Tootfinder

FairEquityFL -- A Fair and Equitable Client Selection in Federated Learning for Heterogeneous IoV Networks
Fahmida Islam, Adnan Mahmood, Noorain Mukhtiar, Kasun Eranda Wijethilake, Quan Z. Sheng
https://arxiv.org/abs/2509.20193

FairEquityFL -- A Fair and Equitable Client Selection in Federated Learning for Heterogeneous IoV Networks
Federated Learning (FL) has been extensively employed for a number of applications in machine learning, i.e., primarily owing to its privacy preserving nature and efficiency in mitigating the communication overhead. Internet of Vehicles (IoV) is one of the promising applications, wherein FL can be utilized to train a model more efficiently. Since only a subset of the clients can participate in each FL training round, challenges arise pertinent to fairness in the client selection process. Over t…

RoboSSM: Scalable In-context Imitation Learning via State-Space Models
Youngju Yoo, Jiaheng Hu, Yifeng Zhu, Bo Liu, Qiang Liu, Roberto Mart\'in-Mart\'in, Peter Stone
https://arxiv.org/abs/2509.19658

RoboSSM: Scalable In-context Imitation Learning via State-Space Models
In-context imitation learning (ICIL) enables robots to learn tasks from prompts consisting of just a handful of demonstrations. By eliminating the need for parameter updates at deployment time, this paradigm supports few-shot adaptation to novel tasks. However, recent ICIL methods rely on Transformers, which have computational limitations and tend to underperform when handling longer prompts than those seen during training. In this work, we introduce RoboSSM, a scalable recipe for in-context im…

Deep Learning for Clouds and Cloud Shadow Segmentation in Methane Satellite and Airborne Imaging Spectroscopy
Manuel Perez-Carrasco, Maya Nasr, Sebastien Roche, Chris Chan Miller, Zhan Zhang, Core Francisco Park, Eleanor Walker, Cecilia Garraffo, Douglas Finkbeiner, Ritesh Gautam, Steven Wofsy
https://arxiv.org/abs/2509.19665

Deep Learning for Clouds and Cloud Shadow Segmentation in Methane Satellite and Airborne Imaging Spectroscopy
Effective cloud and cloud shadow detection is a critical prerequisite for accurate retrieval of concentrations of atmospheric methane or other trace gases in hyperspectral remote sensing. This challenge is especially pertinent for MethaneSAT and for its airborne companion mission, MethaneAIR. In this study, we use machine learning methods to address the cloud and cloud shadow detection problem for sensors with these high spatial resolutions instruments. Cloud and cloud shadows in remote sensing…

Some thoughts from recent talks: 'AI and Machine Learning in Libraries: Promising, But Not Ready Yet' https://www.openobjects.org.uk/2025/10/ai-and-machine-learning-in-libraries-promising-but-not-ready-yet/

"AI in the guise of Machine Learning, Deep Learning, GenerativeAI (GenAI), or Large Language Models (LLMs)... can be very useful in certain application areas such as recognising or generating patterns in large data sets. However, their key drawback is that any correctness arguments will be inherently probabilistic as they are usually based on unknown data distributions and are therefore susceptible to errors (sometimes termed “hallucinations”). "

UserRL: Training Interactive User-Centric Agent via Reinforcement Learning
Cheng Qian, Zuxin Liu, Akshara Prabhakar, Jielin Qiu, Zhiwei Liu, Haolin Chen, Shirley Kokane, Heng Ji, Weiran Yao, Shelby Heinecke, Silvio Savarese, Caiming Xiong, Huan Wang
https://arxiv.org/abs/2509.19736

UserRL: Training Interactive User-Centric Agent via Reinforcement Learning
Reinforcement learning (RL) has shown promise in training agentic models that move beyond static benchmarks to engage in dynamic, multi-turn interactions. Yet, the ultimate value of such agents lies in their ability to assist users, a setting where diversity and dynamics of user interaction pose challenges. In this work, we propose UserRL, a unified framework for training and evaluating user-centric abilities through standardized gym environments paired with simulated users. We systematically v…

This week has been incredibly challenging, but sometimes with people who refuse to accept disagreement, there's only so much you can do.
If you're interested in learning more about anarcho-syndicalism, I’ve curated some excellent articles on my Linktree, mostly in Norwegian, but also some in English.
I’m planning to update it soon with more reliable sources beyond just blog posts.
Anyway, I'm not mad, just really exhausted.

Transfer Learning in Regression with Influential Points
Bingbing Wang, Jiaqi Wang, Yu Tang
https://arxiv.org/abs/2509.20272 https://arxiv.org/pdf/2509.2027…

Transfer Learning in Regression with Influential Points
Regression prediction plays a crucial role in practical applications and strongly relies on data annotation. However, due to prohibitive annotation costs or domain-specific constraints, labeled data in the target domain is often scarce, making transfer learning a critical solution by leveraging knowledge from resource-rich source domains. In the practical target scenario, although transfer learning has been widely applied, influential points can significantly distort parameter estimation for th…

Multilingual Hope Speech Detection: A Comparative Study of Logistic Regression, mBERT, and XLM-RoBERTa with Active Learning
T. O. Abiola, K. D. Abiodun, O. E. Olumide, O. O. Adebanji, O. Hiram Calvo, Grigori Sidorov
https://arxiv.org/abs/2509.20315

Multilingual Hope Speech Detection: A Comparative Study of Logistic Regression, mBERT, and XLM-RoBERTa with Active Learning
Hope speech language that fosters encouragement and optimism plays a vital role in promoting positive discourse online. However, its detection remains challenging, especially in multilingual and low-resource settings. This paper presents a multilingual framework for hope speech detection using an active learning approach and transformer-based models, including mBERT and XLM-RoBERTa. Experiments were conducted on datasets in English, Spanish, German, and Urdu, including benchmark test sets from …

The Impact of Structural Changes on Learning Capacity in the Fly Olfactory Neural Circuit
Katherine Xie, Gabriel Koch Ocker
https://arxiv.org/abs/2509.19351 https://

The Impact of Structural Changes on Learning Capacity in the Fly Olfactory Neural Circuit
The Drosophila mushroom body (MB) is known to be involved in olfactory learning and memory; the synaptic plasticity of the Kenyon cell (KC) to mushroom body output neuron (MBON) synapses plays a key role in the learning process. Previous research has focused on projection neuron (PN) to Kenyon cell (KC) connectivity within the MB; we examine how perturbations to the mushroom body circuit structure and changes in connectivity, specifically within the KC to mushroom body output neuron (MBON) neur…

The Syntax and Semantics of einsum
Maurice Wenig, Paul G. Rump, Mark Blacher, Joachim Giesen
https://arxiv.org/abs/2509.20020 https://arxiv.org/pdf/2509.20…

The Syntax and Semantics of einsum
In 2011, einsum was introduced to NumPy as a practical and convenient notation for tensor expressions in machine learning, quantum circuit simulation, and other fields. It has since been implemented in additional Python frameworks such as PyTorch and TensorFlow, as well as in other programming languages such as Julia. Despite its practical success, the einsum notation still lacks a solid theoretical basis, and is not unified across the different frameworks, limiting opportunities for formal rea…

You know that you’re teaching in #Switzerland when you catch the majority of students running the live broadcast of today’s #ski competition in a separate window while doing learning tasks
#AcademicChatter

I'm just reviewing some old(er) video I recorded quite a while ago ... and I admit that I'm eager to record in higher quality!
But hey, it's all a learning curve. I'm not feeling bad about the bad quality. I regard it pretty nice to see the advancement over time!
https://video.franzgraf.de/w/r3XH…

Choose Your Battles: Distributed Learning Over Multiple Tug of War Games
Siddharth Chandak, Ilai Bistritz, Nicholas Bambos
https://arxiv.org/abs/2509.20147 https://

Choose Your Battles: Distributed Learning Over Multiple Tug of War Games
Consider N players and K games taking place simultaneously. Each of these games is modeled as a Tug-of-War (ToW) game where increasing the action of one player decreases the reward for all other players. Each player participates in only one game at any given time. At each time step, a player decides the game in which they wish to participate in and the action they take in that game. Their reward depends on the actions of all players that are in the same game. This system of K games is termed `M…

An Empirical Analysis of Secure Federated Learning for Autonomous Vehicle Applications
Md Jueal Mia, M. Hadi Amini
https://arxiv.org/abs/2509.20223 https://

An Empirical Analysis of Secure Federated Learning for Autonomous Vehicle Applications
Federated Learning lends itself as a promising paradigm in enabling distributed learning for autonomous vehicles applications and ensuring data privacy while enhancing and refining predictive model performance through collaborative training on edge client vehicles. However, it remains vulnerable to various categories of cyber-attacks, necessitating more robust security measures to effectively mitigate potential threats. Poisoning attacks and inference attacks are commonly initiated within the f…

I have been learning #Rust for a couple of years, and using it for pet projects and demos alike. Working for a JVM-heavy company, I thought it would be my fate forever. Last week, I had a nice surprise: I convinced my management that using Rust for a particular project was the right choice. It’s not a huge project, but I want to describe my experience using Rust in a "real" project.

