Tootfinder

Multi-Hazard Early Warning Systems for Agriculture with Featural-Temporal Explanations
Boyuan Zheng, Victor W. Chu
https://arxiv.org/abs/2507.22962 https://

Multi-Hazard Early Warning Systems for Agriculture with Featural-Temporal Explanations
Climate extremes present escalating risks to agriculture intensifying the need for reliable multi-hazard early warning systems (EWS). The situation is evolving due to climate change and hence such systems should have the intelligent to continue to learn from recent climate behaviours. However, traditional single-hazard forecasting methods fall short in capturing complex interactions among concurrent climatic events. To address this deficiency, in this paper, we combine sequential deep learning …

AutoIndexer: A Reinforcement Learning-Enhanced Index Advisor Towards Scaling Workloads
Taiyi Wang, Eiko Yoneki
https://arxiv.org/abs/2507.23084 https://arx…

AutoIndexer: A Reinforcement Learning-Enhanced Index Advisor Towards Scaling Workloads
Efficiently selecting indexes is fundamental to database performance optimization, particularly for systems handling large-scale analytical workloads. While deep reinforcement learning (DRL) has shown promise in automating index selection through its ability to learn from experience, few works address how these RL-based index advisors can adapt to scaling workloads due to exponentially growing action spaces and heavy trial and error. To address these challenges, we introduce AutoIndexer, a fram…

Learning Truthful Mechanisms without Discretization
Yunxuan Ma, Siqiang Wang, Zhijian Duan, Yukun Cheng, Xiaotie Deng
https://arxiv.org/abs/2506.22911 http…

Learning Truthful Mechanisms without Discretization
This paper introduces TEDI (Truthful, Expressive, and Dimension-Insensitive approach), a discretization-free algorithm to learn truthful and utility-maximizing mechanisms. Existing learning-based approaches often rely on discretization of outcome spaces to ensure truthfulness, which leads to inefficiency with increasing problem size. To address this limitation, we formalize the concept of pricing rules, defined as functions that map outcomes to prices. Based on this concept, we propose a novel …

iLearnRobot: An Interactive Learning-Based Multi-Modal Robot with Continuous Improvement
Kohou Wang, ZhaoXiang Liu, Lin Bai, Kun Fan, Xiang Liu, Huan Hu, Kai Wang, Shiguo Lian
https://arxiv.org/abs/2507.22896

iLearnRobot: An Interactive Learning-Based Multi-Modal Robot with Continuous Improvement
It is crucial that robots' performance can be improved after deployment, as they are inherently likely to encounter novel scenarios never seen before. This paper presents an innovative solution: an interactive learning-based robot system powered by a Multi-modal Large Language Model(MLLM). A key feature of our system is its ability to learn from natural dialogues with non-expert users. We also propose chain of question to clarify the exact intent of the question before providing an answer and d…

Offline Reinforcement Learning for Mobility Robustness Optimization
Pegah Alizadeh, Anastasios Giovanidis, Pradeepa Ramachandra, Vasileios Koutsoukis, Osama Arouk
https://arxiv.org/abs/2506.22793

Offline Reinforcement Learning for Mobility Robustness Optimization
In this work we revisit the Mobility Robustness Optimisation (MRO) algorithm and study the possibility of learning the optimal Cell Individual Offset tuning using offline Reinforcement Learning. Such methods make use of collected offline datasets to learn the optimal policy, without further exploration. We adapt and apply a sequence-based method called Decision Transformers as well as a value-based method called Conservative Q-Learning to learn the optimal policy for the same target reward as t…

The first #DevOpsDaysAustin keynote is @… talking about failing to learn vs. learning to fail.

A Reinforcement Learning Framework for Some Singular Stochastic Control Problems
Zongxia Liang, Xiaodong Luo, Xiang Yu
https://arxiv.org/abs/2506.22203 htt…

A Reinforcement Learning Framework for Some Singular Stochastic Control Problems
We develop a continuous-time reinforcement learning framework for a class of singular stochastic control problems without entropy regularization. The optimal singular control is characterized as the optimal singular control law, which is a pair of regions of time and the augmented states. The goal of learning is to identify such an optimal region via the trial-and-error procedure. In this context, we generalize the existing policy evaluation theories with regular controls to learn our optimal s…

A GENERIC-guided active learning SPH method for viscoelastic fluids using Gaussian process regression
Xuekai Dong, David Nieto Simavilla, Jie Ouyang, Xiaodong Wang, Marco Ellero
https://arxiv.org/abs/2506.21877

A GENERIC-guided active learning SPH method for viscoelastic fluids using Gaussian process regression
When applying machine learning methods to learn viscoelastic constitutive relations, the polymer history dependence in viscoelastic fluids and the generalization ability of machine learning models are challenging. In this paper, guided by the general equation for nonequilibrium reversible-irreversible coupling (GENERIC) framework, a novel GENERIC-guided active learning smoothed particle hydrodynamics (${\rm{G^2ALSPH}}$) method is proposed to obtain effective constitutive relations for reliable …

Editing Cotton Mather's Biblia Americana (1693-1728): America’s First Bible Commentary and Storehouse of Early Modern Learning
https://ift.tt/CbUHYMX
Pirino on Suzuki, 'Humanitarian Internationalism Under Empire: The Global Evolution of the Japanese…
via Input 4 RELCFP

Ah, frequency illusion bias/Baader-Meinhof phenomenon! I have been learning about the nation-state Treaty of Westphalia stuff.
I'm finding it a bit odd that I'm so late to learn about this ... is it less emphasised in Australia? Why is it emphasised in the US?
At my current stage of learning, Australia's self-definition feels heavily 'state', with any discussion of 'nation' often being tied to racism.
More to learn I guess!
#NationState #TreatyOfWestphalia

Effective Note-taking and its Impact on Learning Undergraduate Introductory Physics Courses
Chandra M. Adhikari, Tikaram Neupane, Uma Poudyal
https://arxiv.org/abs/2507.21326 ht…

Effective Note-taking and its Impact on Learning Undergraduate Introductory Physics Courses
Taking notes during lectures is one of the required skills, among many others, that students need (i) to master the topic covered in the lecture, (ii) to actively engage in the learning process with minimal to no distractions, (iii) to retain learned knowledge and skills for a longer time, and (iv) in securing better grade. To learn the role of note-taking in learning undergraduate-level introductory algebra-based physics courses, we present a comparative study of students' achievement in two m…

Learning to Charge More: A Theoretical Study of Collusion by Q-Learning Agents
Cristian Chica, Yinglong Guo, Gilad Lerman
https://arxiv.org/abs/2505.22909 …

Learning to Charge More: A Theoretical Study of Collusion by Q-Learning Agents
There is growing experimental evidence that $Q$-learning agents may learn to charge supracompetitive prices. We provide the first theoretical explanation for this behavior in infinite repeated games. Firms update their pricing policies based solely on observed profits, without computing equilibrium strategies. We show that when the game admits both a one-stage Nash equilibrium price and a collusive-enabling price, and when the $Q$-function satisfies certain inequalities at the end of experiment…

Raiders Veteran Details Learning the Chip Kelly Offense https://www.si.com/nfl/raiders/las-vega-salex-cappa-chip-kelly-ohio-state-buckeyes-training-camp

