comprehensive Survey on Continual Learning in Generative Models
Guo, Zeng, Zhu, Wang, Wang, Zhou, Zhao, Liu, Ma, Wang, Zhang, Liu

Instead of needing to write a complex function or remember complicated formulas, we just need to know how to instruct AI to get the results we want.
And if we’re not experts, we can have multiple AIs check the work.
We’re basically sitting in a council of experts and learning along the way.
So, in the end, we’re not getting dumber - we’re just shifting our knowledge and adapting to a new way of thinking.

fun #chinafake fact: many believe that http://www.eptoys.net is short for “ever profit toys”, but it actually stands for “eepy toys” @…

Sporadic Federated Learning Approach in Quantum Environment to Tackle Quantum Noise
Ratun Rahman, Atit Pokharel, Dinh C. Nguyen
https://arxiv.org/abs/2507.12492

Sporadic Federated Learning Approach in Quantum Environment to Tackle Quantum Noise
Quantum Federated Learning (QFL) is an emerging paradigm that combines quantum computing and federated learning (FL) to enable decentralized model training while maintaining data privacy over quantum networks. However, quantum noise remains a significant barrier in QFL, since modern quantum devices experience heterogeneous noise levels due to variances in hardware quality and sensitivity to quantum decoherence, resulting in inadequate training performance. To address this issue, we propose SpoQ…

#DH2028 will be in South Africa! Congratulations Menno, Juan and DHASA! Now we're learning about #DH2026 in Daejon, South Korea https://dh2026.adho.org

Learning to flock in open space by avoiding collisions and staying together
Martino Brambati, Antonio Celani, Marco Gherardi, Francesco Ginelli
https://arxiv.org/abs/2506.15587

Learning to flock in open space by avoiding collisions and staying together
We investigate the emergence of cohesive flocking in open, boundless space using a multi-agent reinforcement learning framework. Agents integrate positional and orientational information from their closest topological neighbours and learn to balance alignment and attractive interactions by optimizing a local cost function that penalizes both excessive separation and close-range crowding. The resulting Vicsek-like dynamics is robust to algorithmic implementation details and yields cohesive colle…

Transit for All: Mapping Equitable Bike2Subway Connection using Region Representation Learning
Min Namgung, JangHyeon Lee, Fangyi Ding, Yao-Yi Chiang
https://arxiv.org/abs/2506.15113

Transit for All: Mapping Equitable Bike2Subway Connection using Region Representation Learning
Ensuring equitable public transit access remains challenging, particularly in densely populated cities like New York City (NYC), where low-income and minority communities often face limited transit accessibility. Bike-sharing systems (BSS) can bridge these equity gaps by providing affordable first- and last-mile connections. However, strategically expanding BSS into underserved neighborhoods is difficult due to uncertain bike-sharing demand at newly planned ("cold-start") station locations and …

PhantomHunter: Detecting Unseen Privately-Tuned LLM-Generated Text via Family-Aware Learning
Yuhui Shi, Yehan Yang, Qiang Sheng, Hao Mi, Beizhe Hu, Chaoxi Xu, Juan Cao
https://arxiv.org/abs/2506.15683

PhantomHunter: Detecting Unseen Privately-Tuned LLM-Generated Text via Family-Aware Learning
With the popularity of large language models (LLMs), undesirable societal problems like misinformation production and academic misconduct have been more severe, making LLM-generated text detection now of unprecedented importance. Although existing methods have made remarkable progress, a new challenge posed by text from privately tuned LLMs remains underexplored. Users could easily possess private LLMs by fine-tuning an open-source one with private corpora, resulting in a significant performanc…

Deploying and Evaluating Multiple Deep Learning Models on Edge Devices for Diabetic Retinopathy Detection
Akwasi Asare, Dennis Agyemanh Nana Gookyi, Derrick Boateng, Fortunatus Aabangbio Wulnye
https://arxiv.org/abs/2506.14834

Deploying and Evaluating Multiple Deep Learning Models on Edge Devices for Diabetic Retinopathy Detection
Diabetic Retinopathy (DR), a leading cause of vision impairment in individuals with diabetes, affects approximately 34.6% of diabetes patients globally, with the number of cases projected to reach 242 million by 2045. Traditional DR diagnosis relies on the manual examination of retinal fundus images, which is both time-consuming and resource intensive. This study presents a novel solution using Edge Impulse to deploy multiple deep learning models for real-time DR detection on edge devices. A ro…

Learning to Predict Mobile Robot Stability in Off-Road Environments
Nathaniel Rose, Arif Ahmed, Emanuel Gutierrez-Cornejo, Parikshit Maini
https://arxiv.org/abs/2507.12731

Learning to Predict Mobile Robot Stability in Off-Road Environments
Navigating in off-road environments for wheeled mobile robots is challenging due to dynamic and rugged terrain. Traditional physics-based stability metrics, such as Static Stability Margin (SSM) or Zero Moment Point (ZMP) require knowledge of contact forces, terrain geometry, and the robot's precise center-of-mass that are difficult to measure accurately in real-world field conditions. In this work, we propose a learning-based approach to estimate robot platform stability directly from proprioc…

Fast Learning of Optimal Policy Trees
James Cussens, Julia Hatamyar, Vishalie Shah, Noemi Kreif
https://arxiv.org/abs/2506.15435 https://

Fast Learning of Optimal Policy Trees
We develop and implement a version of the popular "policytree" method (Athey and Wager, 2021) using discrete optimisation techniques. We test the performance of our algorithm in finite samples and find an improvement in the runtime of optimal policy tree learning by a factor of nearly 50 compared to the original version. We provide an R package, "fastpolicytree", for public use.

A Machine Learning Framework for Modeling Ensemble Properties of Atomically Disordered Materials
Zhenyao Fang, Ting-Wei Hsu, Qimin Yan
https://arxiv.org/abs/2506.15652

A Machine Learning Framework for Modeling Ensemble Properties of Atomically Disordered Materials
Disorder, though naturally present in experimental samples and strongly influencing a wide range of material phenomena, remains underexplored in first-principles studies due to the computational cost of sampling the large supercell and configurational space. The recent development of machine learning techniques, particularly graph neural networks (GNNs), has enabled the efficient and accurate predictions of complex material properties, offering promising tools for studying disordered systems. I…

I certainly remember learning that standing under a tree is the thing *not* to do in a thunderstorm. Are children no longer getting that lesson?
https://www.cbsnews.com/newyork/news/person-struck-by-lightning-central-park-nyc/

Berlin-based Knowunity, an AI-powered learning platform with 20M users in 15 countries, raised a €27M Series B led by XAnge, bringing its total funding to €45M (Tamara Djurickovic/Tech.eu)
https://tech.eu/2025/06/13/knowunity-raises-eur…

Knowunity raises €27M to scale its personalized AI tutor globally
The Berlin-based learning platform Knowunity, has raised €27 million in a Series B round to expand its personalised AI study companion globally. The new funding brings Knowunity’s total raised to €45 million and will be used to further develop its global AI learning companion. Built by and for students, Knowunity was founded in 2020 by Benedict Kurz (CEO), along with Gregor Weber (CPO), Lucas Hild (CTO), and Yannik Prigl (Backend). All were just 17 years old and still in school at the ti…