Intelligent Algorithm Selection for Recommender Systems: Meta-Learning via in-depth algorithm feature engineering
Jarne Mathi Decker
https://arxiv.org/abs/2509.20134 https://

Intelligent Algorithm Selection for Recommender Systems: Meta-Learning via in-depth algorithm feature engineering
The "No Free Lunch" theorem dictates that no single recommender algorithm is optimal for all users, creating a significant Algorithm Selection Problem. Standard meta-learning approaches aim to solve this by selecting an algorithm based on user features, but treat the fundamentally diverse algorithms themselves as equivalent, "black-box" choices. This thesis investigates the impact of overcoming this limitation by engineering a comprehensive feature set to explicitly characterize the algorithms …

C$^2$MIL: Synchronizing Semantic and Topological Causalities in Multiple Instance Learning for Robust and Interpretable Survival Analysis
Min Cen, Zhenfeng Zhuang, Yuzhe Zhang, Min Zeng, Baptiste Magnier, Lequan Yu, Hong Zhang, Liansheng Wang
https://arxiv.org/abs/2509.20152

C$^2$MIL: Synchronizing Semantic and Topological Causalities in Multiple Instance Learning for Robust and Interpretable Survival Analysis
Graph-based Multiple Instance Learning (MIL) is widely used in survival analysis with Hematoxylin and Eosin (H\&E)-stained whole slide images (WSIs) due to its ability to capture topological information. However, variations in staining and scanning can introduce semantic bias, while topological subgraphs that are not relevant to the causal relationships can create noise, resulting in biased slide-level representations. These issues can hinder both the interpretability and generalization of the …

Experimental insights into data augmentation techniques for deep learning-based multimode fiber imaging: limitations and success
Jawaria Maqbool, M. Imran Cheema
https://arxiv.org/abs/2511.19072 https://arxiv.org/pdf/2511.19072 https://arxiv.org/html/2511.19072
arXiv:2511.19072v1 Announce Type: new
Abstract: Multimode fiber~(MMF) imaging using deep learning has high potential to produce compact, minimally invasive endoscopic systems. Nevertheless, it relies on large, diverse real-world medical data, whose availability is limited by privacy concerns and practical challenges. Although data augmentation has been extensively studied in various other deep learning tasks, it has not been systematically explored for MMF imaging. This work provides the first in-depth experimental and computational study on the efficacy and limitations of augmentation techniques in this field. We demonstrate that standard image transformations and conditional generative adversarial-based synthetic speckle generation fail to improve, or even deteriorate, reconstruction quality, as they neglect the complex modal interference and dispersion that results in speckle formation. To address this, we introduce a physical data augmentation method in which only organ images are digitally transformed, while their corresponding speckles are experimentally acquired via fiber. This approach preserves the physics of light-fiber interaction and enhances the reconstruction structural similarity index measure~(SSIM) by up to 17\%, forming a viable system for reliable MMF imaging under limited data conditions.
toXiv_bot_toot

High-Dimensional Statistical Process Control via Manifold Fitting and Learning
Burak I. Tas, Enrique del Castillo
https://arxiv.org/abs/2509.19820 https://…

High-Dimensional Statistical Process Control via Manifold Fitting and Learning
We address the Statistical Process Control (SPC) of high-dimensional, dynamic industrial processes from two complementary perspectives: manifold fitting and manifold learning, both of which assume data lies on an underlying nonlinear, lower dimensional space. We propose two distinct monitoring frameworks for online or 'phase II' Statistical Process Control (SPC). The first method leverages state-of-the-art techniques in manifold fitting to accurately approximate the manifold where the data resi…

Generative inference unifies feedback processing for learning and perception in natural and artificial vision (here not prosthetic vision) https://www.biorxiv.org/content/10.1101/2025.10.21.683535v2

"“Papers with Code” went offline, the knowledge doesn’t have to" @…: https://blog.tib.eu/2025/10/02/papers-

Projective Kolmogorov Arnold Neural Networks (P-KANs): Entropy-Driven Functional Space Discovery for Interpretable Machine Learning
Alastair Poole, Stig McArthur, Saravan Kumar
https://arxiv.org/abs/2509.20049

Projective Kolmogorov Arnold Neural Networks (P-KANs): Entropy-Driven Functional Space Discovery for Interpretable Machine Learning
Kolmogorov-Arnold Networks (KANs) relocate learnable nonlinearities from nodes to edges, demonstrating remarkable capabilities in scientific machine learning and interpretable modeling. However, current KAN implementations suffer from fundamental inefficiencies due to redundancy in high-dimensional spline parameter spaces, where numerous distinct parameterisations yield functionally equivalent behaviors. This redundancy manifests as a "nuisance space" in the model's Jacobian, leading to suscept…

Neural Network Based Framework for Passive Intermodulation Cancellation in MIMO Systems
Xiaolong Li, Zhi-qin John Xu, Peiting You, Yifei Zhu
https://arxiv.org/abs/2509.19382 htt…

Neural Network Based Framework for Passive Intermodulation Cancellation in MIMO Systems
Passive intermodulation (PIM) has emerged as a critical source of self-interference in modern MIMO-OFDM systems, especially under the stringent requirements of 5G and beyond. Conventional cancellation methods often rely on complex nonlinear models with limited scalability and high computational cost. In this work, we propose a lightweight deep learning framework for PIM cancellation that leverages depthwise separable convolutions and dilated convolutions to efficiently capture nonlinear depende…

Discovering Association Rules in High-Dimensional Small Tabular Data
Erkan Karabulut, Daniel Daza, Paul Groth, Victoria Degeler
https://arxiv.org/abs/2509.20113 https://

Discovering Association Rules in High-Dimensional Small Tabular Data
Association Rule Mining (ARM) aims to discover patterns between features in datasets in the form of propositional rules, supporting both knowledge discovery and interpretable machine learning in high-stakes decision-making. However, in high-dimensional settings, rule explosion and computational overhead render popular algorithmic approaches impractical without effective search space reduction, challenges that propagate to downstream tasks. Neurosymbolic methods, such as Aerial+, have recently b…

CollaPipe: Adaptive Segment-Optimized Pipeline Parallelism for Collaborative LLM Training in Heterogeneous Edge Networks
Jiewei Chen, Xiumei Deng, Zehui Xiong, Shaoyong Guo, Xuesong Qiu, Ping Wang, Dusit Niyato
https://arxiv.org/abs/2509.19855

CollaPipe: Adaptive Segment-Optimized Pipeline Parallelism for Collaborative LLM Training in Heterogeneous Edge Networks
The increasing demand for intelligent mobile applications has made multi-agent collaboration with Transformer-based large language models (LLMs) essential in mobile edge computing (MEC) networks. However, training LLMs in such environments remains challenging due to heavy computation, high end-to-end latency, and limited model generalization. We introduce CollaPipe, a hybrid distributed learning framework that integrates collaborative pipeline parallelism with federated aggregation to support s…

Generalized Persistent Laplacians and their Spectral Properties
Arne Wolf, Jiyu Fan, Anthea Monod
https://arxiv.org/abs/2509.20220 https://arxiv.org/pdf/25…

Generalized Persistent Laplacians and their Spectral Properties
Laplacian operators are classical objects that are fundamental in both pure and applied mathematics and are becoming increasingly prominent in modern computational and data science fields such as applied and computational topology and application areas such as machine learning and network science. In this paper, we introduce a unifying operator-theoretic framework of generalized Laplacians as invariants that encompasses and extends all existing constructions, from discrete combinatorial setting…