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Lakshya A Agrawal, Shangyin Tan, Dilara Soylu, Noah Ziems, Rishi Khare, Krista Opsahl-Ong, Arnav Singhvi, Herumb Shandilya, Michael J Ryan, Meng Jiang, Christopher Potts, Koushik Sen, Alexandros G. Dimakis, Ion Stoica, Dan Klein, Matei Zaharia, Omar Khattab
https://arx…

GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning
Large language models (LLMs) are increasingly adapted to downstream tasks via reinforcement learning (RL) methods like Group Relative Policy Optimization (GRPO), which often require thousands of rollouts to learn new tasks. We argue that the interpretable nature of language can often provide a much richer learning medium for LLMs, compared with policy gradients derived from sparse, scalar rewards. To test this, we introduce GEPA (Genetic-Pareto), a prompt optimizer that thoroughly incorporates …

Learning Kinetic Monte Carlo stochastic dynamics with Deep Generative Adversarial Networks
Daniele Lanzoni, Olivier Pierre-Louis, Roberto Bergamaschini, Francesco Montalenti
https://arxiv.org/abs/2507.21763

Learning Kinetic Monte Carlo stochastic dynamics with Deep Generative Adversarial Networks
We show that Generative Adversarial Networks (GANs) may be fruitfully exploited to learn stochastic dynamics, surrogating traditional models while capturing thermal fluctuations. Specifically, we showcase the application to a two-dimensional, many-particle system, focusing on surface-step fluctuations and on the related time-dependent roughness. After the construction of a dataset based on Kinetic Monte Carlo simulations, a conditional GAN is trained to propagate stochastically the state of the…

Towards Two-Stage Counterfactual Learning to Rank
Shashank Gupta, Yiming Liao, Maarten de Rijke
https://arxiv.org/abs/2506.20854 https://

Towards Two-Stage Counterfactual Learning to Rank
Counterfactual learning to rank (CLTR) aims to learn a ranking policy from user interactions while correcting for the inherent biases in interaction data, such as position bias. Existing CLTR methods assume a single ranking policy that selects top-K ranking from the entire document candidate set. In real-world applications, the candidate document set is on the order of millions, making a single-stage ranking policy impractical. In order to scale to millions of documents, real-world ranking syst…

Modern search demands scalable personalisation. Join Piotr Kobziakowski
at this year's Berlin Buzzwords to discover how Vespa's multi-stage ranking and tensor framework can be used for hybrid queries, multimodal retrieval, and real-time machine learning. Learn how to deploy low-latency, high-relevance search systems at petabyte scale.
Learn more:

Vespa.ai’s Personalized Search: Advanced Ranking & Tensor framework
Today’s applications require search engines to unify text, vectors, and business logic with millisecond latency at petabyte scale. It’s not easy to balance speed, relevance, and personalization for a large user population and a billion scale item base. Vespa.ai, the open-source engine powering Yahoo, Perplexity, Qwant, Vinted, Spotify addresses this through multi-stage ranking with close to data tensor operations and easy to understand custom functions. Vespa’s phased architecture enables…

More Efficient Real-Valued Gray-Box Optimization through Incremental Distribution Estimation in RV-GOMEA
Renzo J. Scholman, Tanja Alderliesten, Peter A. N. Bosman
https://arxiv.org/abs/2506.23738

More Efficient Real-Valued Gray-Box Optimization through Incremental Distribution Estimation in RV-GOMEA
The Gene-pool Optimal Mixing EA (GOMEA) family of EAs offers a specific means to exploit problem-specific knowledge through linkage learning, i.e., inter-variable dependency detection, expressed using subsets of variables, that should undergo joint variation. Such knowledge can be exploited if faster fitness evaluations are possible when only a few variables are changed in a solution, enabling large speed-ups. The recent-most version of Real-Valued GOMEA (RV-GOMEA) can learn a conditional linka…

Causal Representation Learning with Observational Grouping for CXR Classification
Rajat Rasal, Avinash Kori, Ben Glocker
https://arxiv.org/abs/2506.20582 h…

Causal Representation Learning with Observational Grouping for CXR Classification
Identifiable causal representation learning seeks to uncover the true causal relationships underlying a data generation process. In medical imaging, this presents opportunities to improve the generalisability and robustness of task-specific latent features. This work introduces the concept of grouping observations to learn identifiable representations for disease classification in chest X-rays via an end-to-end framework. Our experiments demonstrate that these causal representations improve gen…

Researchers detail "subliminal learning", where LLMs learn traits from model-generated data that is semantically unrelated to those traits (Anthropic)
https://alignment.anthropic.com/2025/subliminal-learning/

Fast prediction of the hydrodynamic QGP evolution in ultra-relativistic heavy-ion collisions using Fourier Neural Operators
David Stewart, Joern Putschke
https://arxiv.org/abs/2507.23598

Fast prediction of the hydrodynamic QGP evolution in ultra-relativistic heavy-ion collisions using Fourier Neural Operators
Recent research in machine learning has employed neural networks to learn mappings between function spaces on bounded domains termed ``neural operators''. As such, these operators can provide alternatives to standard numerical methods for partial differential equation (PDE) solutions. In particular, the Fourier Neural Operator (FNO) has been shown to map solutions for classical fluid flow problems with accuracy competitive with traditional PDE solvers and with much greater computing speed. This…

Learning Physical Interaction Skills from Human Demonstrations
Tianyu Li, Hengbo Ma, Sehoon Ha, Kwonjoon Lee
https://arxiv.org/abs/2507.20445 https://arxiv…

Learning Physical Interaction Skills from Human Demonstrations
Learning physical interaction skills, such as dancing, handshaking, or sparring, remains a fundamental challenge for agents operating in human environments, particularly when the agent's morphology differs significantly from that of the demonstrator. Existing approaches often rely on handcrafted objectives or morphological similarity, limiting their capacity for generalization. Here, we introduce a framework that enables agents with diverse embodiments to learn wholebbody interaction behaviors …

Editing Cotton Mather's Biblia Americana (1693-1728): America’s First Bible Commentary and Storehouse of Early Modern Learning https://networks.h-net.org/group/announcements/20121478/editing-cotton-mathers-biblia-am…

Faster exact learning of k-term DNFs with membership and equivalence queries
Josh Alman, Shivam Nadimpalli, Shyamal Patel, Rocco Servedio
https://arxiv.org/abs/2507.20336 https:…

Faster exact learning of k-term DNFs with membership and equivalence queries
In 1992 Blum and Rudich [BR92] gave an algorithm that uses membership and equivalence queries to learn $k$-term DNF formulas over $\{0,1\}^n$ in time $\textsf{poly}(n,2^k)$, improving on the naive $O(n^k)$ running time that can be achieved without membership queries [Val84]. Since then, many alternative algorithms [Bsh95, Kus97, Bsh97, BBB+00] have been given which also achieve runtime $\textsf{poly}(n,2^k)$. We give an algorithm that uses membership and equivalence queries to learn $k$-term …

Whilter: A Whisper-based Data Filter for "In-the-Wild" Speech Corpora Using Utterance-level Multi-Task Classification
William Ravenscroft, George Close, Kit Bower-Morris, Jamie Stacey, Dmitry Sityaev, Kris Y. Hong
https://arxiv.org/abs/2507.21642

Whilter: A Whisper-based Data Filter for "In-the-Wild" Speech Corpora Using Utterance-level Multi-Task Classification
Large-scale in-the-wild speech datasets have become more prevalent in recent years due to increased interest in models that can learn useful features from unlabelled data for tasks such as speech recognition or synthesis. These datasets often contain undesirable features, such as multiple speakers, non-target languages, and music, which may impact model learning. The Whilter model is proposed as a multitask solution to identify these undesirable samples. Whilter uses a Whisper encoder with an a…