CDP: Towards Robust Autoregressive Visuomotor Policy Learning via Causal Diffusion
Jiahua Ma, Yiran Qin, Yixiong Li, Xuanqi Liao, Yulan Guo, Ruimao Zhang
https://arxiv.org/abs/2506.14769

CDP: Towards Robust Autoregressive Visuomotor Policy Learning via Causal Diffusion
Diffusion Policy (DP) enables robots to learn complex behaviors by imitating expert demonstrations through action diffusion. However, in practical applications, hardware limitations often degrade data quality, while real-time constraints restrict model inference to instantaneous state and scene observations. These limitations seriously reduce the efficacy of learning from expert demonstrations, resulting in failures in object localization, grasp planning, and long-horizon task execution. To add…

EBS-CFL: Efficient and Byzantine-robust Secure Clustered Federated Learning
Zhiqiang Li, Haiyong Bao, Menghong Guan, Hao Pan, Cheng Huang, Hong-Ning Dai
https://arxiv.org/abs/2506.13612

EBS-CFL: Efficient and Byzantine-robust Secure Clustered Federated Learning
Despite federated learning (FL)'s potential in collaborative learning, its performance has deteriorated due to the data heterogeneity of distributed users. Recently, clustered federated learning (CFL) has emerged to address this challenge by partitioning users into clusters according to their similarity. However, CFL faces difficulties in training when users are unwilling to share their cluster identities due to privacy concerns. To address these issues, we present an innovative Efficient and R…

R learning for applied statistics by Chenxin Li: #rstats

A Survey of Reinforcement Learning for Software Engineering
Dong Wang, Hanmo You, Lingwei Zhu, Kaiwei Lin, Zheng Chen, Chen Yang, Junji Yu, Zan Wang, Junjie Chen
https://arxiv.org/abs/2507.12483

A Survey of Reinforcement Learning for Software Engineering
Reinforcement Learning (RL) has emerged as a powerful paradigm for sequential decision-making and has attracted growing interest across various domains, particularly following the advent of Deep Reinforcement Learning (DRL) in 2015. Simultaneously, the rapid advancement of Large Language Models (LLMs) has further fueled interest in integrating RL with LLMs to enable more adaptive and intelligent systems. In the field of software engineering (SE), the increasing complexity of systems and the ris…

Fokker-Planck Score Learning: Efficient Free-Energy Estimation under Periodic Boundary Conditions
Daniel Nagel, Tristan Bereau
https://arxiv.org/abs/2506.15653

Fokker-Planck Score Learning: Efficient Free-Energy Estimation under Periodic Boundary Conditions
Accurate free-energy estimation is essential in molecular simulation, yet the periodic boundary conditions (PBC) commonly used in computer simulations have rarely been explicitly exploited. Equilibrium methods such as umbrella sampling, metadynamics, and adaptive biasing force require extensive sampling, while non-equilibrium pulling with Jarzynski's equality suffers from poor convergence due to exponential averaging. Here, we introduce a physics-informed, score-based diffusion framework: by ma…

Efficient space reduction techniques by optimized majority rules for the Kemeny aggregation problem
Xuan Kien Phung, Sylvie Hamel
https://arxiv.org/abs/2506.15097

Efficient space reduction techniques by optimized majority rules for the Kemeny aggregation problem
The Kemeny aggregation problem consists of computing the consensus rankings of an election with respect to the Kemeny-Young voting method. These aggregated rankings are the geometric medians as well as the maximum likelihood estimators in the Mallows model of the rankings in the election under the Kendall-tau distance which counts the number of pairwise disagreements. The problem admits fundamental applications in various domains such as computational social choice, machine learning, operations…

Autonomous Resource Management in Microservice Systems via Reinforcement Learning
Yujun Zou, Nia Qi, Yingnan Deng, Zhihao Xue, Ming Gong, Wuyang Zhang
https://arxiv.org/abs/2507.12879

Autonomous Resource Management in Microservice Systems via Reinforcement Learning
This paper proposes a reinforcement learning-based method for microservice resource scheduling and optimization, aiming to address issues such as uneven resource allocation, high latency, and insufficient throughput in traditional microservice architectures. In microservice systems, as the number of services and the load increase, efficiently scheduling and allocating resources such as computing power, memory, and storage becomes a critical research challenge. To address this, the paper employs…

An Observation on Lloyd's k-Means Algorithm in High Dimensions
David Silva-S\'anchez, Roy R. Lederman
https://arxiv.org/abs/2506.14952 https://

An Observation on Lloyd's k-Means Algorithm in High Dimensions
Clustering and estimating cluster means are core problems in statistics and machine learning, with k-means and Expectation Maximization (EM) being two widely used algorithms. In this work, we provide a theoretical explanation for the failure of k-means in high-dimensional settings with high noise and limited sample sizes, using a simple Gaussian Mixture Model (GMM). We identify regimes where, with high probability, almost every partition of the data becomes a fixed point of the k-means algorith…

One-shot Face Sketch Synthesis in the Wild via Generative Diffusion Prior and Instruction Tuning
Han Wu, Junyao Li, Kangbo Zhao, Sen Zhang, Yukai Shi, Liang Lin
https://arxiv.org/abs/2506.15312

One-shot Face Sketch Synthesis in the Wild via Generative Diffusion Prior and Instruction Tuning
Face sketch synthesis is a technique aimed at converting face photos into sketches. Existing face sketch synthesis research mainly relies on training with numerous photo-sketch sample pairs from existing datasets. However, these large-scale discriminative learning methods will have to face problems such as data scarcity and high human labor costs. Once the training data becomes scarce, their generative performance significantly degrades. In this paper, we propose a one-shot face sketch synthesi…

WIP: Turning Fake Chips into Learning Opportunities
Haniye Mehraban, Saad Azmeen-ur-Rahman, John Hu
https://arxiv.org/abs/2507.13281 https://

WIP: Turning Fake Chips into Learning Opportunities
This work-in-progress paper presents a case study in which counterfeit TL074 operational amplifiers, discovered in a junior level electronics course, became the basis for a hands on learning experience. Counterfeit integrated circuits (IC) are increasingly common, posing a significant threat to the integrity of undergraduate electronics laboratories. Instead of simply replacing the counterfeit components, we turned the issue into a teaching moment. Students engaged in hands-on diagnostics measu…

You'll never become a NATIVE English speaker
No matter how hard you try, the years in the UK or Ireland, the effort in your accent, or the AI applications you might use to fake it
There is a language wall, made of accents, cultural references and seemingly illogical phrasal verbs and idioms, that we cannot jump
But IT DOESN'T MATTER.
90% of your interactions are probably with other non-native speakers. As long as you understand each other, you're good.

