Tootfinder

SPARSE Data, Rich Results: Few-Shot Semi-Supervised Learning via Class-Conditioned Image Translation
Guido Manni, Clemente Lauretti, Loredana Zollo, Paolo Soda
https://arxiv.org/abs/2508.06429

SPARSE Data, Rich Results: Few-Shot Semi-Supervised Learning via Class-Conditioned Image Translation
Deep learning has revolutionized medical imaging, but its effectiveness is severely limited by insufficient labeled training data. This paper introduces a novel GAN-based semi-supervised learning framework specifically designed for low labeled-data regimes, evaluated across settings with 5 to 50 labeled samples per class. Our approach integrates three specialized neural networks -- a generator for class-conditioned image translation, a discriminator for authenticity assessment and classificatio…

A Unified Empirical Risk Minimization Framework for Flexible N-Tuples Weak Supervision
Shuying Huang, Junpeng Li, Changchun Hua, Yana Yang
https://arxiv.org/abs/2507.07771

A Unified Empirical Risk Minimization Framework for Flexible N-Tuples Weak Supervision
To alleviate the annotation burden in supervised learning, N-tuples learning has recently emerged as a powerful weakly-supervised method. While existing N-tuples learning approaches extend pairwise learning to higher-order comparisons and accommodate various real-world scenarios, they often rely on task-specific designs and lack a unified theoretical foundation. In this paper, we propose a general N-tuples learning framework based on empirical risk minimization, which systematically integrates …

End-to-end Acoustic-linguistic Emotion and Intent Recognition Enhanced by Semi-supervised Learning
Zhao Ren, Rathi Adarshi Rammohan, Kevin Scheck, Sheng Li, Tanja Schultz
https://arxiv.org/abs/2507.07806

End-to-end Acoustic-linguistic Emotion and Intent Recognition Enhanced by Semi-supervised Learning
Emotion and intent recognition from speech is essential and has been widely investigated in human-computer interaction. The rapid development of social media platforms, chatbots, and other technologies has led to a large volume of speech data streaming from users. Nevertheless, annotating such data manually is expensive, making it challenging to train machine learning models for recognition purposes. To this end, we propose applying semi-supervised learning to incorporate a large scale of unlab…

This https://arxiv.org/abs/2204.04198 has been replaced.
link: https://scholar.google.com/scholar?q=a

Modern applications of machine learning in quantum sciences
In this book, we provide a comprehensive introduction to the most recent advances in the application of machine learning methods in quantum sciences. We cover the use of deep learning and kernel methods in supervised, unsupervised, and reinforcement learning algorithms for phase classification, representation of many-body quantum states, quantum feedback control, and quantum circuits optimization. Moreover, we introduce and discuss more specialized topics such as differentiable programming, gen…

Advancing Medical Image Segmentation via Self-supervised Instance-adaptive Prototype Learning
Guoyan Liang, Qin Zhou, Jingyuan Chen, Zhe Wang, Chang Yao
https://arxiv.org/abs/2507.07602

Advancing Medical Image Segmentation via Self-supervised Instance-adaptive Prototype Learning
Medical Image Segmentation (MIS) plays a crucial role in medical therapy planning and robot navigation. Prototype learning methods in MIS focus on generating segmentation masks through pixel-to-prototype comparison. However, current approaches often overlook sample diversity by using a fixed prototype per semantic class and neglect intra-class variation within each input. In this paper, we propose to generate instance-adaptive prototypes for MIS, which integrates a common prototype proposal (CP…

Detecting Galactic Rings in the DESI Legacy Imaging Surveys with Semi-Supervised Deep Learning
Jianzhen Chen, Zhijian Luo, Cheng Cheng, Jun Hou, Shaohua Zhang, Chenggang Shu
https://arxiv.org/abs/2507.07552

Detecting Galactic Rings in the DESI Legacy Imaging Surveys with Semi-Supervised Deep Learning
The ring structures of disk galaxies are vital for understanding galaxy evolution and dynamics. However, due to the scarcity of ringed galaxies and challenges in their identification, traditional methods often struggle to efficiently obtain statistically significant samples. To address this, this study employs a novel semi-supervised deep learning model, GC-SWGAN, aimed at identifying galaxy rings from high-resolution images of the DESI Legacy Imaging Surveys. We selected over 5,000 confirmed r…