A Descriptor Is All You Need: Accurate Machine Learning of Nonadiabatic Coupling Vectors
Jakub Martinka, Lina Zhang, Yi-Fan Hou, Miko{\l}aj Martyka, Ji\v{r}\'i Pittner, Mario Barbatti, Pavlo O. Dral
https://arxiv.org/abs/2505.23344

A Descriptor Is All You Need: Accurate Machine Learning of Nonadiabatic Coupling Vectors
Nonadiabatic couplings (NACs) play a crucial role in modeling photochemical and photophysical processes with methods such as the widely used fewest-switches surface hopping (FSSH). There is therefore a strong incentive to machine learn NACs for accelerating simulations. However, this is challenging due to NACs' vectorial, double-valued character and the singularity near a conical intersection seam. For the first time, we design NAC-specific descriptors based on our domain expertise and show tha…

Smart Cuts: Enhance Active Learning for Vulnerability Detection by Pruning Bad Seeds
Xiang Lan, Tim Menzies, Bowen Xu
https://arxiv.org/abs/2506.20444 http…

Smart Cuts: Enhance Active Learning for Vulnerability Detection by Pruning Bad Seeds
Vulnerability detection is crucial for identifying security weaknesses in software systems. However, the effectiveness of machine learning models in this domain is often hindered by low-quality training datasets, which contain noisy, mislabeled, or imbalanced samples. This paper proposes a novel dataset maps-empowered approach that systematically identifies and mitigates hard-to-learn outliers, referred to as "bad seeds", to improve model training efficiency. Our approach can categorize trainin…

Amplifying Machine Learning Attacks Through Strategic Compositions
Yugeng Liu, Zheng Li, Hai Huang, Michael Backes, Yang Zhang
https://arxiv.org/abs/2506.18870

Amplifying Machine Learning Attacks Through Strategic Compositions
Machine learning (ML) models are proving to be vulnerable to a variety of attacks that allow the adversary to learn sensitive information, cause mispredictions, and more. While these attacks have been extensively studied, current research predominantly focuses on analyzing each attack type individually. In practice, however, adversaries may employ multiple attack strategies simultaneously rather than relying on a single approach. This prompts a crucial yet underexplored question: When the adver…

A Deep Learning Based Method for Fast Registration of Cardiac Magnetic Resonance Images
Benjamin Graham
https://arxiv.org/abs/2506.19167 https://

A Deep Learning Based Method for Fast Registration of Cardiac Magnetic Resonance Images
Image registration is used in many medical image analysis applications, such as tracking the motion of tissue in cardiac images, where cardiac kinematics can be an indicator of tissue health. Registration is a challenging problem for deep learning algorithms because ground truth transformations are not feasible to create, and because there are potentially multiple transformations that can produce images that appear correlated with the goal. Unsupervised methods have been proposed to learn to pr…

This https://arxiv.org/abs/2401.17909 has been replaced.
link: https://scholar.google.com/scholar?q=a

Regularizing Fairness in Optimal Policy Learning with Distributional Targets
A decision maker typically (i) incorporates training data to learn about the relative effectiveness of treatments, and (ii) chooses an implementation mechanism that implies an ``optimal'' predicted outcome distribution according to some target functional. Nevertheless, a fairness-aware decision maker may not be satisfied achieving said optimality at the cost of being ``unfair" against a subgroup of the population, in the sense that the outcome distribution in that subgroup deviates too strongly…

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...

Conservative quantum offline model-based optimization
Kristian Sotirov, Annie E. Paine, Savvas Varsamopoulos, Antonio A. Gentile, Osvaldo Simeone
https://arxiv.org/abs/2506.19714 …

Conservative quantum offline model-based optimization
Offline model-based optimization (MBO) refers to the task of optimizing a black-box objective function using only a fixed set of prior input-output data, without any active experimentation. Recent work has introduced quantum extremal learning (QEL), which leverages the expressive power of variational quantum circuits to learn accurate surrogate functions by training on a few data points. However, as widely studied in the classical machine learning literature, predictive models may incorrectly e…

Embedded FPGA Acceleration of Brain-Like Neural Networks: Online Learning to Scalable Inference
Muhammad Ihsan Al Hafiz, Naresh Ravichandran, Anders Lansner, Pawel Herman, Artur Podobas
https://arxiv.org/abs/2506.18530

Embedded FPGA Acceleration of Brain-Like Neural Networks: Online Learning to Scalable Inference
Edge AI applications increasingly require models that can learn and adapt on-device with minimal energy budget. Traditional deep learning models, while powerful, are often overparameterized, energy-hungry, and dependent on cloud connectivity. Brain-Like Neural Networks (BLNNs), such as the Bayesian Confidence Propagation Neural Network (BCPNN), propose a neuromorphic alternative by mimicking cortical architecture and biologically-constrained learning. They offer sparse architectures with local …

This https://arxiv.org/abs/2503.09492 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Learning Cascade Ranking as One Network
Cascade Ranking is a prevalent architecture in large-scale top-k selection systems like recommendation and advertising platforms. Traditional training methods focus on single-stage optimization, neglecting interactions between stages. Recent advances have introduced interaction-aware training paradigms, but still struggle to 1) align training objectives with the goal of the entire cascade ranking (i.e., end-to-end recall of ground-truth items) and 2) learn effective collaboration patterns for d…

A Foundation Model for Massive MIMO Precoding with an Adaptive per-User Rate-Power Tradeoff
J\'er\^ome Emery, Ali Hasanzadeh Karkan, Jean-Fran\c{c}ois Frigon, Fran\c{c}ois Leduc-Primeau
https://arxiv.org/abs/2507.18587

A Foundation Model for Massive MIMO Precoding with an Adaptive per-User Rate-Power Tradeoff
Deep learning (DL) has emerged as a solution for precoding in massive multiple-input multiple-output (mMIMO) systems due to its capacity to learn the characteristics of the propagation environment. However, training such a model requires high-quality, local datasets at the deployment site, which are often difficult to collect. We propose a transformer-based foundation model for mMIMO precoding that seeks to minimize the energy consumption of the transmitter while dynamically adapting to per-use…

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…

Learning to Communicate in Multi-Agent Reinforcement Learning for Autonomous Cyber Defence
Faizan Contractor, Li Li, Ranwa Al Mallah
https://arxiv.org/abs/2507.14658

Learning to Communicate in Multi-Agent Reinforcement Learning for Autonomous Cyber Defence
Popular methods in cooperative Multi-Agent Reinforcement Learning with partially observable environments typically allow agents to act independently during execution, which may limit the coordinated effect of the trained policies. However, by sharing information such as known or suspected ongoing threats, effective communication can lead to improved decision-making in the cyber battle space. We propose a game design where defender agents learn to communicate and defend against imminent cyber th…

Numerical Artifacts in Learning Dynamical Systems
Bing-Ze Lu, Richard Tsai
https://arxiv.org/abs/2507.14491 https://arxiv.org/pdf/250…

Numerical Artifacts in Learning Dynamical Systems
In many applications, one needs to learn a dynamical system from its solutions sampled at a finite number of time points. The learning problem is often formulated as an optimization problem over a chosen function class. However, in the optimization procedure, it is necessary to employ a numerical scheme to integrate candidate dynamical systems and assess how their solutions fit the data. This paper reveals potentially serious effects of a chosen numerical scheme on the learning outcome. In …