Neither British nor American: how Europeans speak their own flavour of English - The European Perspective
Learning English with Elton John

Now out in #TMLR:
🍇 GRAPES: Learning to Sample Graphs for Scalable Graph Neural Networks 🍇
There's lots of work on sampling subgraphs for GNNs, but relatively little on making this sampling process _adaptive_. That is, learning to select the data from the graph that is relevant for your task.
We introduce an RL-based and a GFLowNet-based sampler and show that the approach perf…

Mapping Emotions in the Brain: A Bi-Hemispheric Neural Model with Explainable Deep Learning
David Freire-Obreg\'on, Agnieszka Dubiel, Prasoon Kumar Vinodkumar, Gholamreza Anbarjafari, Dorota Kami\'nska, Modesto Castrill\'on-Santana
https://arxiv.org/abs/2507.12625

Mapping Emotions in the Brain: A Bi-Hemispheric Neural Model with Explainable Deep Learning
Recent advances have shown promise in emotion recognition from electroencephalogram (EEG) signals by employing bi-hemispheric neural architectures that incorporate neuroscientific priors into deep learning models. However, interpretability remains a significant limitation for their application in sensitive fields such as affective computing and cognitive modeling. In this work, we introduce a post-hoc interpretability framework tailored to dual-stream EEG classifiers, extending the Local Interp…

Weak TransNet: A Petrov-Galerkin based neural network method for solving elliptic PDEs
Zhihang Xu, Min Wang, Zhu Wang
https://arxiv.org/abs/2506.14812 http…

Weak TransNet: A Petrov-Galerkin based neural network method for solving elliptic PDEs
While deep learning has achieved remarkable success in solving partial differential equations (PDEs), it still faces significant challenges, particularly when the PDE solutions have low regularity or singularities. To address these issues, we propose the Weak TransNet (WTN) method, based on a Petrov-Galerkin formulation, for solving elliptic PDEs in this work, though its framework may extend to other classes of equations. Specifically, the neural feature space defined by TransNet (Zhang et al.,…

Review of Machine Learning for Real-Time Analysis at the Large Hadron Collider experiments ALICE, ATLAS, CMS and LHCb
Laura Boggia, Carlos Cocha, Fotis Giasemis, Joachim Hansen, Patin Inkaew, Kaare Endrup Iversen, Pratik Jawahar, Henrique Pineiro Monteagudo, Micol Olocco, Sten Astrand, Martino Borsato, Leon Bozianu, Steven Schramm, the SMARTHEP Network

Review of Machine Learning for Real-Time Analysis at the Large Hadron Collider experiments ALICE, ATLAS, CMS and LHCb
The field of high energy physics (HEP) has seen a marked increase in the use of machine learning (ML) techniques in recent years. The proliferation of applications has revolutionised many aspects of the data processing pipeline at collider experiments including the Large Hadron Collider (LHC). In this whitepaper, we discuss the increasingly crucial role that ML plays in real-time analysis (RTA) at the LHC, namely in the context of the unique challenges posed by the trigger systems of the large …

Bayesian inference for the learning rate in Generalised Bayesian inference
Jeong Eun Lee, Sitong Liu, Geoff K. Nicholls
https://arxiv.org/abs/2506.12532 ht…

Bayesian inference for the learning rate in Generalised Bayesian inference
In Generalised Bayesian Inference (GBI), the learning rate and hyperparameters of the loss must be estimated. However, these inference-hyperparameters can't be estimated jointly with the other parameters by giving them a prior, as we discuss. Several methods for estimating the learning rate have been given which elicit and minimise a loss based on the goals of the overall inference (in our case, prediction of new data). However, in some settings there exists an unknown ``true'' learning rate ab…

PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning
M. Anwar Ma'sum, Mahardhika Pratama, Savitha Ramasamy, Lin Liu, Habibullah Habibullah, Ryszard Kowalczyk
https://arxiv.org/abs/2507.12305

PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning
The data privacy constraint in online continual learning (OCL), where the data can be seen only once, complicates the catastrophic forgetting problem in streaming data. A common approach applied by the current SOTAs in OCL is with the use of memory saving exemplars or features from previous classes to be replayed in the current task. On the other hand, the prompt-based approach performs excellently in continual learning but with the cost of a growing number of trainable parameters. The first ap…

Human-Centred AI in FinTech: Developing a User Experience (UX) Research Point of View (PoV) Playbook
Festus Adedoyin, Huseyin Dogan
https://arxiv.org/abs/2506.15325

Human-Centred AI in FinTech: Developing a User Experience (UX) Research Point of View (PoV) Playbook
Advancements in Artificial Intelligence (AI) have significantly transformed the financial industry, enabling the development of more personalised and adaptable financial products and services. This research paper explores various instances where Human-Centred AI (HCAI) has facilitated these advancements, drawing from contemporary studies and industry progress. The paper examines how the application of HCAI-powered data analytics, machine learning, and natural language processing enables financi…

Fiber Signal Denoising Algorithm using Hybrid Deep Learning Networks
Linlin Wang, Wei Wang, Dezhao Wang, Shanwen Wang
https://arxiv.org/abs/2506.15125 http…

Fiber Signal Denoising Algorithm using Hybrid Deep Learning Networks
With the applicability of optical fiber-based distributed acoustic sensing (DAS) systems, effective signal processing and analysis approaches are needed to promote its popularization in the field of intelligent transportation systems (ITS). This paper presents a signal denoising algorithm using a hybrid deep-learning network (HDLNet). Without annotated data and time-consuming labeling, this self-supervised network runs in parallel, combining an autoencoder for denoising (DAE) and a long short-t…

Machine learning based prediction of dynamical clustering in granular gases
Sai Preetham Sata, Ralf Stannarius, Benjamin Noack, Dmitry Puzyrev
https://arxiv.org/abs/2506.15657

Machine learning based prediction of dynamical clustering in granular gases
When dense granular gases are continuously excited under microgravity conditions, spatial inhomogeneities of the particle number density can emerge. A significant share of particles may collect in strongly overpopulated regions, called clusters. This dynamical clustering, or gas-cluster transition, is caused by a complex interplay and balance between the energy influx and dissipation in particle collisions. Particle number density, container geometry, and excitation strength influence this tran…

Learning to Maximize Quantum Neural Network Expressivity via Effective Rank
Juan Yao
https://arxiv.org/abs/2506.15375 https://arxiv.o…

Learning to Maximize Quantum Neural Network Expressivity via Effective Rank
Quantum neural networks (QNNs) are widely employed as ansätze for solving variational problems, where their expressivity directly impacts performance. Yet, accurately characterizing QNN expressivity remains an open challenge, impeding the optimal design of quantum circuits. In this work, we introduce the effective rank, denoted as $κ$, as a novel quantitative measure of expressivity. Specifically, $κ$ captures the number of effectively independent parameters among all the variational paramet…

Enhancing Symbolic Machine Learning by Subsymbolic Representations
Stephen Roth, Lennart Baur, Derian Boer, Stefan Kramer
https://arxiv.org/abs/2506.14569 …