FedOC: Multi-Server FL with Overlapping Client Relays in Wireless Edge Networks
Yun Ji, Zeyu Chen, Xiaoxiong Zhong, Yanan Ma, Sheng Zhang, Yuguang Fang
https://arxiv.org/abs/2509.19398

FedOC: Multi-Server FL with Overlapping Client Relays in Wireless Edge Networks
Multi-server Federated Learning (FL) has emerged as a promising solution to mitigate communication bottlenecks of single-server FL. We focus on a typical multi-server FL architecture, where the regions covered by different edge servers (ESs) may overlap. A key observation of this architecture is that clients located in the overlapping areas can access edge models from multiple ESs. Building on this insight, we propose FedOC (Federated learning with Overlapping Clients), a novel framework design…

Photon-starved polarimetry via functional classical shadows
Matteo Rosati, Miranda Parisi, Linda Sansoni, Eleonora Stefanutti, Andrea Chiuri, Marco Barbieri
https://arxiv.org/abs/2509.19547

Photon-starved polarimetry via functional classical shadows
Polarimetry and optical imaging techniques face challenges in photon-starved scenarios, where the low number of detected photons imposes a trade-off between image resolution, integration time, and sample sensitivity. Here we introduce a quantum-inspired method, functional classical shadows, for reconstructing a polarization profile in the low photon-flux regime. Our method harnesses correlations between neighbouring datapoints, based on the recent realisation that machine learning can estimate …

Deep learning for exoplanet detection and characterization by direct imaging at high contrast
Th\'eo Bodrito, Olivier Flasseur, Julien Mairal, Jean Ponce, Maud Langlois, Anne-Marie Lagrange
https://arxiv.org/abs/2509.20310

Deep learning for exoplanet detection and characterization by direct imaging at high contrast
Exoplanet imaging is a major challenge in astrophysics due to the need for high angular resolution and high contrast. We present a multi-scale statistical model for the nuisance component corrupting multivariate image series at high contrast. Integrated into a learnable architecture, it leverages the physics of the problem and enables the fusion of multiple observations of the same star in a way that is optimal in terms of detection signal-to-noise ratio. Applied to data from the VLT/SPHERE ins…

Replaced article(s) found for cs.LO. https://arxiv.org/list/cs.LO/new
[1/1]:
- Compact Rule-Based Classifier Learning via Gradient Descent
Javier Fumanal-Idocin, Raquel Fernandez-Peralta, Javier Andreu-Perez

PEPS: Quantum-Inspired Reinforcement Learning for Coherent Reasoning Traces in LLMs
Venkat Margapuri, Garik Kazanjian, Naren Kosaraju
https://arxiv.org/abs/2509.20105 https://…

PEPS: Quantum-Inspired Reinforcement Learning for Coherent Reasoning Traces in LLMs
Large Language Models (LLMs) often struggle with maintaining coherent multi-step reasoning traces, particularly in tasks that require a structured logical flow. This work introduces a quantum-inspired approach to address the challenge by incorporating a fidelity-based reward derived from Projected Entangled Pair States (PEPS) into Proximal Policy Optimization. Unlike prior approaches that use direct supervision or contrastive objectives, the proposed method guides learning through structural co…

Quantum Harmonic Analysis and the Structure in Data: Augmentation
Monika Doerfler, Franz Luef, Henry McNulty
https://arxiv.org/abs/2509.19474 https://arxiv…

Quantum Harmonic Analysis and the Structure in Data: Augmentation
In this short note, we study the impact of data augmentation on the smoothness of principal components of high-dimensional datasets. Using tools from quantum harmonic analysis, we show that eigenfunctions of operators corresponding to augmented data sets lie in the modulation space $M^1(\mathbb{R}^d)$, guaranteeing smoothness and continuity. Numerical examples on synthetic and audio data confirm the theoretical findings. While interesting in itself, the results suggest that manifold learning an…

CoMelSinger: Discrete Token-Based Zero-Shot Singing Synthesis With Structured Melody Control and Guidance
Junchuan Zhao, Wei Zeng, Tianle Lyu, Ye Wang
https://arxiv.org/abs/2509.19883

CoMelSinger: Discrete Token-Based Zero-Shot Singing Synthesis With Structured Melody Control and Guidance
Singing Voice Synthesis (SVS) aims to generate expressive vocal performances from structured musical inputs such as lyrics and pitch sequences. While recent progress in discrete codec-based speech synthesis has enabled zero-shot generation via in-context learning, directly extending these techniques to SVS remains non-trivial due to the requirement for precise melody control. In particular, prompt-based generation often introduces prosody leakage, where pitch information is inadvertently entang…

Week 8 NFL player props, picks, odds: Target Daniel Jones Over 233.5 passing yards for Sunday NFL prop bets

https://www.cbssports.com/nfl/news/week-8-

Non-Clairvoyant Scheduling with Progress Bars
Ziyad Benomar, Romain Cosson, Alexander Lindermayr, Jens Schl\"oter
https://arxiv.org/abs/2509.19662 https://

Non-Clairvoyant Scheduling with Progress Bars
In non-clairvoyant scheduling, the goal is to minimize the total job completion time without prior knowledge of individual job processing times. This classical online optimization problem has recently gained attention through the framework of learning-augmented algorithms. We introduce a natural setting in which the scheduler receives continuous feedback in the form of progress bars: estimates of the fraction of each job completed over time. We design new algorithms for both adversarial and sto…

Self-evolved Imitation Learning in Simulated World
Yifan Ye, Jun Cen, Jing Chen, Zhihe Lu
https://arxiv.org/abs/2509.19460 https://arxiv.org/pdf/2509.19460…

Self-evolved Imitation Learning in Simulated World
Imitation learning has been a trend recently, yet training a generalist agent across multiple tasks still requires large-scale expert demonstrations, which are costly and labor-intensive to collect. To address the challenge of limited supervision, we propose Self-Evolved Imitation Learning (SEIL), a framework that progressively improves a few-shot model through simulator interactions. The model first attempts tasksin the simulator, from which successful trajectories are collected as new demonst…

SMILES-Inspired Transfer Learning for Quantum Operators in Generative Quantum Eigensolver
Zhi Yin, Xiaoran Li, Shengyu Zhang, Xin Li, Xiaojin Zhang
https://arxiv.org/abs/2509.19715

SMILES-Inspired Transfer Learning for Quantum Operators in Generative Quantum Eigensolver
Given the inherent limitations of traditional Variational Quantum Eigensolver(VQE) algorithms, the integration of deep generative models into hybrid quantum-classical frameworks, specifically the Generative Quantum Eigensolver(GQE), represents a promising innovative approach. However, taking the Unitary Coupled Cluster with Singles and Doubles(UCCSD) ansatz which is widely used in quantum chemistry as an example, different molecular systems require constructions of distinct quantum operators. C…

I wrote up a talk I did recently: 'AI and Machine Learning in Libraries: Promising, But Not Ready Yet' https://www.openobjects.org.uk/2025/10/ai-and-machine-learning-in-libraries-promising-but-not-ready-yet

Towards Robust In-Context Learning for Medical Image Segmentation via Data Synthesis
Jiesi Hu, Yanwu Yang, Zhiyu Ye, Chenfei Ye, Hanyang Peng, Jianfeng Cao, Ting Ma
https://arxiv.org/abs/2509.19711

Towards Robust In-Context Learning for Medical Image Segmentation via Data Synthesis
The rise of In-Context Learning (ICL) for universal medical image segmentation has introduced an unprecedented demand for large-scale, diverse datasets for training, exacerbating the long-standing problem of data scarcity. While data synthesis offers a promising solution, existing methods often fail to simultaneously achieve both high data diversity and a domain distribution suitable for medical data. To bridge this gap, we propose \textbf{SynthICL}, a novel data synthesis framework built upon …

Embedding Domain Knowledge for Large Language Models via Reinforcement Learning from Augmented Generation
Chaojun Nie, Jun Zhou, Guanxiang Wang, Shisong Wud, Zichen Wang
https://arxiv.org/abs/2509.20162

Embedding Domain Knowledge for Large Language Models via Reinforcement Learning from Augmented Generation
Large language models (LLMs) often exhibit limited performance on domain-specific tasks due to the natural disproportionate representation of specialized information in their training data and the static nature of these datasets. Knowledge scarcity and temporal lag create knowledge gaps for domain applications. While post-training on domain datasets can embed knowledge into models, existing approaches have some limitations. Continual Pre-Training (CPT) treats all tokens in domain documents with…