✨ What’s it like to join the Trust & Identity Mentorship Programme (TIM)?
“If you are thinking about joining TIM—don’t hesitate. Learning from international experts, gaining practical skills, building a professional network, and doing all that while being supported and financially compensated, it’s an opportunity I’m grateful I didn’t miss." – Jovan Simonoski
Applications for the next TIM cohort are open until 5 August 2025.
👉 Learn more and apply:

CA-Cut: Crop-Aligned Cutout for Data Augmentation to Learn More Robust Under-Canopy Navigation
Robel Mamo, Taeyeong Choi
https://arxiv.org/abs/2507.17727 https://

CA-Cut: Crop-Aligned Cutout for Data Augmentation to Learn More Robust Under-Canopy Navigation
State-of-the-art visual under-canopy navigation methods are designed with deep learning-based perception models to distinguish traversable space from crop rows. While these models have demonstrated successful performance, they require large amounts of training data to ensure reliability in real-world field deployment. However, data collection is costly, demanding significant human resources for in-field sampling and annotation. To address this challenge, various data augmentation techniques are…

Decentralized Federated Learning of Probabilistic Generative Classifiers
Aritz P\'erez, Carlos Echegoyen, Guzm\'an Santaf\'e
https://arxiv.org/abs/2507.17285

Decentralized Federated Learning of Probabilistic Generative Classifiers
Federated learning is a paradigm of increasing relevance in real world applications, aimed at building a global model across a network of heterogeneous users without requiring the sharing of private data. We focus on model learning over decentralized architectures, where users collaborate directly to update the global model without relying on a central server. In this context, the current paper proposes a novel approach to collaboratively learn probabilistic generative classifiers with a parame…

Optimizing Federated Learning using Remote Embeddings for Graph Neural Networks
Pranjal Naman, Yogesh Simmhan
https://arxiv.org/abs/2506.12425 https://

Optimizing Federated Learning using Remote Embeddings for Graph Neural Networks
Graph Neural Networks (GNNs) have experienced rapid advancements in recent years due to their ability to learn meaningful representations from graph data structures. Federated Learning (FL) has emerged as a viable machine learning approach for training a shared model on decentralized data, addressing privacy concerns while leveraging parallelism. Existing methods that address the unique requirements of federated GNN training using remote embeddings to enhance convergence accuracy are limited by…

Exploration-Exploitation Tradeoff in Universal Lossy Compression
Nir Weinberger, Ram Zamir
https://arxiv.org/abs/2506.20261 https://a…

Exploration-Exploitation Tradeoff in Universal Lossy Compression
Universal compression can learn the source and adapt to it either in a batch mode (forward adaptation), or in a sequential mode (backward adaptation). We recast the sequential mode as a multi-armed bandit problem, a fundamental model in reinforcement-learning, and study the trade-off between exploration and exploitation in the lossy compression case. We show that a previously proposed "natural type selection" scheme can be cast as a reconstruction-directed MAB algorithm, for sequential lossy co…

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

Next stop in our NLP timeline is 2013, the introduction of low dimensional dense word vectors - so-called "word embeddings" - based on distributed semantics, as e.g. word2vec by Mikolov et al. from Google, which enabled representation learning on text.
T. Mikolov et al. (2013). Efficient Estimation of Word Representations in Vector Space.
…

Efficient Estimation of Word Representations in Vector Space
We propose two novel model architectures for computing continuous vector representations of words from very large data sets. The quality of these representations is measured in a word similarity task, and the results are compared to the previously best performing techniques based on different types of neural networks. We observe large improvements in accuracy at much lower computational cost, i.e. it takes less than a day to learn high quality word vectors from a 1.6 billion words data set. Fur…

Delighted to see these two new papers come out in Nature (they've been on bioRxiv for a while).
How does Pavlov's dog learn that the bell predicts the food? One answer is that the bell appears ``close'' in time to the food and that enables learning. We're certain that dopamine has something to do with learning these kinds of associations. But the definition of ``close'' in time is actually really difficult to pin down. You can get associations over prett…

@… I think it’s partially a question of motivation for me. Everyone around me speaks English, so learning German is… low on the list.
I hope to take more classes, and learn more, and eventually become proficient. But I think fluency, or thinking in German, is probably never going to happen for me.
I’m OK with that, most days. 🙃

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…

CC-LEARN: Cohort-based Consistency Learning
Xiao Ye, Shaswat Shrivastava, Zhaonan Li, Jacob Dineen, Shijie Lu, Avneet Ahuja, Ming Shen, Zhikun Xu, Ben Zhou
https://arxiv.org/abs/2506.15662

CC-LEARN: Cohort-based Consistency Learning
Large language models excel at many tasks but still struggle with consistent, robust reasoning. We introduce Cohort-based Consistency Learning (CC-Learn), a reinforcement learning framework that improves the reliability of LLM reasoning by training on cohorts of similar questions derived from shared programmatic abstractions. To enforce cohort-level consistency, we define a composite objective combining cohort accuracy, a retrieval bonus for effective problem decomposition, and a rejection pena…

Exact Finite Koopman Embedding of Block-Oriented Polynomial Systems
Lucian Cristian Iacob, Roland T\'oth, Maarten Schoukens
https://arxiv.org/abs/2507.15093

Exact Finite Koopman Embedding of Block-Oriented Polynomial Systems
The challenge of finding exact and finite-dimensional Koopman embeddings of nonlinear systems has been largely circumvented by employing data-driven techniques to learn models of different complexities (e.g., linear, bilinear, input affine). Although these models may provide good accuracy, selecting the model structure and dimension is still ad-hoc and it is difficult to quantify the error that is introduced. In contrast to the general trend of data-driven learning, in this paper, we develop a …

CosmoFlow: Scale-Aware Representation Learning for Cosmology with Flow Matching
Sidharth Kannan, Tian Qiu, Carolina Cuesta-Lazaro, Haewon Jeong
https://arxiv.org/abs/2507.11842

CosmoFlow: Scale-Aware Representation Learning for Cosmology with Flow Matching
Generative machine learning models have been demonstrated to be able to learn low dimensional representations of data that preserve information required for downstream tasks. In this work, we demonstrate that flow matching based generative models can learn compact, semantically rich latent representations of field level cold dark matter (CDM) simulation data without supervision. Our model, CosmoFlow, learns representations 32x smaller than the raw field data, usable for field level reconstructi…

As Canada Day approaches, this story of a Mom finding her Canadian identity through helping Syrian refugees settle here after 2015 is poignant.
"In 2025, being a Canadian woman to me means looking out for our neighbours, leaning into differences in culture, religious practices and learning how to help others in need. Because we are not different at all. We are all just looking for safety and peace. It's our Canadian values of equality, respect and freedom in action.
It is the singular privilege of my life to walk alongside these families from Cape Breton and those who are newcomers to Canada. It's changed how I live, and I intend to do this work as long as I am able. I learn from them grace, service, faith and hope. They taught me how to be a Canadian.”
#Canada #CanPoli #CdnPoli #Refugees #Immigration #Syria #AlanKurdi
https://www.cbc.ca/news/canada/nova-scotia/first-person-cape-breton-welcomes-syrian-refugees-1.7559341

Learning, Reasoning, Refinement: A Framework for Kahneman's Dual-System Intelligence in GUI Agents
Jinjie Wei, Jiyao Liu, Lihao Liu, Ming Hu, Junzhi Ning, Mingcheng Li, Weijie Yin, Junjun He, Xiao Liang, Chao Feng, Dingkang Yang
https://arxiv.org/abs/2506.17913