Enhancing Symbolic Machine Learning by Subsymbolic Representations
The goal of neuro-symbolic AI is to integrate symbolic and subsymbolic AI approaches, to overcome the limitations of either. Prominent systems include Logic Tensor Networks (LTN) or DeepProbLog, which offer neural predicates and end-to-end learning. The versatility of systems like LTNs and DeepProbLog, however, makes them less efficient in simpler settings, for instance, for discriminative machine learning, in particular in domains with many constants. Therefore, we follow a different approach:…

Towards Perception-based Collision Avoidance for UAVs when Guiding the Visually Impaired
Suman Raj, Swapnil Padhi, Ruchi Bhoot, Prince Modi, Yogesh Simmhan
https://arxiv.org/abs/2506.14857

Towards Perception-based Collision Avoidance for UAVs when Guiding the Visually Impaired
Autonomous navigation by drones using onboard sensors combined with machine learning and computer vision algorithms is impacting a number of domains, including agriculture, logistics, and disaster management. In this paper, we examine the use of drones for assisting visually impaired people (VIPs) in navigating through outdoor urban environments. Specifically, we present a perception-based path planning system for local planning around the neighborhood of the VIP, integrated with a global plann…

QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation
Jiazheng Li, Hong Lu, Kaiyue Wen, Zaiwen Yang, Jiaxuan Gao, Hongzhou Lin, Yi Wu, Jingzhao Zhang
https://arxiv.org/abs/2507.13266

QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation
Reinforcement learning (RL) has become a key component in training large language reasoning models (LLMs). However, recent studies questions its effectiveness in improving multi-step reasoning-particularly on hard problems. To address this challenge, we propose a simple yet effective strategy via Question Augmentation: introduce partial solutions during training to reduce problem difficulty and provide more informative learning signals. Our method, QuestA, when applied during RL training on mat…

Make Your AUV Adaptive: An Environment-Aware Reinforcement Learning Framework For Underwater Tasks
Yimian Ding, Jingzehua Xu, Guanwen Xie, Shuai Zhang, Yi Li
https://arxiv.org/abs/2506.15082

Make Your AUV Adaptive: An Environment-Aware Reinforcement Learning Framework For Underwater Tasks
This study presents a novel environment-aware reinforcement learning (RL) framework designed to augment the operational capabilities of autonomous underwater vehicles (AUVs) in underwater environments. Departing from traditional RL architectures, the proposed framework integrates an environment-aware network module that dynamically captures flow field data, effectively embedding this critical environmental information into the state space. This integration facilitates real-time environmental ad…

NeuroMoE: A Transformer-Based Mixture-of-Experts Framework for Multi-Modal Neurological Disorder Classification
Wajih Hassan Raza, Aamir Bader Shah, Yu Wen, Yidan Shen, Juan Diego Martinez Lemus, Mya Caryn Schiess, Timothy Michael Ellmore, Renjie Hu, Xin Fu
https://arxiv.org/abs/2506.14970…

NeuroMoE: A Transformer-Based Mixture-of-Experts Framework for Multi-Modal Neurological Disorder Classification
The integration of multi-modal Magnetic Resonance Imaging (MRI) and clinical data holds great promise for enhancing the diagnosis of neurological disorders (NDs) in real-world clinical settings. Deep Learning (DL) has recently emerged as a powerful tool for extracting meaningful patterns from medical data to aid in diagnosis. However, existing DL approaches struggle to effectively leverage multi-modal MRI and clinical data, leading to suboptimal performance. To address this challenge, we util…

Isolating Noisy Labelled Test Cases in Human-in-the-Loop Oracle Learning
Charaka Geethal Kapugama
https://arxiv.org/abs/2506.13273 https://

Isolating Noisy Labelled Test Cases in Human-in-the-Loop Oracle Learning
Incorrectly labelled test cases can adversely affect the training process of human-in-the-loop oracle learning tech-niques. This paper introduces ISONOISE, a technique designed to identify such mislabelled test cases introduced during human-in-the-loop oracle learning. This technique can be applied to programs taking numeric inputs. Given a compromised automatic test oracle and its training test suite, ISONOISE first isolates thetest cases suspected of being mislabelled. This task is performed …

VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning
Senqiao Yang, Junyi Li, Xin Lai, Bei Yu, Hengshuang Zhao, Jiaya Jia
https://arxiv.org/abs/2507.13348

VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning
Recent advancements in vision-language models (VLMs) have improved performance by increasing the number of visual tokens, which are often significantly longer than text tokens. However, we observe that most real-world scenarios do not require such an extensive number of visual tokens. While the performance drops significantly in a small subset of OCR-related tasks, models still perform accurately in most other general VQA tasks with only 1/4 resolution. Therefore, we propose to dynamically proc…

SonicVerse: Multi-Task Learning for Music Feature-Informed Captioning
Anuradha Chopra, Abhinaba Roy, Dorien Herremans
https://arxiv.org/abs/2506.15154 http…

SonicVerse: Multi-Task Learning for Music Feature-Informed Captioning
Detailed captions that accurately reflect the characteristics of a music piece can enrich music databases and drive forward research in music AI. This paper introduces a multi-task music captioning model, SonicVerse, that integrates caption generation with auxiliary music feature detection tasks such as key detection, vocals detection, and more, so as to directly capture both low-level acoustic details as well as high-level musical attributes. The key contribution is a projection-based architec…

Advanced Prediction of Hypersonic Missile Trajectories with CNN-LSTM-GRU Architectures
Amir Hossein Baradaran
https://arxiv.org/abs/2506.15043 https://

Advanced Prediction of Hypersonic Missile Trajectories with CNN-LSTM-GRU Architectures
Advancements in the defense industry are paramount for ensuring the safety and security of nations, providing robust protection against emerging threats. Among these threats, hypersonic missiles pose a significant challenge due to their extreme speeds and maneuverability, making accurate trajectory prediction a critical necessity for effective countermeasures. This paper addresses this challenge by employing a novel hybrid deep learning approach, integrating Convolutional Neural Networks (CNNs)…

Evolutionary chemical learning in dimerization networks
Alexei V. Tkachenko, Bortolo Matteo Mognetti, Sergei Maslov
https://arxiv.org/abs/2506.14006 https:…

Evolutionary chemical learning in dimerization networks
We present a novel framework for chemical learning based on Competitive Dimerization Networks (CDNs) - systems in which multiple molecular species, e.g. proteins or DNA/RNA oligomers, reversibly bind to form dimers. We show that these networks can be trained in vitro through directed evolution, enabling the implementation of complex learning tasks such as multiclass classification without digital hardware or explicit parameter tuning. Each molecular species functions analogously to a neuron, wi…

Between Regulation and Accessibility: How Chinese University Students Navigate Global and Domestic Generative AI
Qin Xie, Ming Li, Fei Cheng
https://arxiv.org/abs/2506.14377