This https://arxiv.org/abs/2504.11284 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csLG_…

Bipartite Ranking From Multiple Labels: On Loss Versus Label Aggregation
Bipartite ranking is a fundamental supervised learning problem, with the goal of learning a ranking over instances with maximal Area Under the ROC Curve (AUC) against a single binary target label. However, one may often observe multiple binary target labels, e.g., from distinct human annotators. How can one synthesize such labels into a single coherent ranking? In this work, we formally analyze two approaches to this problem -- loss aggregation and label aggregation -- by characterizing their B…

Value Function Approximation for Nonlinear MPC: Learning a Terminal Cost Function with a Descent Property
T. M. J. T. Baltussen, C. A. Orrico, A. Katriniok, W. P. M. H. Heemels, D. Krishnamoorthy
https://arxiv.org/abs/2508.05804

Value Function Approximation for Nonlinear MPC: Learning a Terminal Cost Function with a Descent Property
We present a novel method to synthesize a terminal cost function for a nonlinear model predictive controller (MPC) through value function approximation using supervised learning. Existing methods enforce a descent property on the terminal cost function by construction, thereby restricting the class of terminal cost functions, which in turn can limit the performance and applicability of the MPC. We present a method to approximate the true cost-to-go with a general function approximator that is c…

Best Practices for Machine Learning-Assisted Protein Engineering
Fabio Herrera-Rocha, David Medina-Ortiz, Fabian Mauz, Juergen Pleiss, Mehdi D. Davari
https://arxiv.org/abs/2507.07547

Best Practices for Machine Learning-Assisted Protein Engineering
Data-driven modeling based on Machine Learning (ML) is becoming a central component of protein engineering workflows. This perspective presents the elements necessary to develop effective, reliable, and reproducible ML models, and a set of guidelines for ML developments for protein engineering. This includes a critical discussion of software engineering good practices for development and evaluation of ML-based protein engineering projects, emphasizing supervised learning. These guidelines cover…

This https://arxiv.org/abs/2505.22942 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCL_…

WorkForceAgent-R1: Incentivizing Reasoning Capability in LLM-based Web Agents via Reinforcement Learning
Large language models (LLMs)-empowered web agents enables automating complex, real-time web navigation tasks in enterprise environments. However, existing web agents relying on supervised fine-tuning (SFT) often struggle with generalization and robustness due to insufficient reasoning capabilities when handling the inherently dynamic nature of web interactions. In this study, we introduce WorkForceAgent-R1, an LLM-based web agent trained using a rule-based R1-style reinforcement learning framew…

Self-supervised Learning of Latent Space Dynamics
Yue Li, Gene Wei-Chin Lin, Egor Larionov, Aljaz Bozic, Doug Roble, Ladislav Kavan, Stelian Coros, Bernhard Thomaszewski, Tuur Stuyck, Hsiao-yu Chen
https://arxiv.org/abs/2507.07440

Self-supervised Learning of Latent Space Dynamics
Modeling the dynamic behavior of deformable objects is crucial for creating realistic digital worlds. While conventional simulations produce high-quality motions, their computational costs are often prohibitive. Subspace simulation techniques address this challenge by restricting deformations to a lower-dimensional space, improving performance while maintaining visually compelling results. However, even subspace methods struggle to meet the stringent performance demands of portable devices such…

Acoustic Non-Stationarity Objective Assessment with Hard Label Criteria for Supervised Learning Models
Guilherme Zucatelli, Ricardo Barioni, Gabriela Dantas
https://arxiv.org/abs/2508.06405

Acoustic Non-Stationarity Objective Assessment with Hard Label Criteria for Supervised Learning Models
Objective non-stationarity measures are resource intensive and impose critical limitations for real-time processing solutions. In this paper, a novel Hard Label Criteria (HLC) algorithm is proposed to generate a global non-stationarity label for acoustic signals, enabling supervised learning strategies to be trained as stationarity estimators. The HLC is first evaluated on state-of-the-art general-purpose acoustic models, demonstrating that these models encode stationarity information. Furtherm…