Diffusion-Augmented Contrastive Learning: A Noise-Robust Encoder for Biosignal Representations
Rami Zewail
https://arxiv.org/abs/2509.20048 https://arxiv.o…

Diffusion-Augmented Contrastive Learning: A Noise-Robust Encoder for Biosignal Representations
Learning robust representations for biosignals is often hampered by the challenge of designing effective data augmentations.Traditional methods can fail to capture the complex variations inherent in physiological data. Within this context, we propose a novel hybrid framework, Diffusion-Augmented Contrastive Learning (DACL), that fuses concepts from diffusion models and supervised contrastive learning. The DACL framework operates on a latent space created by a lightweight Variational Autoencoder…

Multimodal-enhanced Federated Recommendation: A Group-wise Fusion Approach
Chunxu Zhang, Weipeng Zhang, Guodong Long, Zhiheng Xue, Riting Xia, Bo Yang
https://arxiv.org/abs/2509.19955

Multimodal-enhanced Federated Recommendation: A Group-wise Fusion Approach
Federated Recommendation (FR) is a new learning paradigm to tackle the learn-to-rank problem in a privacy-preservation manner. How to integrate multi-modality features into federated recommendation is still an open challenge in terms of efficiency, distribution heterogeneity, and fine-grained alignment. To address these challenges, we propose a novel multimodal fusion mechanism in federated recommendation settings (GFMFR). Specifically, it offloads multimodal representation learning to the serv…

Diffusion-Based Impedance Learning for Contact-Rich Manipulation Tasks
Noah Geiger, Tamim Asfour, Neville Hogan, Johannes Lachner
https://arxiv.org/abs/2509.19696 https://

Diffusion-Based Impedance Learning for Contact-Rich Manipulation Tasks
Learning methods excel at motion generation in the information domain but are not primarily designed for physical interaction in the energy domain. Impedance Control shapes physical interaction but requires task-aware tuning by selecting feasible impedance parameters. We present Diffusion-Based Impedance Learning, a framework that combines both domains. A Transformer-based Diffusion Model with cross-attention to external wrenches reconstructs a simulated Zero-Force Trajectory (sZFT). This captu…

A Statistical Mixture-of-Experts Framework for EMG Artifact Removal in EEG: Empirical Insights and a Proof-of-Concept Application
Benjamin J. Choi, Griffin Milsap, Clara A. Scholl, Francesco Tenore, Mattson Ogg
https://arxiv.org/abs/2509.19385

A Statistical Mixture-of-Experts Framework for EMG Artifact Removal in EEG: Empirical Insights and a Proof-of-Concept Application
Effective control of neural interfaces is limited by poor signal quality. While neural network-based electroencephalography (EEG) denoising methods for electromyogenic (EMG) artifacts have improved in recent years, current state-of-the-art (SOTA) models perform suboptimally in settings with high noise. To address the shortcomings of current machine learning (ML)-based denoising algorithms, we present a signal filtration algorithm driven by a new mixture-of-experts (MoE) framework. Our algorithm…

Evaluation-Aware Reinforcement Learning
Shripad Vilasrao Deshmukh, Will Schwarzer, Scott Niekum
https://arxiv.org/abs/2509.19464 https://arxiv.org/pdf/2509…

Evaluation-Aware Reinforcement Learning
Policy evaluation is often a prerequisite for deploying safety- and performance-critical systems. Existing evaluation approaches frequently suffer from high variance due to limited data and long-horizon tasks, or high bias due to unequal support or inaccurate environmental models. We posit that these challenges arise, in part, from the standard reinforcement learning (RL) paradigm of policy learning without explicit consideration of evaluation. As an alternative, we propose evaluation-aware rei…

PerFace: Metric Learning in Perceptual Facial Similarity for Enhanced Face Anonymization
Haruka Kumagai, Leslie W\"ohler, Satoshi Ikehata, Kiyoharu Aizawa
https://arxiv.org/abs/2509.20281

PerFace: Metric Learning in Perceptual Facial Similarity for Enhanced Face Anonymization
In response to rising societal awareness of privacy concerns, face anonymization techniques have advanced, including the emergence of face-swapping methods that replace one identity with another. Achieving a balance between anonymity and naturalness in face swapping requires careful selection of identities: overly similar faces compromise anonymity, while dissimilar ones reduce naturalness. Existing models, however, focus on binary identity classification "the same person or not", making it dif…

Multi-population Ensemble Genetic Programming via Cooperative Coevolution and Multi-view Learning for Classification
Mohammad Sadegh Khorshidi, Navid Yazdanjue, Hassan Gharoun, Mohammad Reza Nikoo, Fang Chen, Amir H. Gandomi
https://arxiv.org/abs/2509.19339

Multi-population Ensemble Genetic Programming via Cooperative Coevolution and Multi-view Learning for Classification
This paper introduces Multi-population Ensemble Genetic Programming (MEGP), a computational intelligence framework that integrates cooperative coevolution and the multiview learning paradigm to address classification challenges in high-dimensional and heterogeneous feature spaces. MEGP decomposes the input space into conditionally independent feature subsets, enabling multiple subpopulations to evolve in parallel while interacting through a dynamic ensemble-based fitness mechanism. Each individ…

Chiseling: Powerful and Valid Subgroup Selection via Interactive Machine Learning
Nathan Cheng, Asher Spector, Lucas Janson
https://arxiv.org/abs/2509.19490 https://

Chiseling: Powerful and Valid Subgroup Selection via Interactive Machine Learning
In regression and causal inference, controlled subgroup selection aims to identify, with inferential guarantees, a subgroup (defined as a subset of the covariate space) on which the average response or treatment effect is above a given threshold. E.g., in a clinical trial, it may be of interest to find a subgroup with a positive average treatment effect. However, existing methods either lack inferential guarantees, heavily restrict the search for the subgroup, or sacrifice efficiency by naive d…

Geometric Autoencoder Priors for Bayesian Inversion: Learn First Observe Later
Arnaud Vadeboncoeur, Gregory Duth\'e, Mark Girolami, Eleni Chatzi
https://arxiv.org/abs/2509.19929

Geometric Autoencoder Priors for Bayesian Inversion: Learn First Observe Later
Uncertainty Quantification (UQ) is paramount for inference in engineering applications. A common inference task is to recover full-field information of physical systems from a small number of noisy observations, a usually highly ill-posed problem. Critically, engineering systems often have complicated and variable geometries prohibiting the use of standard Bayesian UQ. In this work, we introduce Geometric Autoencoders for Bayesian Inversion (GABI), a framework for learning geometry-aware genera…

A Survey of Recent Advancements in Secure Peer-to-Peer Networks
Raj Patel, Umesh Biswas, Surya Kodipaka, Will Carroll, Preston Peranich, Maxwell Young
https://arxiv.org/abs/2509.19539

A Survey of Recent Advancements in Secure Peer-to-Peer Networks
Peer-to-peer (P2P) networks are a cornerstone of modern computing, and their security is an active area of research. Many defenses with strong security guarantees have been proposed; however, the most-recent survey is over a decade old. This paper delivers an updated review of recent theoretical advances that address classic threats, such as the Sybil and routing attacks, while highlighting how emerging trends -- such as machine learning, social networks, and dynamic systems -- pose new challen…

Dynamic Lagging for Time-Series Forecasting in E-Commerce Finance: Mitigating Information Loss with A Hybrid ML Architecture
Abhishek Sharma, Anat Parush, Sumit Wadhwa, Amihai Savir, Anne Guinard, Prateek Srivastava
https://arxiv.org/abs/2509.20244