Learning, Reasoning, Refinement: A Framework for Kahneman's Dual-System Intelligence in GUI Agents
Graphical User Interface (GUI) agents have made significant progress in automating digital tasks through the utilization of computer vision and language models. Nevertheless, existing agent systems encounter notable limitations. Firstly, they predominantly depend on trial and error decision making rather than progressive reasoning, thereby lacking the capability to learn and adapt from interactive encounters. Secondly, these systems are assessed using overly simplistic single step accuracy metr…

PIMBS: Efficient Body Schema Learning for Musculoskeletal Humanoids with Physics-Informed Neural Networks
Kento Kawaharazuka, Takahiro Hattori, Keita Yoneda, Kei Okada
https://arxiv.org/abs/2506.20343

PIMBS: Efficient Body Schema Learning for Musculoskeletal Humanoids with Physics-Informed Neural Networks
Musculoskeletal humanoids are robots that closely mimic the human musculoskeletal system, offering various advantages such as variable stiffness control, redundancy, and flexibility. However, their body structure is complex, and muscle paths often significantly deviate from geometric models. To address this, numerous studies have been conducted to learn body schema, particularly the relationships among joint angles, muscle tension, and muscle length. These studies typically rely solely on data …

At Berlin Buzzwords 2025, join Dhrubo Saha to discover how OpenSearch pipelines are integrating ML inference processors for powerful multi-modal search. Learn to search directly within images, audio, and text – locally on your own hardware!
Learn more: https://

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…

Learning Acceleration Algorithms for Fast Parametric Convex Optimization with Certified Robustness
Rajiv Sambharya, Jinho Bok, Nikolai Matni, George Pappas
https://arxiv.org/abs/2507.16264

Learning Acceleration Algorithms for Fast Parametric Convex Optimization with Certified Robustness
We develop a machine-learning framework to learn hyperparameter sequences for accelerated first-order methods (e.g., the step size and momentum sequences in accelerated gradient descent) to quickly solve parametric convex optimization problems with certified robustness. We obtain a strong form of robustness guarantee -- certification of worst-case performance over all parameters within a set after a given number of iterations -- through regularization-based training. The regularization term is …

This https://arxiv.org/abs/2412.17629 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csNE_…

Learn from Global Correlations: Enhancing Evolutionary Algorithm via Spectral GNN
Evolutionary algorithms (EAs) simulate natural selection but have two main limitations: (1) they rarely update individuals based on global correlations, limiting comprehensive learning; (2) they struggle with balancing exploration and exploitation, where excessive exploitation causes premature convergence, and excessive exploration slows down the search. Moreover, EAs often depend on manual parameter settings, which can disrupt the exploration-exploitation balance.To address these issues, we pr…

Diverse and Adaptive Behavior Curriculum for Autonomous Driving: A Student-Teacher Framework with Multi-Agent RL
Ahmed Abouelazm, Johannes Ratz, Philip Sch\"orner, J. Marius Z\"ollner
https://arxiv.org/abs/2507.19146

Diverse and Adaptive Behavior Curriculum for Autonomous Driving: A Student-Teacher Framework with Multi-Agent RL
Autonomous driving faces challenges in navigating complex real-world traffic, requiring safe handling of both common and critical scenarios. Reinforcement learning (RL), a prominent method in end-to-end driving, enables agents to learn through trial and error in simulation. However, RL training often relies on rule-based traffic scenarios, limiting generalization. Additionally, current scenario generation methods focus heavily on critical scenarios, neglecting a balance with routine driving beh…

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…

Optimal Transceiver Design in Over-the-Air Federated Distillation
Zihao Hu (The Chinese University of Hong Kong), Jia Yan (The Hong Kong University of Science and Technology), Ying-Jun Angela Zhang (The Chinese University of Hong Kong), Jun Zhang (The Hong Kong University of Science and Technology), Khaled B. Letaief (The Hong Kong University of Science and Technology)

Optimal Transceiver Design in Over-the-Air Federated Distillation
The rapid proliferation and growth of artificial intelligence (AI) has led to the development of federated learning (FL). FL allows wireless devices (WDs) to cooperatively learn by sharing only local model parameters, without needing to share the entire dataset. However, the emergence of large AI models has made existing FL approaches inefficient, due to the significant communication overhead required. In this paper, we propose a novel over-the-air federated distillation (FD) framework by syner…

PICore: Physics-Informed Unsupervised Coreset Selection for Data Efficient Neural Operator Training
Anirudh Satheesh, Anant Khandelwal, Mucong Ding, Radu Balan
https://arxiv.org/abs/2507.17151

PICore: Physics-Informed Unsupervised Coreset Selection for Data Efficient Neural Operator Training
Neural operators offer a powerful paradigm for solving partial differential equations (PDEs) that cannot be solved analytically by learning mappings between function spaces. However, there are two main bottlenecks in training neural operators: they require a significant amount of training data to learn these mappings, and this data needs to be labeled, which can only be accessed via expensive simulations with numerical solvers. To alleviate both of these issues simultaneously, we propose PICore…

Data-Agnostic Cardinality Learning from Imperfect Workloads
Peizhi Wu, Rong Kang, Tieying Zhang, Jianjun Chen, Ryan Marcus, Zachary G. Ives
https://arxiv.org/abs/2506.16007

Data-Agnostic Cardinality Learning from Imperfect Workloads
Cardinality estimation (CardEst) is a critical aspect of query optimization. Traditionally, it leverages statistics built directly over the data. However, organizational policies (e.g., regulatory compliance) may restrict global data access. Fortunately, query-driven cardinality estimation can learn CardEst models using query workloads. However, existing query-driven models often require access to data or summaries for best performance, and they assume perfect training workloads with complete a…

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…

This https://arxiv.org/abs/2412.17629 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csNE_…

Learn from Global Correlations: Enhancing Evolutionary Algorithm via Spectral GNN
Evolutionary algorithms (EAs) simulate natural selection but have two main limitations: (1) they rarely update individuals based on global correlations, limiting comprehensive learning; (2) they struggle with balancing exploration and exploitation, where excessive exploitation causes premature convergence, and excessive exploration slows down the search. Moreover, EAs often depend on manual parameter settings, which can disrupt the exploration-exploitation balance.To address these issues, we pr…

Is It Safe To Learn And Share? On Psychological Safety and Social Learning in (Agile) Communities of Practice
Christiaan Verwijs, Evelien Acun-Roos, Daniel Russo
https://arxiv.org/abs/2507.01065

Is It Safe To Learn And Share? On Psychological Safety and Social Learning in (Agile) Communities of Practice
As hybrid, distributed, and asynchronous work models become more prevalent, continuous learning in Agile Software Development (ASD) gains renewed importance. Communities of Practice (CoPs) are increasingly adopted to support social learning beyond formal education, often relying on virtual communication. Psychological safety, a prerequisite for effective learning, remains insufficiently understood in these settings. This mixed-methods study investigates psychological safety within Agile CoPs th…

EKPC: Elastic Knowledge Preservation and Compensation for Class-Incremental Learning
Huaijie Wang, De Cheng, Lingfeng He, Yan Li, Jie Li, Nannan Wang, Xinbo Gao
https://arxiv.org/abs/2506.12351