Frequency Prior Guided Matching: A Data Augmentation Approach for Generalizable Semi-Supervised Polyp Segmentation
Haoran Xi, Chen Liu, Xiaolin Li
https://arxiv.org/abs/2508.06517

Frequency Prior Guided Matching: A Data Augmentation Approach for Generalizable Semi-Supervised Polyp Segmentation
Automated polyp segmentation is essential for early diagnosis of colorectal cancer, yet developing robust models remains challenging due to limited annotated data and significant performance degradation under domain shift. Although semi-supervised learning (SSL) reduces annotation requirements, existing methods rely on generic augmentations that ignore polyp-specific structural properties, resulting in poor generalization to new imaging centers and devices. To address this, we introduce Frequen…

Topological Machine Learning with Unreduced Persistence Diagrams
Nicole Abreu, Parker B. Edwards, Francis Motta
https://arxiv.org/abs/2507.07156 https://…

Topological Machine Learning with Unreduced Persistence Diagrams
Supervised machine learning pipelines trained on features derived from persistent homology have been experimentally observed to ignore much of the information contained in a persistence diagram. Computing persistence diagrams is often the most computationally demanding step in such a pipeline, however. To explore this, we introduce several methods to generate topological feature vectors from unreduced boundary matrices. We compared the performance of pipelines trained on vectorizations of unred…

Semi-supervised Community Detection using Glauber Dynamics for an Ising Model
Konstantin Avrachenkov, Diego Goldsztajn
https://arxiv.org/abs/2506.09223 htt…

Semi-supervised Community Detection using Glauber Dynamics for an Ising Model
We consider graphs with two communities and analyze an algorithm for learning the community labels when the edges of the graph and only a small fraction of the labels are known in advance. The algorithm is based on the Glauber dynamics for an Ising model where the energy function includes a quadratic penalty on the magnetization. The analysis focuses on graphs sampled from a Stochastic Block Model (SBM) with slowly growing mean degree. We derive a mean-field limit for the magnetization of each …

Self-supervised learning predicts plant growth trajectories from multi-modal industrial greenhouse data
Adam J Riesselman, Evan M Cofer, Therese LaRue, Wim Meeussen
https://arxiv.org/abs/2507.06336

Self-supervised learning predicts plant growth trajectories from multi-modal industrial greenhouse data
Quantifying organism-level phenotypes, such as growth dynamics and biomass accumulation, is fundamental to understanding agronomic traits and optimizing crop production. However, quality growing data of plants at scale is difficult to generate. Here we use a mobile robotic platform to capture high-resolution environmental sensing and phenotyping measurements of a large-scale hydroponic leafy greens system. We describe a self-supervised modeling approach to build a map from observed growing data…

Self-supervised Deep Learning for Denoising in Ultrasound Microvascular Imaging
Lijie Huang, Jingyi Yin, Jingke Zhang, U-Wai Lok, Ryan M. DeRuiter, Jieyang Jin, Kate M. Knoll, Kendra E. Petersen, James D. Krier, Xiang-yang Zhu, Gina K. Hesley, Kathryn A. Robinson, Andrew J. Bentall, Thomas D. Atwell, Andrew D. Rule, Lilach O. Lerman, Shigao Chen, Chengwu Huang

Self-supervised Deep Learning for Denoising in Ultrasound Microvascular Imaging
Ultrasound microvascular imaging (UMI) is often hindered by low signal-to-noise ratio (SNR), especially in contrast-free or deep tissue scenarios, which impairs subsequent vascular quantification and reliable disease diagnosis. To address this challenge, we propose Half-Angle-to-Half-Angle (HA2HA), a self-supervised denoising framework specifically designed for UMI. HA2HA constructs training pairs from complementary angular subsets of beamformed radio-frequency (RF) blood flow data, across whic…

This https://arxiv.org/abs/2409.14453 has been replaced.
initial toot: https://mastoxiv.page/@arX…