Dynamic Lagging for Time-Series Forecasting in E-Commerce Finance: Mitigating Information Loss with A Hybrid ML Architecture
Accurate forecasting in the e-commerce finance domain is particularly challenging due to irregular invoice schedules, payment deferrals, and user-specific behavioral variability. These factors, combined with sparse datasets and short historical windows, limit the effectiveness of conventional time-series methods. While deep learning and Transformer-based models have shown promise in other domains, their performance deteriorates under partial observability and limited historical data. To address…

mindmap: Spatial Memory in Deep Feature Maps for 3D Action Policies
Remo Steiner, Alexander Millane, David Tingdahl, Clemens Volk, Vikram Ramasamy, Xinjie Yao, Peter Du, Soha Pouya, Shiwei Sheng
https://arxiv.org/abs/2509.20297

mindmap: Spatial Memory in Deep Feature Maps for 3D Action Policies
End-to-end learning of robot control policies, structured as neural networks, has emerged as a promising approach to robotic manipulation. To complete many common tasks, relevant objects are required to pass in and out of a robot's field of view. In these settings, spatial memory - the ability to remember the spatial composition of the scene - is an important competency. However, building such mechanisms into robot learning systems remains an open research problem. We introduce mindmap (Spatial…

From Pheromones to Policies: Reinforcement Learning for Engineered Biological Swarms
Aymeric Vellinger, Nemanja Antonic, Elio Tuci
https://arxiv.org/abs/2509.20095 https://

From Pheromones to Policies: Reinforcement Learning for Engineered Biological Swarms
Swarm intelligence emerges from decentralised interactions among simple agents, enabling collective problem-solving. This study establishes a theoretical equivalence between pheromone-mediated aggregation in \celeg\ and reinforcement learning (RL), demonstrating how stigmergic signals function as distributed reward mechanisms. We model engineered nematode swarms performing foraging tasks, showing that pheromone dynamics mathematically mirror cross-learning updates, a fundamental RL algorithm. E…

EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning
Xuan Ju, Tianyu Wang, Yuqian Zhou, He Zhang, Qing Liu, Nanxuan Zhao, Zhifei Zhang, Yijun Li, Yuanhao Cai, Shaoteng Liu, Daniil Pakhomov, Zhe Lin, Soo Ye Kim, Qiang Xu
https://arxiv.org/abs/2509.20360

EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning
Recent advances in foundation models highlight a clear trend toward unification and scaling, showing emergent capabilities across diverse domains. While image generation and editing have rapidly transitioned from task-specific to unified frameworks, video generation and editing remain fragmented due to architectural limitations and data scarcity. In this work, we introduce EditVerse, a unified framework for image and video generation and editing within a single model. By representing all modali…

Incomplete Data, Complete Dynamics: A Diffusion Approach
Zihan Zhou, Chenguang Wang, Hongyi Ye, Yongtao Guan, Tianshu Yu
https://arxiv.org/abs/2509.20098 https://

Incomplete Data, Complete Dynamics: A Diffusion Approach
Learning physical dynamics from data is a fundamental challenge in machine learning and scientific modeling. Real-world observational data are inherently incomplete and irregularly sampled, posing significant challenges for existing data-driven approaches. In this work, we propose a principled diffusion-based framework for learning physical systems from incomplete training samples. To this end, our method strategically partitions each such sample into observed context and unobserved query compo…

Short-Term Regional Electricity Demand Forecasting in Argentina Using LSTM Networks
Oscar A. Oviedo
https://arxiv.org/abs/2509.19374 https://arxiv.org/pdf/…

Short-Term Regional Electricity Demand Forecasting in Argentina Using LSTM Networks
This study presents the development and optimization of a deep learning model based on Long Short-Term Memory (LSTM) networks to predict short-term hourly electricity demand in Córdoba, Argentina. Integrating historical consumption data with exogenous variables (climatic factors, temporal cycles, and demographic statistics), the model achieved high predictive precision, with a mean absolute percentage error of 3.20\% and a determination coefficient of 0.95. The inclusion of periodic temporal e…

Table Detection with Active Learning
Somraj Gautam, Nachiketa Purohit, Gaurav Harit
https://arxiv.org/abs/2509.20003 https://arxiv.org/pdf/2509.20003

Table Detection with Active Learning
Efficient data annotation remains a critical challenge in machine learning, particularly for object detection tasks requiring extensive labeled data. Active learning (AL) has emerged as a promising solution to minimize annotation costs by selecting the most informative samples. While traditional AL approaches primarily rely on uncertainty-based selection, recent advances suggest that incorporating diversity-based strategies can enhance sampling efficiency in object detection tasks. Our approach…

Hierarchical Bayesian Operator-induced Symbolic Regression Trees for Structural Learning of Scientific Expressions
Somjit Roy, Pritam Dey, Debdeep Pati, Bani K. Mallick
https://arxiv.org/abs/2509.19710

Hierarchical Bayesian Operator-induced Symbolic Regression Trees for Structural Learning of Scientific Expressions
The advent of Scientific Machine Learning has heralded a transformative era in scientific discovery, driving progress across diverse domains. Central to this progress is uncovering scientific laws from experimental data through symbolic regression. However, existing approaches are dominated by heuristic algorithms or data-hungry black-box methods, which often demand low-noise settings and lack principled uncertainty quantification. Motivated by interpretable Statistical Artificial Intelligence,…

Language Models that Think, Chat Better
Adithya Bhaskar, Xi Ye, Danqi Chen
https://arxiv.org/abs/2509.20357 https://arxiv.org/pdf/2509.20357

Language Models that Think, Chat Better
Reinforcement learning with verifiable rewards (RLVR) improves language model reasoning by using rule-based rewards in verifiable domains such as mathematics and code. However, RLVR leads to limited generalization for open-ended tasks -- such as writing outline essays or making meal plans -- where humans reason routinely. This paper shows that the RLVR paradigm is effective beyond verifiable domains, and introduces **RL** with **M**odel-rewarded **T**hinking (**RLMT**) for general-purpose chat …

Learning Contextual Retrieval for Robust Conversational Search
Seunghan Yang, Juntae Lee, Jihwan Bang, Kyuhong Shim, Minsoo Kim, Simyung Chang
https://arxiv.org/abs/2509.19700 h…

Learning Contextual Retrieval for Robust Conversational Search
Effective conversational search demands a deep understanding of user intent across multiple dialogue turns. Users frequently use abbreviations and shift topics in the middle of conversations, posing challenges for conventional retrievers. While query rewriting techniques improve clarity, they often incur significant computational cost due to additional autoregressive steps. Moreover, although LLM-based retrievers demonstrate strong performance, they are not explicitly optimized to track user in…

TopoCut: Learning Multi-Step Cutting with Spectral Rewards and Discrete Diffusion Policies
Liquan Wang, Jiangjie Bian, Eric Heiden, Animesh Garg
https://arxiv.org/abs/2509.19712

TopoCut: Learning Multi-Step Cutting with Spectral Rewards and Discrete Diffusion Policies
Robotic manipulation tasks involving cutting deformable objects remain challenging due to complex topological behaviors, difficulties in perceiving dense object states, and the lack of efficient evaluation methods for cutting outcomes. In this paper, we introduce TopoCut, a comprehensive benchmark for multi-step robotic cutting tasks that integrates a cutting environment and generalized policy learning. TopoCut is built upon three core components: (1) We introduce a high-fidelity simulation env…

Adaptive Model Ensemble for Continual Learning
Yuchuan Mao, Zhi Gao, Xiaomeng Fan, Yuwei Wu, Yunde Jia, Chenchen Jing
https://arxiv.org/abs/2509.19819 https://

Adaptive Model Ensemble for Continual Learning
Model ensemble is an effective strategy in continual learning, which alleviates catastrophic forgetting by interpolating model parameters, achieving knowledge fusion learned from different tasks. However, existing model ensemble methods usually encounter the knowledge conflict issue at task and layer levels, causing compromised learning performance in both old and new tasks. To solve this issue, we propose meta-weight-ensembler that adaptively fuses knowledge of different tasks for continual le…

Process-Informed Forecasting of Complex Thermal Dynamics in Pharmaceutical Manufacturing
Ramona Rubini, Siavash Khodakarami, Aniruddha Bora, George Em Karniadakis, Michele Dassisti
https://arxiv.org/abs/2509.20349

Process-Informed Forecasting of Complex Thermal Dynamics in Pharmaceutical Manufacturing
Accurate time-series forecasting for complex physical systems is the backbone of modern industrial monitoring and control. While deep learning models excel at capturing complex dynamics, currently, their deployment is limited due to physical inconsistency and robustness, hence constraining their reliability in regulated environments. We introduce process-informed forecasting (PIF) models for temperature in pharmaceutical lyophilization. We investigate a wide range of models, from classical ones…