EKPC: Elastic Knowledge Preservation and Compensation for Class-Incremental Learning
Class-Incremental Learning (CIL) aims to enable AI models to continuously learn from sequentially arriving data of different classes over time while retaining previously acquired knowledge. Recently, Parameter-Efficient Fine-Tuning (PEFT) methods, like prompt pool-based approaches and adapter tuning, have shown great attraction in CIL. However, these methods either introduce additional parameters that increase memory usage, or rely on rigid regularization techniques which reduce forgetting but …

Reconstruction of Dark Matter and Baryon Density From Galaxies: A Comparison of Linear, Halo Model and Machine Learning-Based Methods
Jordan Krywonos, Yurii Kvasiuk, Matthew C. Johnson, Moritz M\"unchmeyer
https://arxiv.org/abs/2507.12530

Reconstruction of Dark Matter and Baryon Density From Galaxies: A Comparison of Linear, Halo Model and Machine Learning-Based Methods
For many analyses in cosmology it is necessary to reconstruct the likely distribution of unobserved fields, such as dark matter or baryons, from observed luminous tracers. The dominant approach in cosmology has been to use the so-called halo model, which assumes radially symmetric profiles centered around luminous tracers such as galaxies. More recently, field-level machine learning methods have been proposed that can learn to estimate the unobserved field after being trained on simulations. Ho…

Unsupervised Ground Metric Learning
Janis Auffenberg, Jonas Bresch, Oleh Melnyk, Gabriele Steidl
https://arxiv.org/abs/2507.13094 https://

Unsupervised Ground Metric Learning
Data classification without access to labeled samples remains a challenging problem. It usually depends on an appropriately chosen distance between features, a topic addressed in metric learning. Recently, Huizing, Cantini and Peyré proposed to simultaneously learn optimal transport (OT) cost matrices between samples and features of the dataset. This leads to the task of finding positive eigenvectors of a certain nonlinear function that maps cost matrices to OT distances. Having this basic ide…

ErrorEraser: Unlearning Data Bias for Improved Continual Learning
Xuemei Cao, Hanlin Gu, Xin Yang, Bingjun Wei, Haoyang Liang, Xiangkun Wang, Tianrui Li
https://arxiv.org/abs/2506.09347

ErrorEraser: Unlearning Data Bias for Improved Continual Learning
Continual Learning (CL) primarily aims to retain knowledge to prevent catastrophic forgetting and transfer knowledge to facilitate learning new tasks. Unlike traditional methods, we propose a novel perspective: CL not only needs to prevent forgetting, but also requires intentional forgetting.This arises from existing CL methods ignoring biases in real-world data, leading the model to learn spurious correlations that transfer and amplify across tasks. From feature extraction and prediction resul…

Document Similarity Enhanced IPS Estimation for Unbiased Learning to Rank
Zeyan Liang, Graham McDonald, Iadh Ounis
https://arxiv.org/abs/2507.07909 https:/…

Document Similarity Enhanced IPS Estimation for Unbiased Learning to Rank
Learning to Rank (LTR) models learn from historical user interactions, such as user clicks. However, there is an inherent bias in the clicks of users due to position bias, i.e., users are more likely to click highly-ranked documents than low-ranked documents. To address this bias when training LTR models, many approaches from the literature re-weight the users' click data using Inverse Propensity Scoring (IPS). IPS re-weights the user's clicks proportionately to the position in the historical r…

A Hybrid Neural Network -- Polynomial Series Scheme for Learning Invariant Manifolds of Discrete Dynamical Systems
Dimitrios G. Patsatzis, Nikolaos Kazantzis, Ioannis G. Kevrekidis, Constantinos Siettos
https://arxiv.org/abs/2506.13950

A Hybrid Neural Network -- Polynomial Series Scheme for Learning Invariant Manifolds of Discrete Dynamical Systems
We propose a hybrid machine learning scheme to learn -- in physics-informed and numerical analysis-informed fashion -- invariant manifolds (IM) of discrete maps for constructing reduced-order models (ROMs) for dynamical systems. The proposed scheme combines polynomial series with shallow neural networks, exploiting the complementary strengths of both approaches. Polynomials enable an efficient and accurate modeling of ROMs with guaranteed local exponential convergence rate around the fixed poin…

Attention on flow control: transformer-based reinforcement learning for lift regulation in highly disturbed flows
Zhecheng Liu, Jeff D. Eldredge
https://arxiv.org/abs/2506.10153

Attention on flow control: transformer-based reinforcement learning for lift regulation in highly disturbed flows
A linear flow control strategy designed for weak disturbances may not remain effective in sequences of strong disturbances due to nonlinear interactions, but it is sensible to leverage it for developing a better strategy. In the present study, we propose a transformer-based reinforcement learning (RL) framework to learn an effective control strategy for regulating aerodynamic lift in gust sequences via pitch control. The transformer addresses the challenge of partial observability from limited …

Self-Supervised Inductive Logic Programming
Stassa Patsantzis
https://arxiv.org/abs/2507.16405 https://arxiv.org/pdf/2507.16405

Self-Supervised Inductive Logic Programming
Inductive Logic Programming (ILP) approaches like Meta \-/ Interpretive Learning (MIL) can learn, from few examples, recursive logic programs with invented predicates that generalise well to unseen instances. This ability relies on a background theory and negative examples, both carefully selected with expert knowledge of a learning problem and its solutions. But what if such a problem-specific background theory or negative examples are not available? We formalise this question as a new setting…

Foundation Models as Class-Incremental Learners for Dermatological Image Classification
Mohamed Elkhayat, Mohamed Mahmoud, Jamil Fayyad, Nourhan Bayasi
https://arxiv.org/abs/2507.14050

Foundation Models as Class-Incremental Learners for Dermatological Image Classification
Class-Incremental Learning (CIL) aims to learn new classes over time without forgetting previously acquired knowledge. The emergence of foundation models (FM) pretrained on large datasets presents new opportunities for CIL by offering rich, transferable representations. However, their potential for enabling incremental learning in dermatology remains largely unexplored. In this paper, we systematically evaluate frozen FMs pretrained on large-scale skin lesion datasets for CIL in dermatological …

Aligning Humans and Robots via Reinforcement Learning from Implicit Human Feedback
Suzie Kim, Hye-Bin Shin, Seong-Whan Lee
https://arxiv.org/abs/2507.13171

Aligning Humans and Robots via Reinforcement Learning from Implicit Human Feedback
Conventional reinforcement learning (RL) ap proaches often struggle to learn effective policies under sparse reward conditions, necessitating the manual design of complex, task-specific reward functions. To address this limitation, rein forcement learning from human feedback (RLHF) has emerged as a promising strategy that complements hand-crafted rewards with human-derived evaluation signals. However, most existing RLHF methods depend on explicit feedback mechanisms such as button presses or pr…

Beyond Rate Coding: Surrogate Gradients Enable Spike Timing Learning in Spiking Neural Networks
Ziqiao Yu, Pengfei Sun, Dan F. M. Goodman
https://arxiv.org/abs/2507.16043 https:…

Beyond Rate Coding: Surrogate Gradients Enable Spike Timing Learning in Spiking Neural Networks
We investigate the extent to which Spiking Neural Networks (SNNs) trained with Surrogate Gradient Descent (Surrogate GD), with and without delay learning, can learn from precise spike timing beyond firing rates. We first design synthetic tasks isolating intra-neuron inter-spike intervals and cross-neuron synchrony under matched spike counts. On more complex spike-based speech recognition datasets (Spiking Heidelberg Digits (SHD) and Spiking Speech Commands (SSC), we construct variants where spi…