Between Regulation and Accessibility: How Chinese University Students Navigate Global and Domestic Generative AI
Despite the rapid proliferation of generative AI in higher education, students in China face significant barriers in accessing global tools like ChatGPT due to regulations and constraints. Grounded in the Unified Theory of Acceptance and Use of Technology 2 (UTAUT2) model, this study employs qualitative interviews to investigate how Chinese university students interact with both global and domestic generative AIs in the learning process. Findings reveal that engagement is shaped by accessibilit…

AI, AGI, and learning efficiency
My 4-month-old kid is not DDoSing Wikipedia right now, nor will they ever do so before learning to speak, read, or write. Their entire "training corpus" will not top even 100 million "tokens" before they can speak & understand language, and do so with real intentionally.
Just to emphasize that point: 100 words-per-minute times 60 minutes-per-hour times 12 hours-per-day times 365 days-per-year times 4 years is a mere 105,120,000 words. That's a ludicrously *high* estimate of words-per-minute and hours-per-day, and 4 years old (the age of my other kid) is well after basic speech capabilities are developed in many children, etc. More likely the available "training data" is at least 1 or 2 orders of magnitude less than this.
The point here is that large language models, trained as they are on multiple *billions* of tokens, are not developing their behavioral capabilities in a way that's remotely similar to humans, even if you believe those capabilities are similar (they are by certain very biased ways of measurement; they very much aren't by others). This idea that humans must be naturally good at acquiring language is an old one (see e.g. #AI #LLM #AGI

Analytical Optimization for Antenna Placement in Pinching-Antenna Systems
Zhiguo Ding, H. Vincent Poor
https://arxiv.org/abs/2507.13307 https://

Analytical Optimization for Antenna Placement in Pinching-Antenna Systems
As the main issue in pinching-antenna system design, antenna location optimization is key to realizing channel reconfigurability and system flexibility. Most existing works in this area adopt sophisticated optimization and learning tools to identify the optimal antenna locations in a numerical manner, where insightful understandings of the pinching antenna placement are still missing. Motivated by this research gap, this paper aims to carry out analytical optimization for pinching antenna place…

Evaluating Reinforcement Learning Algorithms for Navigation in Simulated Robotic Quadrupeds: A Comparative Study Inspired by Guide Dog Behaviour
Emma M. A. Harrison
https://arxiv.org/abs/2507.13277

Evaluating Reinforcement Learning Algorithms for Navigation in Simulated Robotic Quadrupeds: A Comparative Study Inspired by Guide Dog Behaviour
Robots are increasingly integrated across industries, particularly in healthcare. However, many valuable applications for quadrupedal robots remain overlooked. This research explores the effectiveness of three reinforcement learning algorithms in training a simulated quadruped robot for autonomous navigation and obstacle avoidance. The goal is to develop a robotic guide dog simulation capable of path following and obstacle avoidance, with long-term potential for real-world assistance to guide d…

Discovering Temporal Structure: An Overview of Hierarchical Reinforcement Learning
Martin Klissarov, Akhil Bagaria, Ziyan Luo, George Konidaris, Doina Precup, Marlos C. Machado
https://arxiv.org/abs/2506.14045

Discovering Temporal Structure: An Overview of Hierarchical Reinforcement Learning
Developing agents capable of exploring, planning and learning in complex open-ended environments is a grand challenge in artificial intelligence (AI). Hierarchical reinforcement learning (HRL) offers a promising solution to this challenge by discovering and exploiting the temporal structure within a stream of experience. The strong appeal of the HRL framework has led to a rich and diverse body of literature attempting to discover a useful structure. However, it is still not clear how one might …

Universal Rates of ERM for Agnostic Learning
Steve Hanneke, Mingyue Xu
https://arxiv.org/abs/2506.14110 https://arxiv.org/pdf/2506.14…

Universal Rates of ERM for Agnostic Learning
The universal learning framework has been developed to obtain guarantees on the learning rates that hold for any fixed distribution, which can be much faster than the ones uniformly hold over all the distributions. Given that the Empirical Risk Minimization (ERM) principle being fundamental in the PAC theory and ubiquitous in practical machine learning, the recent work of arXiv:2412.02810 studied the universal rates of ERM for binary classification under the realizable setting. However, the ass…

WebXAII: an open-source web framework to study human-XAI interaction
Jules Leguy, Pierre-Antoine Jean, Felipe Torres Figueroa, S\'ebastien Harispe
https://arxiv.org/abs/2506.14777

WebXAII: an open-source web framework to study human-XAI interaction
This article introduces WebXAII, an open-source web framework designed to facilitate research on human interaction with eXplainable Artificial Intelligence (XAI) systems. The field of XAI is rapidly expanding, driven by the growing societal implications of the widespread adoption of AI (and in particular machine learning) across diverse applications. Researchers who study the interaction between humans and XAI techniques typically develop ad hoc interfaces in order to conduct their studies. The…

Reasoning with Exploration: An Entropy Perspective
Daixuan Cheng, Shaohan Huang, Xuekai Zhu, Bo Dai, Wayne Xin Zhao, Zhenliang Zhang, Furu Wei
https://arxiv.org/abs/2506.14758

Reasoning with Exploration: An Entropy Perspective
Balancing exploration and exploitation is a central goal in reinforcement learning (RL). Despite recent advances in enhancing language model (LM) reasoning, most methods lean toward exploitation, and increasingly encounter performance plateaus. In this work, we revisit entropy -- a signal of exploration in RL -- and examine its relationship to exploratory reasoning in LMs. Through empirical analysis, we uncover strong positive correlations between high-entropy regions and three types of explora…

Leveraging Quantum Layers in Classical Neural Networks
Silvie Ill\'esov\'a
https://arxiv.org/abs/2507.12505 https://arxiv.org…

Leveraging Quantum Layers in Classical Neural Networks
Hybrid quantum-classical neural networks represent a promising frontier in the search for improved machine learning models. This thesis explores the integration of quantum layers within classical convolutional neural network architectures, aiming to leverage quantum entanglement and feature mapping to enhance learning capabilities. A detailed methodology for constructing and training such hybrid models is presented, using PyTorch and Qiskit Machine Learning frameworks. Experiments investigate t…

Reinforcement Learning-Based Policy Optimisation For Heterogeneous Radio Access
Anup Mishra, \v{C}edomir Stefanovi\'c, Xiuqiang Xu, Petar Popovski, Israel Leyva-Mayorga
https://arxiv.org/abs/2506.15273

Reinforcement Learning-Based Policy Optimisation For Heterogeneous Radio Access
Flexible and efficient wireless resource sharing across heterogeneous services is a key objective for future wireless networks. In this context, we investigate the performance of a system where latency-constrained internet-of-things (IoT) devices coexist with a broadband user. The base station adopts a grant-free access framework to manage resource allocation, either through orthogonal radio access network (RAN) slicing or by allowing shared access between services. For the IoT users, we propos…

Branch, or Layer? Zeroth-Order Optimization for Continual Learning of Vision-Language Models
Ziwei Liu, Borui Kang, Wei Li, Hangjie Yuan, Yanbing Yang, Wenbin Li, Jun Luo, Yifan Zhu, Tao Feng
https://arxiv.org/abs/2506.12409