SpellerSSL: Self-Supervised Learning with P300 Aggregation for Speller BCIs
Jiazhen Hong, Geoff Mackellar, Soheila Ghane
https://arxiv.org/abs/2509.19401 https://

SpellerSSL: Self-Supervised Learning with P300 Aggregation for Speller BCIs
Electroencephalogram (EEG)-based P300 speller brain-computer interfaces (BCIs) face three main challenges: low signal-to-noise ratio (SNR), poor generalization, and time-consuming calibration. We propose SpellerSSL, a framework that combines self-supervised learning (SSL) with P300 aggregation to address these issues. First, we introduce an aggregation strategy to enhance SNR. Second, to achieve generalization in training, we employ a customized 1D U-Net backbone and pretrain the model on both …

Overview of LifeCLEF Plant Identification task 2020
Herve Goeau, Pierre Bonnet, Alexis Joly
https://arxiv.org/abs/2509.19402 https://arxiv.org/pdf/2509.194…

Overview of LifeCLEF Plant Identification task 2020
Automated identification of plants has improved considerably thanks to the recent progress in deep learning and the availability of training data with more and more photos in the field. However, this profusion of data only concerns a few tens of thousands of species, mostly located in North America and Western Europe, much less in the richest regions in terms of biodiversity such as tropical countries. On the other hand, for several centuries, botanists have collected, catalogued and systematic…

Low-Resource English-Tigrinya MT: Leveraging Multilingual Models, Custom Tokenizers, and Clean Evaluation Benchmarks
Hailay Kidu Teklehaymanot, Gebrearegawi Gidey, Wolfgang Nejdl
https://arxiv.org/abs/2509.20209

Low-Resource English-Tigrinya MT: Leveraging Multilingual Models, Custom Tokenizers, and Clean Evaluation Benchmarks
Despite advances in Neural Machine Translation (NMT), low-resource languages like Tigrinya remain underserved due to persistent challenges, including limited corpora, inadequate tokenization strategies, and the lack of standardized evaluation benchmarks. This paper investigates transfer learning techniques using multilingual pretrained models to enhance translation quality for morphologically rich, low-resource languages. We propose a refined approach that integrates language-specific tokenizat…

Extended Low-Rank Approximation Accelerates Learning of Elastic Response in Heterogeneous Materials
Prabhat Karmakar, Sayan Gupta, Ilaksh Adlakha
https://arxiv.org/abs/2509.20276

Extended Low-Rank Approximation Accelerates Learning of Elastic Response in Heterogeneous Materials
Predicting how the microstructure governs the mechanical response of heterogeneous materials is essential for optimizing design and performance. Yet this task remains difficult due to the complex, high dimensional nature of microstructural features. Relying on physics based simulations to probe the microstructural space is computationally prohibitive. This motivates the development of computational tools to efficiently learn structure property linkages governing mechanical behavior. While conte…

Parse-Augment-Distill: Learning Generalizable Bimanual Visuomotor Policies from Single Human Video
Georgios Tziafas, Jiayun Zhang, Hamidreza Kasaei
https://arxiv.org/abs/2509.20286

Parse-Augment-Distill: Learning Generalizable Bimanual Visuomotor Policies from Single Human Video
Learning visuomotor policies from expert demonstrations is an important frontier in modern robotics research, however, most popular methods require copious efforts for collecting teleoperation data and struggle to generalize out-ofdistribution. Scaling data collection has been explored through leveraging human videos, as well as demonstration augmentation techniques. The latter approach typically requires expensive simulation rollouts and trains policies with synthetic image data, therefore int…

A decision-theoretic framework for uncertainty quantification in epidemiological modelling
Nicholas Steyn, Freddie Bickford Smith, Cathal Mills, Vik Shirvaikar, Christl A Donnelly, Kris V Parag
https://arxiv.org/abs/2509.20013

A decision-theoretic framework for uncertainty quantification in epidemiological modelling
Estimating, understanding, and communicating uncertainty is fundamental to statistical epidemiology, where model-based estimates regularly inform real-world decisions. However, sources of uncertainty are rarely formalised, and existing classifications are often defined inconsistently. This lack of structure hampers interpretation, model comparison, and targeted data collection. Connecting ideas from machine learning, information theory, experimental design, and health economics, we present a fi…

Learning to Stop: Reinforcement Learning for Efficient Patient-Level Echocardiographic Classification
Woo-Jin Cho Kim, Jorge Oliveira, Arian Beqiri, Alex Thorley, Jordan Strom, Jamie O'Driscoll, Rajan Sharma, Jeremy Slivnick, Roberto Lang, Alberto Gomez, Agisilaos Chartsias
https://arxiv.org/abs/2509.19694

Learning to Stop: Reinforcement Learning for Efficient Patient-Level Echocardiographic Classification
Guidelines for transthoracic echocardiographic examination recommend the acquisition of multiple video clips from different views of the heart, resulting in a large number of clips. Typically, automated methods, for instance disease classifiers, either use one clip or average predictions from all clips. Relying on one clip ignores complementary information available from other clips, while using all clips is computationally expensive and may be prohibitive for clinical adoption. To select the…

Learning Robust Penetration-Testing Policies under Partial Observability: A systematic evaluation
Raphael Simon, Pieter Libin, Wim Mees
https://arxiv.org/abs/2509.20008 https://…

Learning Robust Penetration-Testing Policies under Partial Observability: A systematic evaluation
Penetration testing, the simulation of cyberattacks to identify security vulnerabilities, presents a sequential decision-making problem well-suited for reinforcement learning (RL) automation. Like many applications of RL to real-world problems, partial observability presents a major challenge, as it invalidates the Markov property present in Markov Decision Processes (MDPs). Partially Observable MDPs require history aggregation or belief state estimation to learn successful policies. We investi…

Score the Steps, Not Just the Goal: VLM-Based Subgoal Evaluation for Robotic Manipulation
Ramy ElMallah, Krish Chhajer, Chi-Guhn Lee
https://arxiv.org/abs/2509.19524 https://

Score the Steps, Not Just the Goal: VLM-Based Subgoal Evaluation for Robotic Manipulation
Robot learning papers typically report a single binary success rate (SR), which obscures where a policy succeeds or fails along a multi-step manipulation task. We argue that subgoal-level reporting should become routine: for each trajectory, a vector of per-subgoal SRs that makes partial competence visible (e.g., grasp vs. pour). We propose a blueprint for StepEval, a cost-aware plug-in evaluation framework that utilizes vision-language models (VLMs) as automated judges of subgoal outcomes from…

Vision-Based Perception for Autonomous Vehicles in Off-Road Environment Using Deep Learning
Nelson Alves Ferreira Neto
https://arxiv.org/abs/2509.19378 https://

Vision-Based Perception for Autonomous Vehicles in Off-Road Environment Using Deep Learning
Low-latency intelligent systems are required for autonomous driving on non-uniform terrain in open-pit mines and developing countries. This work proposes a perception system for autonomous vehicles on unpaved roads and off-road environments, capable of navigating rough terrain without a predefined trail. The Configurable Modular Segmentation Network (CMSNet) framework is proposed, facilitating different architectural arrangements. CMSNet configurations were trained to segment obstacles and traf…

Beyond Human Demonstrations: Diffusion-Based Reinforcement Learning to Generate Data for VLA Training
Rushuai Yang, Hangxing Wei, Ran Zhang, Zhiyuan Feng, Xiaoyu Chen, Tong Li, Chuheng Zhang, Li Zhao, Jiang Bian, Xiu Su, Yi Chen
https://arxiv.org/abs/2509.19752

Beyond Human Demonstrations: Diffusion-Based Reinforcement Learning to Generate Data for VLA Training
Vision-language-action (VLA) models have shown strong generalization across tasks and embodiments; however, their reliance on large-scale human demonstrations limits their scalability owing to the cost and effort of manual data collection. Reinforcement learning (RL) offers a potential alternative to generate demonstrations autonomously, yet conventional RL algorithms often struggle on long-horizon manipulation tasks with sparse rewards. In this paper, we propose a modified diffusion policy opt…

Self-Alignment Learning to Improve Myocardial Infarction Detection from Single-Lead ECG
Jiarui Jin, Xiaocheng Fang, Haoyu Wang, Jun Li, Che Liu, Donglin Xie, Hongyan Li, Shenda Hong
https://arxiv.org/abs/2509.19397