Neural Functions for Learning Periodic Signal
Woojin Cho, Minju Jo, Kookjin Lee, Noseong Park
https://arxiv.org/abs/2506.09526 https://

Neural Functions for Learning Periodic Signal
As function approximators, deep neural networks have served as an effective tool to represent various signal types. Recent approaches utilize multi-layer perceptrons (MLPs) to learn a nonlinear mapping from a coordinate to its corresponding signal, facilitating the learning of continuous neural representations from discrete data points. Despite notable successes in learning diverse signal types, coordinate-based MLPs often face issues of overfitting and limited generalizability beyond the train…

MT4DP: Data Poisoning Attack Detection for DL-based Code Search Models via Metamorphic Testing
Gong Chen, Wenjie Liu, Xiaoyuan Xie, Xunzhu Tang, Tegawend\'e F. Bissyand\'e, Songqiang Chen
https://arxiv.org/abs/2507.11092

MT4DP: Data Poisoning Attack Detection for DL-based Code Search Models via Metamorphic Testing
Recently, several studies have indicated that data poisoning attacks pose a severe security threat to deep learning-based (DL-based) code search models. Attackers inject carefully crafted malicious patterns into the training data, misleading the code search model to learn these patterns during training. During the usage of the poisoned code search model for inference, once the malicious pattern is triggered, the model tends to rank the vulnerability code higher. However, existing detection meth…

Application of LLMs to Multi-Robot Path Planning and Task Allocation
Ashish Kumar
https://arxiv.org/abs/2507.07302 https://arxiv.org/…

Application of LLMs to Multi-Robot Path Planning and Task Allocation
Efficient exploration is a well known problem in deep reinforcement learning and this problem is exacerbated in multi-agent reinforcement learning due the intrinsic complexities of such algorithms. There are several approaches to efficiently explore an environment to learn to solve tasks by multi-agent operating in that environment, of which, the idea of expert exploration is investigated in this work. More specifically, this work investigates the application of large-language models as expert …

Directed Acyclic Graph Convolutional Networks
Samuel Rey, Hamed Ajorlou, Gonzalo Mateos
https://arxiv.org/abs/2506.12218 https://arxi…

Directed Acyclic Graph Convolutional Networks
Directed acyclic graphs (DAGs) are central to science and engineering applications including causal inference, scheduling, and neural architecture search. In this work, we introduce the DAG Convolutional Network (DCN), a novel graph neural network (GNN) architecture designed specifically for convolutional learning from signals supported on DAGs. The DCN leverages causal graph filters to learn nodal representations that account for the partial ordering inherent to DAGs, a strong inductive bias d…

The Emergence of Deep Reinforcement Learning for Path Planning
Thanh Thi Nguyen, Saeid Nahavandi, Imran Razzak, Dung Nguyen, Nhat Truong Pham, Quoc Viet Hung Nguyen
https://arxiv.org/abs/2507.15469

The Emergence of Deep Reinforcement Learning for Path Planning
The increasing demand for autonomous systems in complex and dynamic environments has driven significant research into intelligent path planning methodologies. For decades, graph-based search algorithms, linear programming techniques, and evolutionary computation methods have served as foundational approaches in this domain. Recently, deep reinforcement learning (DRL) has emerged as a powerful method for enabling autonomous agents to learn optimal navigation strategies through interaction with t…

This https://arxiv.org/abs/2503.10503 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Sample Compression for Continual Learning
Continual learning algorithms aim to learn from a sequence of tasks, making the training distribution non-stationary. The majority of existing continual learning approaches in the literature rely on heuristics and do not provide learning guarantees. In this paper, we present a new method called Continual Pick-to-Learn (CoP2L), which is able to retain the most representative samples for each task in an efficient way. CoP2L combines the Pick-to-Learn algorithm (rooted in the sample compression th…

Three-dimensional Deep Shape Optimization with a Limited Dataset
Yongmin Kwon, Namwoo Kang
https://arxiv.org/abs/2506.12326 https://a…

Three-dimensional Deep Shape Optimization with a Limited Dataset
Generative models have attracted considerable attention for their ability to produce novel shapes. However, their application in mechanical design remains constrained due to the limited size and variability of available datasets. This study proposes a deep learning-based optimization framework specifically tailored for shape optimization with limited datasets, leveraging positional encoding and a Lipschitz regularization term to robustly learn geometric characteristics and maintain a meaningful…

Past, Present and Future: Exploring Adaptive AI in Software Development Bots
Omar Elsisi, Glaucia Melo
https://arxiv.org/abs/2507.10822 https://

Past, Present and Future: Exploring Adaptive AI in Software Development Bots
Conversational agents, such as chatbots and virtual assistants, have become essential in software development, boosting productivity, collaboration, and automating various tasks. This paper examines the role of adaptive AI-powered conversational agents in software development, highlighting their ability to offer dynamic, context-aware assistance to developers. Unlike traditional rule-based systems, adaptive AI agents use machine learning and natural language processing to learn from interaction…

Gradient Similarity Surgery in Multi-Task Deep Learning
Thomas Borsani, Andrea Rosani, Giuseppe Nicosia, Giuseppe Di Fatta
https://arxiv.org/abs/2506.06130

Gradient Similarity Surgery in Multi-Task Deep Learning
The multi-task learning ($MTL$) paradigm aims to simultaneously learn multiple tasks within a single model capturing higher-level, more general hidden patterns that are shared by the tasks. In deep learning, a significant challenge in the backpropagation training process is the design of advanced optimisers to improve the convergence speed and stability of the gradient descent learning rule. In particular, in multi-task deep learning ($MTDL$) the multitude of tasks may generate potentially conf…

This https://arxiv.org/abs/2501.00296 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csRO_…

From Pixels to Predicates: Learning Symbolic World Models via Pretrained Vision-Language Models
Our aim is to learn to solve long-horizon decision-making problems in complex robotics domains given low-level skills and a handful of short-horizon demonstrations containing sequences of images. To this end, we focus on learning abstract symbolic world models that facilitate zero-shot generalization to novel goals via planning. A critical component of such models is the set of symbolic predicates that define properties of and relationships between objects. In this work, we leverage pretrained …

Dually Hierarchical Drift Adaptation for Online Configuration Performance Learning
Zezhen Xiang, Jingzhi Gong, Tao Chen
https://arxiv.org/abs/2507.08730 ht…

Dually Hierarchical Drift Adaptation for Online Configuration Performance Learning
Modern configurable software systems need to learn models that correlate configuration and performance. However, when the system operates in dynamic environments, the workload variations, hardware changes, and system updates will inevitably introduce concept drifts at different levels - global drifts, which reshape the performance landscape of the entire configuration space; and local drifts, which only affect certain sub-regions of that space. As such, existing offline and transfer learning ap…

MOORL: A Framework for Integrating Offline-Online Reinforcement Learning
Gaurav Chaudhary, Wassim Uddin Mondal, Laxmidhar Behera
https://arxiv.org/abs/2506.09574

MOORL: A Framework for Integrating Offline-Online Reinforcement Learning
Sample efficiency and exploration remain critical challenges in Deep Reinforcement Learning (DRL), particularly in complex domains. Offline RL, which enables agents to learn optimal policies from static, pre-collected datasets, has emerged as a promising alternative. However, offline RL is constrained by issues such as out-of-distribution (OOD) actions that limit policy performance and generalization. To overcome these limitations, we propose Meta Offline-Online Reinforcement Learning (MOORL), …