Branch, or Layer? Zeroth-Order Optimization for Continual Learning of Vision-Language Models
Continual learning in vision-language models (VLMs) faces critical challenges in balancing parameter efficiency, memory consumption, and optimization stability. While First-Order (FO) optimization (e.g., SGD) dominate current approaches, their deterministic gradients often trap models in suboptimal local minima and incur substantial memory overhead. This paper pioneers a systematic exploration of Zeroth-Order (ZO) optimization for vision-language continual learning (VLCL). We first identify the…

SENIOR: Efficient Query Selection and Preference-Guided Exploration in Preference-based Reinforcement Learning
Hexian Ni, Tao Lu, Haoyuan Hu, Yinghao Cai, Shuo Wang
https://arxiv.org/abs/2506.14648

SENIOR: Efficient Query Selection and Preference-Guided Exploration in Preference-based Reinforcement Learning
Preference-based Reinforcement Learning (PbRL) methods provide a solution to avoid reward engineering by learning reward models based on human preferences. However, poor feedback- and sample- efficiency still remain the problems that hinder the application of PbRL. In this paper, we present a novel efficient query selection and preference-guided exploration method, called SENIOR, which could select the meaningful and easy-to-comparison behavior segment pairs to improve human feedback-efficiency…

Latent Anomaly Detection: Masked VQ-GAN for Unsupervised Segmentation in Medical CBCT
Pengwei Wang
https://arxiv.org/abs/2506.14209 https://

Latent Anomaly Detection: Masked VQ-GAN for Unsupervised Segmentation in Medical CBCT
Advances in treatment technology now allow for the use of customizable 3D-printed hydrogel wound dressings for patients with osteoradionecrosis (ORN) of the jaw (ONJ). Meanwhile, deep learning has enabled precise segmentation of 3D medical images using tools like nnUNet. However, the scarcity of labeled data in ONJ imaging makes supervised training impractical. This study aims to develop an unsupervised training approach for automatically identifying anomalies in imaging scans. We propose a…

Local Differential Privacy for Distributed Stochastic Aggregative Optimization with Guaranteed Optimality
Ziqin Chen, Yongqiang Wang
https://arxiv.org/abs/2506.15106

Local Differential Privacy for Distributed Stochastic Aggregative Optimization with Guaranteed Optimality
Distributed aggregative optimization underpins many cooperative optimization and multi-agent control systems, where each agent's objective function depends both on its local optimization variable and an aggregate of all agents' optimization variables. Existing distributed aggregative optimization approaches typically require access to accurate gradients of the objective functions, which, however, are often hard to obtain in real-world applications. For example, in machine learning, gradients ar…

Don't throw the baby out with the bathwater: How and why deep learning for ARC
Jack Cole, Mohamed Osman
https://arxiv.org/abs/2506.14276 https://

Don't throw the baby out with the bathwater: How and why deep learning for ARC
The Abstraction and Reasoning Corpus (ARC-AGI) presents a formidable challenge for AI systems. Despite the typically low performance on ARC, the deep learning paradigm remains the most effective known strategy for generating skillful (state-of-the-art) neural networks (NN) across varied modalities and tasks in vision, language etc. The deep learning paradigm has proven to be able to train these skillful neural networks and learn the abstractions needed in these diverse domains. Our work doubles…

Enhancing Cross-task Transfer of Large Language Models via Activation Steering
Xinyu Tang, Zhihao Lv, Xiaoxue Cheng, Junyi Li, Wayne Xin Zhao, Zujie Wen, Zhiqiang Zhang, Jun Zhou
https://arxiv.org/abs/2507.13236

Enhancing Cross-task Transfer of Large Language Models via Activation Steering
Large language models (LLMs) have shown impressive abilities in leveraging pretrained knowledge through prompting, but they often struggle with unseen tasks, particularly in data-scarce scenarios. While cross-task in-context learning offers a direct solution for transferring knowledge across tasks, it still faces critical challenges in terms of robustness, scalability, and efficiency. In this paper, we investigate whether cross-task transfer can be achieved via latent space steering without par…

Architectural Backdoors in Deep Learning: A Survey of Vulnerabilities, Detection, and Defense
Victoria Childress, Josh Collyer, Jodie Knapp
https://arxiv.org/abs/2507.12919

Architectural Backdoors in Deep Learning: A Survey of Vulnerabilities, Detection, and Defense
Architectural backdoors pose an under-examined but critical threat to deep neural networks, embedding malicious logic directly into a model's computational graph. Unlike traditional data poisoning or parameter manipulation, architectural backdoors evade standard mitigation techniques and persist even after clean retraining. This survey systematically consolidates research on architectural backdoors, spanning compiler-level manipulations, tainted AutoML pipelines, and supply-chain vulnerabilitie…

Replaced article(s) found for stat.ML. https://arxiv.org/list/stat.ML/new
[1/1]:
- Local minima of the empirical risk in high dimension: General theorems and convex examples
Kiana Asgari, Andrea Montanari, Basil Saeed

Can you see how I learn? Human observers' inferences about Reinforcement Learning agents' learning processes
Bernhard Hilpert, Muhan Hou, Kim Baraka, Joost Broekens
https://arxiv.org/abs/2506.13583

Can you see how I learn? Human observers' inferences about Reinforcement Learning agents' learning processes
Reinforcement Learning (RL) agents often exhibit learning behaviors that are not intuitively interpretable by human observers, which can result in suboptimal feedback in collaborative teaching settings. Yet, how humans perceive and interpret RL agent's learning behavior is largely unknown. In a bottom-up approach with two experiments, this work provides a data-driven understanding of the factors of human observers' understanding of the agent's learning process. A novel, observation-based paradi…

Inverse Physics-informed neural networks procedure for detecting noise in open quantum systems
Gubio G. de Lima, Iann Cunha, Leonardo Kleber Castelano
https://arxiv.org/abs/2507.12552

Inverse Physics-informed neural networks procedure for detecting noise in open quantum systems
Accurate characterization of quantum systems is essential for the development of quantum technologies, particularly in the noisy intermediate-scale quantum (NISQ) era. While traditional methods for Hamiltonian learning and noise characterization often require extensive measurements and scale poorly with system size, machine learning approaches offer promising alternatives. In this work, we extend the inverse physics-informed neural network (referred to as PINNverse) framework to open quantum sy…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[2/5]:
- Advancing oncology with federated learning: transcending boundaries in breast, lung, and prostate...
Anshu Ankolekar, et al.