Self-Alignment Learning to Improve Myocardial Infarction Detection from Single-Lead ECG
Myocardial infarction is a critical manifestation of coronary artery disease, yet detecting it from single-lead electrocardiogram (ECG) remains challenging due to limited spatial information. An intuitive idea is to convert single-lead into multiple-lead ECG for classification by pre-trained models, but generative methods optimized at the signal level in most cases leave a large latent space gap, ultimately degrading diagnostic performance. This naturally raises the question of whether latent s…

PGCLODA: Prompt-Guided Graph Contrastive Learning for Oligopeptide-Infectious Disease Association Prediction
Dayu Tan, Jing Chen, Xiaoping Zhou, Yansen Su, Chunhou Zheng
https://arxiv.org/abs/2509.20290

PGCLODA: Prompt-Guided Graph Contrastive Learning for Oligopeptide-Infectious Disease Association Prediction
Infectious diseases continue to pose a serious threat to public health, underscoring the urgent need for effective computational approaches to screen novel anti-infective agents. Oligopeptides have emerged as promising candidates in antimicrobial research due to their structural simplicity, high bioavailability, and low susceptibility to resistance. Despite their potential, computational models specifically designed to predict associations between oligopeptides and infectious diseases remain sc…

nnFilterMatch: A Unified Semi-Supervised Learning Framework with Uncertainty-Aware Pseudo-Label Filtering for Efficient Medical Segmentation
Yi Yang
https://arxiv.org/abs/2509.19746

nnFilterMatch: A Unified Semi-Supervised Learning Framework with Uncertainty-Aware Pseudo-Label Filtering for Efficient Medical Segmentation
Semi-supervised learning (SSL) has emerged as a promising paradigm in medical image segmentation, offering competitive performance while substantially reducing the need for extensive manual annotation. When combined with active learning (AL), these strategies further minimize annotation burden by selectively incorporating the most informative samples. However, conventional SSL_AL hybrid approaches often rely on iterative and loop-based retraining cycles after each annotation round, incurring si…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[2/6]:
- Pretrained deep models outperform GBDTs in Learning-To-Rank under label scarcity
Hou, Thekumparampil, Shavlovsky, Fanti, Dattatreya, Sanghavi

D3Grasp: Diverse and Deformable Dexterous Grasping for General Objects
Keyu Wang, Bingcong Lu, Zhengxue Cheng, Hengdi Zhang, Li Song
https://arxiv.org/abs/2509.19892 https://

D3Grasp: Diverse and Deformable Dexterous Grasping for General Objects
Achieving diverse and stable dexterous grasping for general and deformable objects remains a fundamental challenge in robotics, due to high-dimensional action spaces and uncertainty in perception. In this paper, we present D3Grasp, a multimodal perception-guided reinforcement learning framework designed to enable Diverse and Deformable Dexterous Grasping. We firstly introduce a unified multimodal representation that integrates visual and tactile perception to robustly grasp common objects with …

Spatio-Temporal Directed Graph Learning for Account Takeover Fraud Detection
Mohsen Nayebi Kerdabadi, William Andrew Byron, Xin Sun, Amirfarrokh Iranitalab
https://arxiv.org/abs/2509.20339

Spatio-Temporal Directed Graph Learning for Account Takeover Fraud Detection
Account Takeover (ATO) fraud poses a significant challenge in consumer banking, requiring high recall under strict latency while minimizing friction for legitimate users. Production systems typically rely on tabular gradient-boosted decision trees (e.g., XGBoost) that score sessions independently, overlooking the relational and temporal structure of online activity that characterizes coordinated attacks and "fraud rings." We introduce ATLAS (Account Takeover Learning Across Spatio-Temporal Dire…

Parameter-Efficient Multi-Task Learning via Progressive Task-Specific Adaptation
Neeraj Gangwar, Anshuka Rangi, Rishabh Deshmukh, Holakou Rahmanian, Yesh Dattatreya, Nickvash Kani
https://arxiv.org/abs/2509.19602

Parameter-Efficient Multi-Task Learning via Progressive Task-Specific Adaptation
Parameter-efficient fine-tuning methods have emerged as a promising solution for adapting pre-trained models to various downstream tasks. While these methods perform well in single-task learning, extending them to multi-task learning exacerbates common challenges, such as task interference and negative transfer, due to the limited number of trainable parameters. To address these issues, we introduce progressive task-specific multi-task adaptation, a novel parameter-efficient approach for multi-…

You Only Measure Once: On Designing Single-Shot Quantum Machine Learning Models
Chen-Yu Liu, Leonardo Placidi, Kuan-Cheng Chen, Samuel Yen-Chi Chen, Gabriel Matos
https://arxiv.org/abs/2509.20090

You Only Measure Once: On Designing Single-Shot Quantum Machine Learning Models
Quantum machine learning (QML) models conventionally rely on repeated measurements (shots) of observables to obtain reliable predictions. This dependence on large shot budgets leads to high inference cost and time overhead, which is particularly problematic as quantum hardware access is typically priced proportionally to the number of shots. In this work we propose You Only Measure Once (Yomo), a simple yet effective design that achieves accurate inference with dramatically fewer measurements, …

MoTiC: Momentum Tightness and Contrast for Few-Shot Class-Incremental Learning
Zeyu He, Shuai Huang, Yuwu Lu, Ming Zhao
https://arxiv.org/abs/2509.19664 https://

MoTiC: Momentum Tightness and Contrast for Few-Shot Class-Incremental Learning
Few-Shot Class-Incremental Learning (FSCIL) must contend with the dual challenge of learning new classes from scarce samples while preserving old class knowledge. Existing methods use the frozen feature extractor and class-averaged prototypes to mitigate against catastrophic forgetting and overfitting. However, new-class prototypes suffer significant estimation bias due to extreme data scarcity, whereas base-class prototypes benefit from sufficient data. In this work, we theoretically demonstra…

Analysis of approximate linear programming solution to Markov decision problem with log barrier function
Donghwan Lee, Hyukjun Yang, Bum Geun Park
https://arxiv.org/abs/2509.19800

Analysis of approximate linear programming solution to Markov decision problem with log barrier function
There are two primary approaches to solving Markov decision problems (MDPs): dynamic programming based on the Bellman equation and linear programming (LP). Dynamic programming methods are the most widely used and form the foundation of both classical and modern reinforcement learning (RL). By contrast, LP-based methods have been less commonly employed, although they have recently gained attention in contexts such as offline RL. The relative underuse of the LP-based methods stems from the fact t…

U-Mamba2-SSL for Semi-Supervised Tooth and Pulp Segmentation in CBCT
Zhi Qin Tan, Xiatian Zhu, Owen Addison, Yunpeng Li
https://arxiv.org/abs/2509.20154 https://

U-Mamba2-SSL for Semi-Supervised Tooth and Pulp Segmentation in CBCT
Accurate segmentation of teeth and pulp in Cone-Beam Computed Tomography (CBCT) is vital for clinical applications like treatment planning and diagnosis. However, this process requires extensive expertise and is exceptionally time-consuming, highlighting the critical need for automated algorithms that can effectively utilize unlabeled data. In this paper, we propose U-Mamba2-SSL, a novel semi-supervised learning framework that builds on the U-Mamba2 model and employs a multi-stage training stra…

Failure Modes of Maximum Entropy RLHF
\"Omer Veysel \c{C}a\u{g}atan, Bar{\i}\c{s} Akg\"un
https://arxiv.org/abs/2509.20265 https://arxiv.org/pdf/…

Failure Modes of Maximum Entropy RLHF
In this paper, we show that Simple Preference Optimization (SimPO) can be derived as Maximum Entropy Reinforcement Learning with length-normalized temperature, providing a theoretical foundation for this reference-free method. Motivated by SimPO's strong performance in offline preference optimization, we investigate whether Maximum Entropy RL can achieve similar results in online RLHF settings. Our experiments find that Maximum Entropy RL consistently exhibits overoptimization and unstable KL d…

Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving
Pengxiang Li, Yinan Zheng, Yue Wang, Huimin Wang, Hang Zhao, Jingjing Liu, Xianyuan Zhan, Kun Zhan, Xianpeng Lang
https://arxiv.org/abs/2509.20109