Dilution, Diffusion and Symbiosis in Spatial Prisoner's Dilemma with Reinforcement Learning
Gustavo C. Mangold, Heitor C. M. Fernandes, Mendeli H. Vainstein
https://arxiv.org/abs/2507.02211

Dilution, Diffusion and Symbiosis in Spatial Prisoner's Dilemma with Reinforcement Learning
Recent studies in the spatial prisoner's dilemma games with reinforcement learning have shown that static agents can learn to cooperate through a diverse sort of mechanisms, including noise injection, different types of learning algorithms and neighbours' payoff knowledge.In this work, using an independent multi-agent Q-learning algorithm, we study the effects of dilution and mobility in the spatial version of the prisoner's dilemma. Within this setting, different possible actions for the algor…

High-Order Deep Meta-Learning with Category-Theoretic Interpretation
David H. Mguni
https://arxiv.org/abs/2507.02634 https://arxiv.or…

High-Order Deep Meta-Learning with Category-Theoretic Interpretation
We introduce a new hierarchical deep learning framework for recursive higher-order meta-learning that enables neural networks (NNs) to construct, solve, and generalise across hierarchies of tasks. Central to this approach is a generative mechanism that creates \emph{virtual tasks} -- synthetic problem instances designed to enable the meta-learner to learn \emph{soft constraints} and unknown generalisable rules across related tasks. Crucially, this enables the framework to generate its own infor…

This https://arxiv.org/abs/2506.03703 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Learning-at-Criticality in Large Language Models for Quantum Field Theory and Beyond
Fundamental physics often confronts complex symbolic problems with few guiding exemplars or established principles. While artificial intelligence (AI) offers promise, its typical need for vast datasets to learn from hinders its use in these information-scarce frontiers. We introduce learning at criticality (LaC), a reinforcement learning (RL) scheme that tunes Large Language Models (LLMs) to a sharp learning transition, addressing this information scarcity. At this transition, LLMs achieve peak…

Latent Action Diffusion for Cross-Embodiment Manipulation
Erik Bauer, Elvis Nava, Robert K. Katzschmann
https://arxiv.org/abs/2506.14608 https://

Latent Action Diffusion for Cross-Embodiment Manipulation
End-to-end learning approaches offer great potential for robotic manipulation, but their impact is constrained by data scarcity and heterogeneity across different embodiments. In particular, diverse action spaces across different end-effectors create barriers for cross-embodiment learning and skill transfer. We address this challenge through diffusion policies learned in a latent action space that unifies diverse end-effector actions. We first show that we can learn a semantically aligned laten…

Efficient Preference-Based Reinforcement Learning: Randomized Exploration Meets Experimental Design
Andreas Schlaginhaufen, Reda Ouhamma, Maryam Kamgarpour
https://arxiv.org/abs/2506.09508

Efficient Preference-Based Reinforcement Learning: Randomized Exploration Meets Experimental Design
We study reinforcement learning from human feedback in general Markov decision processes, where agents learn from trajectory-level preference comparisons. A central challenge in this setting is to design algorithms that select informative preference queries to identify the underlying reward while ensuring theoretical guarantees. We propose a meta-algorithm based on randomized exploration, which avoids the computational challenges associated with optimistic approaches and remains tractable. We e…

Hybrid Diffusion Policies with Projective Geometric Algebra for Efficient Robot Manipulation Learning
Xiatao Sun, Yuxuan Wang, Shuo Yang, Yinxing Chen, Daniel Rakita
https://arxiv.org/abs/2507.05695

Hybrid Diffusion Policies with Projective Geometric Algebra for Efficient Robot Manipulation Learning
Diffusion policies have become increasingly popular in robot learning due to their reliable convergence in motion generation tasks. At a high level, these policies learn to transform noisy action trajectories into effective ones, conditioned on observations. However, each time such a model is trained in a robotics context, the network must relearn fundamental spatial representations and operations, such as translations and rotations, from scratch in order to ground itself and operate effectivel…

MultiGen: Using Multimodal Generation in Simulation to Learn Multimodal Policies in Real
Renhao Wang, Haoran Geng, Tingle Li, Feishi Wang, Gopala Anumanchipalli, Philipp Wu, Trevor Darrell, Boyi Li, Pieter Abbeel, Jitendra Malik, Alexei A. Efros
https://arxiv.org/abs/2507.02864

MultiGen: Using Multimodal Generation in Simulation to Learn Multimodal Policies in Real
Robots must integrate multiple sensory modalities to act effectively in the real world. Yet, learning such multimodal policies at scale remains challenging. Simulation offers a viable solution, but while vision has benefited from high-fidelity simulators, other modalities (e.g. sound) can be notoriously difficult to simulate. As a result, sim-to-real transfer has succeeded primarily in vision-based tasks, with multimodal transfer still largely unrealized. In this work, we tackle these challenge…

Sequence Modeling for Time-Optimal Quadrotor Trajectory Optimization with Sampling-based Robustness Analysis
Katherine Mao, Hongzhan Yu, Ruipeng Zhang, Igor Spasojevic, M Ani Hsieh, Sicun Gao, Vijay Kumar
https://arxiv.org/abs/2506.13915

Sequence Modeling for Time-Optimal Quadrotor Trajectory Optimization with Sampling-based Robustness Analysis
Time-optimal trajectories drive quadrotors to their dynamic limits, but computing such trajectories involves solving non-convex problems via iterative nonlinear optimization, making them prohibitively costly for real-time applications. In this work, we investigate learning-based models that imitate a model-based time-optimal trajectory planner to accelerate trajectory generation. Given a dataset of collision-free geometric paths, we show that modeling architectures can effectively learn the pat…

This https://arxiv.org/abs/2303.17475 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Learning distributed representations with efficient SoftMax normalization
Learning distributed representations, or embeddings, that encode the relational similarity patterns among objects is a relevant task in machine learning. A popular method to learn the embedding matrices $X, Y$ is optimizing a loss function of the term ${\rm SoftMax}(XY^T)$. The complexity required to calculate this term, however, runs quadratically with the problem size, making it a computationally heavy solution. In this article, we propose a linear-time heuristic approximation to compute the …

HAC-LOCO: Learning Hierarchical Active Compliance Control for Quadruped Locomotion under Continuous External Disturbances
Xiang Zhou, Xinyu Zhang, Qingrui Zhang
https://arxiv.org/abs/2507.02447

HAC-LOCO: Learning Hierarchical Active Compliance Control for Quadruped Locomotion under Continuous External Disturbances
Despite recent remarkable achievements in quadruped control, it remains challenging to ensure robust and compliant locomotion in the presence of unforeseen external disturbances. Existing methods prioritize locomotion robustness over compliance, often leading to stiff, high-frequency motions, and energy inefficiency. This paper, therefore, presents a two-stage hierarchical learning framework that can learn to take active reactions to external force disturbances based on force estimation. In the…

This https://arxiv.org/abs/2505.19946 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Inverse Q-Learning Done Right: Offline Imitation Learning in $Q^π$-Realizable MDPs
We study the problem of offline imitation learning in Markov decision processes (MDPs), where the goal is to learn a well-performing policy given a dataset of state-action pairs generated by an expert policy. Complementing a recent line of work on this topic that assumes the expert belongs to a tractable class of known policies, we approach this problem from a new angle and leverage a different type of structural assumption about the environment. Specifically, for the class of linear $Q^π$-rea…