DiFuse-Net: RGB and Dual-Pixel Depth Estimation using Window Bi-directional Parallax Attention and Cross-modal Transfer Learning
Kunal Swami, Debtanu Gupta, Amrit Kumar Muduli, Chirag Jaiswal, Pankaj Kumar Bajpai
https://arxiv.org/abs/2506.14709

DiFuse-Net: RGB and Dual-Pixel Depth Estimation using Window Bi-directional Parallax Attention and Cross-modal Transfer Learning
Depth estimation is crucial for intelligent systems, enabling applications from autonomous navigation to augmented reality. While traditional stereo and active depth sensors have limitations in cost, power, and robustness, dual-pixel (DP) technology, ubiquitous in modern cameras, offers a compelling alternative. This paper introduces DiFuse-Net, a novel modality decoupled network design for disentangled RGB and DP based depth estimation. DiFuse-Net features a window bi-directional parallax atte…

From Model to Classroom: Evaluating Generated MCQs for Portuguese with Narrative and Difficulty Concerns
Bernardo Leite, Henrique Lopes Cardoso, Pedro Pinto, Abel Ferreira, Lu\'is Abreu, Isabel Rangel, Sandra Monteiro
https://arxiv.org/abs/2506.15598

From Model to Classroom: Evaluating Generated MCQs for Portuguese with Narrative and Difficulty Concerns
While MCQs are valuable for learning and evaluation, manually creating them with varying difficulty levels and targeted reading skills remains a time-consuming and costly task. Recent advances in generative AI provide an opportunity to automate MCQ generation efficiently. However, assessing the actual quality and reliability of generated MCQs has received limited attention -- particularly regarding cases where generation fails. This aspect becomes particularly important when the generated MCQs …

FedWSIDD: Federated Whole Slide Image Classification via Dataset Distillation
Haolong Jin, Shenglin Liu, Cong Cong, Qingmin Feng, Yongzhi Liu, Lina Huang, Yingzi Hu
https://arxiv.org/abs/2506.15365

FedWSIDD: Federated Whole Slide Image Classification via Dataset Distillation
Federated learning (FL) has emerged as a promising approach for collaborative medical image analysis, enabling multiple institutions to build robust predictive models while preserving sensitive patient data. In the context of Whole Slide Image (WSI) classification, FL faces significant challenges, including heterogeneous computational resources across participating medical institutes and privacy concerns. To address these challenges, we propose FedWSIDD, a novel FL paradigm that leverages datas…

See What I Mean? CUE: A Cognitive Model of Understanding Explanations
Tobias Labarta, Nhi Hoang, Katharina Weitz, Wojciech Samek, Sebastian Lapuschkin, Leander Weber
https://arxiv.org/abs/2506.14775

See What I Mean? CUE: A Cognitive Model of Understanding Explanations
As machine learning systems increasingly inform critical decisions, the need for human-understandable explanations grows. Current evaluations of Explainable AI (XAI) often prioritize technical fidelity over cognitive accessibility which critically affects users, in particular those with visual impairments. We propose CUE, a model for Cognitive Understanding of Explanations, linking explanation properties to cognitive sub-processes: legibility (perception), readability (comprehension), and inter…

Oldies but Goldies: The Potential of Character N-grams for Romanian Texts
Dana Lupsa, Sanda-Maria Avram
https://arxiv.org/abs/2506.15650 https://

Oldies but Goldies: The Potential of Character N-grams for Romanian Texts
This study addresses the problem of authorship attribution for Romanian texts using the ROST corpus, a standard benchmark in the field. We systematically evaluate six machine learning techniques: Support Vector Machine (SVM), Logistic Regression (LR), k-Nearest Neighbors (k-NN), Decision Trees (DT), Random Forests (RF), and Artificial Neural Networks (ANN), employing character n-gram features for classification. Among these, the ANN model achieved the highest performance, including perfect clas…

DEMONSTRATE: Zero-shot Language to Robotic Control via Multi-task Demonstration Learning
Rahel Rickenbach, Bruce Lee, Ren\'e Zurbr\"ugg, Carmen Amo Alonso, Melanie N. Zeilinger
https://arxiv.org/abs/2507.12855

DEMONSTRATE: Zero-shot Language to Robotic Control via Multi-task Demonstration Learning
The integration of large language models (LLMs) with control systems has demonstrated significant potential in various settings, such as task completion with a robotic manipulator. A main reason for this success is the ability of LLMs to perform in-context learning, which, however, strongly relies on the design of task examples, closely related to the target tasks. Consequently, employing LLMs to formulate optimal control problems often requires task examples that contain explicit mathematical …

Beyond Shapley Values: Cooperative Games for the Interpretation of Machine Learning Models
Marouane Il Idrissi, Agathe Fernandes Machado, Arthur Charpentier
https://arxiv.org/abs/2506.13900

Beyond Shapley Values: Cooperative Games for the Interpretation of Machine Learning Models
Cooperative game theory has become a cornerstone of post-hoc interpretability in machine learning, largely through the use of Shapley values. Yet, despite their widespread adoption, Shapley-based methods often rest on axiomatic justifications whose relevance to feature attribution remains debatable. In this paper, we revisit cooperative game theory from an interpretability perspective and argue for a broader and more principled use of its tools. We highlight two general families of efficient al…

DDS-NAS: Dynamic Data Selection within Neural Architecture Search via On-line Hard Example Mining applied to Image Classification
Matt Poyser, Toby P. Breckon
https://arxiv.org/abs/2506.14667

DDS-NAS: Dynamic Data Selection within Neural Architecture Search via On-line Hard Example Mining applied to Image Classification
In order to address the scalability challenge within Neural Architecture Search (NAS), we speed up NAS training via dynamic hard example mining within a curriculum learning framework. By utilizing an autoencoder that enforces an image similarity embedding in latent space, we construct an efficient kd-tree structure to order images by furthest neighbour dissimilarity in a low-dimensional embedding. From a given query image from our subsample dataset, we can identify the most dissimilar image wit…

Learning mixed quantum states in large-scale experiments
Matteo Votto, Marko Ljubotina, C\'ecilia Lancien, J. Ignacio Cirac, Peter Zoller, Maksym Serbyn, Lorenzo Piroli, Beno\^it Vermersch
https://arxiv.org/abs/2507.12550

Learning mixed quantum states in large-scale experiments
We present and test a protocol to learn the matrix-product operator (MPO) representation of an experimentally prepared quantum state. The protocol takes as an input classical shadows corresponding to local randomized measurements, and outputs the tensors of a MPO which maximizes a suitably-defined fidelity with the experimental state. The tensor optimization is carried out sequentially, similarly to the well-known density matrix renormalization group algorithm. Our approach is provably efficien…

Latent Policy Steering with Embodiment-Agnostic Pretrained World Models
Yiqi Wang, Mrinal Verghese, Jeff Schneider
https://arxiv.org/abs/2507.13340 https:/…

Latent Policy Steering with Embodiment-Agnostic Pretrained World Models
Learning visuomotor policies via imitation has proven effective across a wide range of robotic domains. However, the performance of these policies is heavily dependent on the number of training demonstrations, which requires expensive data collection in the real world. In this work, we aim to reduce data collection efforts when learning visuomotor robot policies by leveraging existing or cost-effective data from a wide range of embodiments, such as public robot datasets and the datasets of huma…

Mirror Descent Using the Tempesta Generalized Multi-parametric Logarithms
Andrzej Cichocki
https://arxiv.org/abs/2506.13984 https://a…