Self-Attention Assistant Classification of Non-Hermitian Phases in Two-Dimensional Lattice
Classification of the non-Hermitian phases in high-dimensional lattice becomes challenging due to interplay of the band topology and non-Hermiticity. The significant increase in data dimensions and the number of categories has rendered traditional supervised learning and unsupervised manifold learning failed. Here, we propose the self-attention assistant machine learning for clustering non-Hermitian phases in two-dimensional lattice. By incorporating the self-attention mechanism, the model can …

MMOC: Self-Supervised EEG Emotion Recognition Framework with Multi-Model Online Collaboration
Hanqi Wang, Yang Liu, Peng Ye, Liang Song
https://arxiv.org/abs/2507.03977

MMOC: Self-Supervised EEG Emotion Recognition Framework with Multi-Model Online Collaboration
Electroencephalography (EEG) emotion recognition plays a crucial role in human-computer interaction, particularly in healthcare and neuroscience. While supervised learning has been widely used, its reliance on manual annotations introduces high costs and potential bias. Self-supervised learning (SSL) offers a promising alternative by generating labels through pretext tasks. However, high inter-subject variability in EEG signals leads to significant data drift, limiting self-supervised models' g…

Liquid and solid layers in a thermal deep learning machine
Gang Huang, Lai Shun Chan, Hajime Yoshino, Ge Zhang, Yuliang Jin
https://arxiv.org/abs/2506.06789

Liquid and solid layers in a thermal deep learning machine
Based on deep neural networks (DNNs), deep learning has been successfully applied to many problems, but its mechanism is still not well understood -- especially the reason why over-parametrized DNNs can generalize. A recent statistical mechanics theory on supervised learning by a prototypical multi-layer perceptron (MLP) on some artificial learning scenarios predicts that adjustable parameters of over-parametrized MLPs become strongly constrained by the training data close to the input/output b…

A Topological Improvement of the Overall Performance of Sparse Evolutionary Training: Motif-Based Structural Optimization of Sparse MLPs Project
Xiaotian Chen, Hongyun Liu, Seyed Sahand Mohammadi Ziabari
https://arxiv.org/abs/2506.09204

A Topological Improvement of the Overall Performance of Sparse Evolutionary Training: Motif-Based Structural Optimization of Sparse MLPs Project
Deep Neural Networks (DNNs) have been proven to be exceptionally effective and have been applied across diverse domains within deep learning. However, as DNN models increase in complexity, the demand for reduced computational costs and memory overheads has become increasingly urgent. Sparsity has emerged as a leading approach in this area. The robustness of sparse Multi-layer Perceptrons (MLPs) for supervised feature selection, along with the application of Sparse Evolutionary Training (SET), i…

Flexible and Efficient Drift Detection without Labels
Nelvin Tan, Yu-Ching Shih, Dong Yang, Amol Salunkhe
https://arxiv.org/abs/2506.08734 https://

Flexible and Efficient Drift Detection without Labels
Machine learning models are being increasingly used to automate decisions in almost every domain, and ensuring the performance of these models is crucial for ensuring high quality machine learning enabled services. Ensuring concept drift is detected early is thus of the highest importance. A lot of research on concept drift has focused on the supervised case that assumes the true labels of supervised tasks are available immediately after making predictions. Controlling for false positives while…

Model-Driven Graph Contrastive Learning
Ali Azizpour, Nicolas Zilberstein, Santiago Segarra
https://arxiv.org/abs/2506.06212 https://…

Model-Driven Graph Contrastive Learning
We propose $\textbf{MGCL}$, a model-driven graph contrastive learning (GCL) framework that leverages graphons (probabilistic generative models for graphs) to guide contrastive learning by accounting for the data's underlying generative process. GCL has emerged as a powerful self-supervised framework for learning expressive node or graph representations without relying on annotated labels, which are often scarce in real-world data. By contrasting augmented views of graph data, GCL has demonstrat…

Supervised Machine Learning Methods with Uncertainty Quantification for Exoplanet Atmospheric Retrievals from Transmission Spectroscopy
Roy T. Forestano, Konstantin T. Matchev, Katia Matcheva, Eyup B. Unlu
https://arxiv.org/abs/2508.04982