Discrete Diffusion for Reflective Vision-Language-Action Models in Autonomous Driving
End-to-End (E2E) solutions have emerged as a mainstream approach for autonomous driving systems, with Vision-Language-Action (VLA) models representing a new paradigm that leverages pre-trained multimodal knowledge from Vision-Language Models (VLMs) to interpret and interact with complex real-world environments. However, these methods remain constrained by the limitations of imitation learning, which struggles to inherently encode physical rules during training. Existing approaches often rely on…

An Anisotropic Cross-View Texture Transfer with Multi-Reference Non-Local Attention for CT Slice Interpolation
Kwang-Hyun Uhm, Hyunjun Cho, Sung-Hoo Hong, Seung-Won Jung
https://arxiv.org/abs/2509.20242

An Anisotropic Cross-View Texture Transfer with Multi-Reference Non-Local Attention for CT Slice Interpolation
Computed tomography (CT) is one of the most widely used non-invasive imaging modalities for medical diagnosis. In clinical practice, CT images are usually acquired with large slice thicknesses due to the high cost of memory storage and operation time, resulting in an anisotropic CT volume with much lower inter-slice resolution than in-plane resolution. Since such inconsistent resolution may lead to difficulties in disease diagnosis, deep learning-based volumetric super-resolution methods have b…

VIMD: Monocular Visual-Inertial Motion and Depth Estimation
Saimouli Katragadda, Guoquan Huang
https://arxiv.org/abs/2509.19713 https://arxiv.org/pdf/2509.…

VIMD: Monocular Visual-Inertial Motion and Depth Estimation
Accurate and efficient dense metric depth estimation is crucial for 3D visual perception in robotics and XR. In this paper, we develop a monocular visual-inertial motion and depth (VIMD) learning framework to estimate dense metric depth by leveraging accurate and efficient MSCKF-based monocular visual-inertial motion tracking. At the core the proposed VIMD is to exploit multi-view information to iteratively refine per-pixel scale, instead of globally fitting an invariant affine model as in the …

SHMoAReg: Spark Deformable Image Registration via Spatial Heterogeneous Mixture of Experts and Attention Heads
Yuxi Zheng, Jianhui Feng, Tianran Li, Marius Staring, Yuchuan Qiao
https://arxiv.org/abs/2509.20073

SHMoAReg: Spark Deformable Image Registration via Spatial Heterogeneous Mixture of Experts and Attention Heads
Encoder-Decoder architectures are widely used in deep learning-based Deformable Image Registration (DIR), where the encoder extracts multi-scale features and the decoder predicts deformation fields by recovering spatial locations. However, current methods lack specialized extraction of features (that are useful for registration) and predict deformation jointly and homogeneously in all three directions. In this paper, we propose a novel expert-guided DIR network with Mixture of Experts (MoE) mec…

EgoBridge: Domain Adaptation for Generalizable Imitation from Egocentric Human Data
Ryan Punamiya, Dhruv Patel, Patcharapong Aphiwetsa, Pranav Kuppili, Lawrence Y. Zhu, Simar Kareer, Judy Hoffman, Danfei Xu
https://arxiv.org/abs/2509.19626

EgoBridge: Domain Adaptation for Generalizable Imitation from Egocentric Human Data
Egocentric human experience data presents a vast resource for scaling up end-to-end imitation learning for robotic manipulation. However, significant domain gaps in visual appearance, sensor modalities, and kinematics between human and robot impede knowledge transfer. This paper presents EgoBridge, a unified co-training framework that explicitly aligns the policy latent spaces between human and robot data using domain adaptation. Through a measure of discrepancy on the joint policy latent featu…

Crosslisted article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[2/5]:
- A Statistical Mixture-of-Experts Framework for EMG Artifact Removal in EEG: Empirical Insights an...
Benjamin J. Choi, Griffin Milsap, Clara A. Scholl, Francesco Tenore, Mattson Ogg

Crosslisted article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[3/5]:
- MAGIC: Multi-task Gaussian process for joint imputation and classification in healthcare time series
Dohyun Ku, Catherine D. Chong, Visar Berisha, Todd J. Schwedt, Jing Li

ROPA: Synthetic Robot Pose Generation for RGB-D Bimanual Data Augmentation
Jason Chen, I-Chun Arthur Liu, Gaurav Sukhatme, Daniel Seita
https://arxiv.org/abs/2509.19454 https://…

ROPA: Synthetic Robot Pose Generation for RGB-D Bimanual Data Augmentation
Training robust bimanual manipulation policies via imitation learning requires demonstration data with broad coverage over robot poses, contacts, and scene contexts. However, collecting diverse and precise real-world demonstrations is costly and time-consuming, which hinders scalability. Prior works have addressed this with data augmentation, typically for either eye-in-hand (wrist camera) setups with RGB inputs or for generating novel images without paired actions, leaving augmentation for eye…

ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression
Tom Burgert, Oliver Stoll, Paolo Rota, Beg\"um Demir
https://arxiv.org/abs/2509.20234

ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression
The hypothesis that Convolutional Neural Networks (CNNs) are inherently texture-biased has shaped much of the discourse on feature use in deep learning. We revisit this hypothesis by examining limitations in the cue-conflict experiment by Geirhos et al. To address these limitations, we propose a domain-agnostic framework that quantifies feature reliance through systematic suppression of shape, texture, and color cues, avoiding the confounds of forced-choice conflicts. By evaluating humans and n…

Faster Than SVD, Smarter Than SGD: The OPLoRA Alternating Update
Abdulla Jasem Almansoori, Maria Ivanova, Andrey Veprikov, Aleksandr Beznosikov, Samuel Horv\'ath, Martin Tak\'a\v{c}
https://arxiv.org/abs/2509.19977

Faster Than SVD, Smarter Than SGD: The OPLoRA Alternating Update
Low-Rank Adaptation (LoRA) fine-tunes large models by learning low-rank updates on top of frozen weights, dramatically reducing trainable parameters and memory. However, there is still a gap between full training with low-rank projections (SVDLoRA) and LoRA fine-tuning, indicating that LoRA steps can be further improved. In this study, we propose OPLoRA, a memory-efficient optimizer that closes this gap by casting LoRA optimization as an interpretable sub-problem and solving it efficiently with…

Time-adaptive H\'enonNets for separable Hamiltonian systems
Konrad Janik, Peter Benner
https://arxiv.org/abs/2509.20212 https://arxiv.org/pdf/2509.2021…

Time-adaptive HénonNets for separable Hamiltonian systems
Measurement data is often sampled irregularly, i.e., not on equidistant time grids. This is also true for Hamiltonian systems. However, existing machine learning methods, which learn symplectic integrators, such as SympNets [1] and HénonNets [2] still require training data generated by fixed step sizes. To learn time-adaptive symplectic integrators, an extension to SympNets called TSympNets is introduced in [3]. The aim of this work is to do a similar extension for HénonNets. We propose a nov…

Hyperspectral Adapter for Semantic Segmentation with Vision Foundation Models
JuanaJuana Valeria Hurtado, Rohit Mohan, Abhinav Valada
https://arxiv.org/abs/2509.20107 https://…

Hyperspectral Adapter for Semantic Segmentation with Vision Foundation Models
Hyperspectral imaging (HSI) captures spatial information along with dense spectral measurements across numerous narrow wavelength bands. This rich spectral content has the potential to facilitate robust robotic perception, particularly in environments with complex material compositions, varying illumination, or other visually challenging conditions. However, current HSI semantic segmentation methods underperform due to their reliance on architectures and learning frameworks optimized for RGB in…

Robust RGB-T Tracking via Learnable Visual Fourier Prompt Fine-tuning and Modality Fusion Prompt Generation
Hongtao Yang, Bineng Zhong, Qihua Liang, Zhiruo Zhu, Yaozong Zheng, Ning Li
https://arxiv.org/abs/2509.19733

Robust RGB-T Tracking via Learnable Visual Fourier Prompt Fine-tuning and Modality Fusion Prompt Generation
Recently, visual prompt tuning is introduced to RGB-Thermal (RGB-T) tracking as a parameter-efficient finetuning (PEFT) method. However, these PEFT-based RGB-T tracking methods typically rely solely on spatial domain information as prompts for feature extraction. As a result, they often fail to achieve optimal performance by overlooking the crucial role of frequency-domain information in prompt learning. To address this issue, we propose an efficient Visual Fourier Prompt Tracking (named VFPTra…