Mirror Descent Using the Tempesta Generalized Multi-parametric Logarithms
In this paper, we develop a wide class Mirror Descent (MD) algorithms, which play a key role in machine learning. For this purpose we formulated the constrained optimization problem, in which we exploits the Bregman divergence with the Tempesta multi-parametric deformation logarithm as a link function. This link function called also mirror function defines the mapping between the primal and dual spaces and is associated with a very-wide (in fact, theoretically infinite) class of generalized tra…

AviationLLM: An LLM-based Knowledge System for Aviation Training
Jia'ang Wan, Feng Shen, Fujuan Li, Yanjin Sun, Yan Li, Shiwen Zhang
https://arxiv.org/abs/2506.14336

AviationLLM: An LLM-based Knowledge System for Aviation Training
Aviation training is a core link in ensuring flight safety, improving industry efficiency and promoting sustainable development. It not only involves flight simulation but also requires the learning of a great deal of professional aviation theory knowledge. In the existing training system, the knowledge is mainly imparted by the the instructors. However, the number of instructors is limited and the professional answers obtained from the Internet are not accurate enough, resulting in low trainin…

SemCSE: Semantic Contrastive Sentence Embeddings Using LLM-Generated Summaries For Scientific Abstracts
Marc Brinner, Sina Zarriess
https://arxiv.org/abs/2507.13105

SemCSE: Semantic Contrastive Sentence Embeddings Using LLM-Generated Summaries For Scientific Abstracts
We introduce SemCSE, an unsupervised method for learning semantic embeddings of scientific texts. Building on recent advances in contrastive learning for text embeddings, our approach leverages LLM-generated summaries of scientific abstracts to train a model that positions semantically related summaries closer together in the embedding space. This resulting objective ensures that the model captures the true semantic content of a text, in contrast to traditional citation-based approaches that do…

Conversational AI as a Catalyst for Informal Learning: An Empirical Large-Scale Study on LLM Use in Everyday Learning
Na{\dj}a Terzimehi\'c, Babette B\"uhler, Enkelejda Kasneci
https://arxiv.org/abs/2506.11789

Conversational AI as a Catalyst for Informal Learning: An Empirical Large-Scale Study on LLM Use in Everyday Learning
Large language models have not only captivated the public imagination but have also sparked a profound rethinking of how we learn. In the third year following the breakthrough launch of ChatGPT, everyday informal learning has been transformed as diverse user groups explore these novel tools. Who is embracing LLMs for self-directed learning, and who remains hesitant? What are their reasons for adoption or avoidance? What learning patterns emerge with this novel technological landscape? We presen…

Theoretical Tensions in RLHF: Reconciling Empirical Success with Inconsistencies in Social Choice Theory
Jiancong Xiao, Zhekun Shi, Kaizhao Liu, Qi Long, Weijie J. Su
https://arxiv.org/abs/2506.12350

Theoretical Tensions in RLHF: Reconciling Empirical Success with Inconsistencies in Social Choice Theory
Despite its empirical success, Reinforcement Learning from Human Feedback (RLHF) has been shown to violate almost all the fundamental axioms in social choice theory -- such as majority consistency, pairwise majority consistency, and Condorcet consistency. This raises a foundational question: why does RLHF perform so well in practice if it fails these seemingly essential properties? In this paper, we resolve this paradox by showing that under mild and empirically plausible assumptions on the pre…

Cross-lingual Few-shot Learning for Persian Sentiment Analysis with Incremental Adaptation
Farideh Majidi, Ziaeddin Beheshtifard
https://arxiv.org/abs/2507.11634

Cross-lingual Few-shot Learning for Persian Sentiment Analysis with Incremental Adaptation
This research examines cross-lingual sentiment analysis using few-shot learning and incremental learning methods in Persian. The main objective is to develop a model capable of performing sentiment analysis in Persian using limited data, while getting prior knowledge from high-resource languages. To achieve this, three pre-trained multilingual models (XLM-RoBERTa, mDeBERTa, and DistilBERT) were employed, which were fine-tuned using few-shot and incremental learning approaches on small samples o…

Understanding Learning Invariance in Deep Linear Networks
Hao Duan, Guido Mont\'ufar
https://arxiv.org/abs/2506.13714 https://arx…

Understanding Learning Invariance in Deep Linear Networks
Equivariant and invariant machine learning models exploit symmetries and structural patterns in data to improve sample efficiency. While empirical studies suggest that data-driven methods such as regularization and data augmentation can perform comparably to explicitly invariant models, theoretical insights remain scarce. In this paper, we provide a theoretical comparison of three approaches for achieving invariance: data augmentation, regularization, and hard-wiring. We focus on mean squared e…

Advances in LLMs with Focus on Reasoning, Adaptability, Efficiency and Ethics
Asifullah khan, Muhammad Zaeem Khan, Saleha Jamshed, Sadia Ahmad, Aleesha Zainab, Kaynat Khatib, Faria Bibi, Abdul Rehman
https://arxiv.org/abs/2506.12365

Advances in LLMs with Focus on Reasoning, Adaptability, Efficiency and Ethics
This survey paper outlines the key developments in the field of Large Language Models (LLMs), such as enhancing their reasoning skills, adaptability to various tasks, increased computational efficiency, and ability to make ethical decisions. The techniques that have been most effective in bridging the gap between human and machine communications include the Chain-of-Thought prompting, Instruction Tuning, and Reinforcement Learning from Human Feedback. The improvements in multimodal learning and…

Revisiting Chain-of-Thought Prompting: Zero-shot Can Be Stronger than Few-shot
Xiang Cheng, Chengyan Pan, Minjun Zhao, Deyang Li, Fangchao Liu, Xinyu Zhang, Xiao Zhang, Yong Liu
https://arxiv.org/abs/2506.14641

Revisiting Chain-of-Thought Prompting: Zero-shot Can Be Stronger than Few-shot
In-Context Learning (ICL) is an essential emergent ability of Large Language Models (LLMs), and recent studies introduce Chain-of-Thought (CoT) to exemplars of ICL to enhance the reasoning capability, especially in mathematics tasks. However, given the continuous advancement of model capabilities, it remains unclear whether CoT exemplars still benefit recent, stronger models in such tasks. Through systematic experiments, we find that for recent strong models such as the Qwen2.5 series, adding t…

Automatically assessing oral narratives of Afrikaans and isiXhosa children
R. Louw (Stellenbosch University), E. Sharratt (Stellenbosch University), F. de Wet (Stellenbosch University), C. Jacobs (Stellenbosch University), A. Smith (Stellenbosch University), H. Kamper (Stellenbosch University)
https://arxiv.org/abs/2507.13205

Automatically assessing oral narratives of Afrikaans and isiXhosa children
Developing narrative and comprehension skills in early childhood is critical for later literacy. However, teachers in large preschool classrooms struggle to accurately identify students who require intervention. We present a system for automatically assessing oral narratives of preschool children in Afrikaans and isiXhosa. The system uses automatic speech recognition followed by a machine learning scoring model to predict narrative and comprehension scores. For scoring predicted transcripts, we…