Supervised Machine Learning Methods with Uncertainty Quantification for Exoplanet Atmospheric Retrievals from Transmission Spectroscopy
Standard Bayesian retrievals for exoplanet atmospheric parameters from transmission spectroscopy, while well understood and widely used, are generally computationally expensive. In the era of the JWST and other upcoming observatories, machine learning approaches have emerged as viable alternatives that are both efficient and robust. In this paper we present a systematic study of several existing machine learning regression techniques and compare their performance for retrieving exoplanet atmosp…

Denoising radio pulses from air showers using machine-learning methods
Aur\'elien Benoit-L\'evy (for the GRAND Collaboration), Zhisen Lai (for the GRAND Collaboration), Oscar Macias (for the GRAND Collaboration), Ars\`ene Ferri\`ere (for the GRAND Collaboration)
https://arxiv.org/abs/2507.06688

Denoising radio pulses from air showers using machine-learning methods
The Giant Radio Array for Neutrino Detection (GRAND) aims to detect radio signals from extensive air showers (EAS) caused by ultra-high-energy (UHE) cosmic particles. Galactic, hardware-like, and anthropogenic noise are expected to contaminate these signals. To address this problem, we propose training a supervised convolutional network known as an encoder-decoder. This network is used to learn a coded representation of the data and remove specific features from it. This denoiser is trained usi…

Bridging Perception and Action: Spatially-Grounded Mid-Level Representations for Robot Generalization
Jonathan Yang, Chuyuan Kelly Fu, Dhruv Shah, Dorsa Sadigh, Fei Xia, Tingnan Zhang
https://arxiv.org/abs/2506.06196

Bridging Perception and Action: Spatially-Grounded Mid-Level Representations for Robot Generalization
In this work, we investigate how spatially grounded auxiliary representations can provide both broad, high-level grounding as well as direct, actionable information to improve policy learning performance and generalization for dexterous tasks. We study these mid-level representations across three critical dimensions: object-centricity, pose-awareness, and depth-awareness. We use these interpretable mid-level representations to train specialist encoders via supervised learning, then feed them as…

The Gauss-Markov Adjunction: Categorical Semantics of Residuals in Supervised Learning
Moto Kamiura
https://arxiv.org/abs/2507.02442 https://

The Gauss-Markov Adjunction: Categorical Semantics of Residuals in Supervised Learning
Enhancing the intelligibility and interpretability of machine learning is a crucial task in responding to the demand for Explicability as an AI principle, and in promoting the better social implementation of AI. The aim of our research is to contribute to this improvement by reformulating machine learning models through the lens of category theory, thereby developing a semantic framework for structuring and understanding AI systems. Our categorical modeling in this paper clarifies and formalize…

Enhancement of Quantum Semi-Supervised Learning via Improved Laplacian and Poisson Methods
Hamed Gholipour, Farid Bozorgnia, Hamzeh Mohammadigheymasi, Kailash Hambarde, Javier Mancilla, Hugo Proenca, Joao Neves, Moharram Challenger
https://arxiv.org/abs/2508.02054

Enhancement of Quantum Semi-Supervised Learning via Improved Laplacian and Poisson Methods
This paper develops a hybrid quantum approach for graph-based semi-supervised learning to enhance performance in scenarios where labeled data is scarce. We introduce two enhanced quantum models, the Improved Laplacian Quantum Semi-Supervised Learning (ILQSSL) and the Improved Poisson Quantum Semi-Supervised Learning (IPQSSL), that incorporate advanced label propagation strategies within variational quantum circuits. These models utilize QR decomposition to embed graph structure directly into qu…

Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning
Ziyang Wang, Jaehong Yoon, Shoubin Yu, Md Mohaiminul Islam, Gedas Bertasius, Mohit Bansal
https://arxiv.org/abs/2507.06485

Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning
Despite advances in reinforcement learning (RL)-based video reasoning with large language models (LLMs), data collection and finetuning remain significant challenges. These methods often rely on large-scale supervised fine-tuning (SFT) with extensive video data and long Chain-of-Thought (CoT) annotations, making them costly and hard to scale. To address this, we present Video-RTS, a new approach to improve video reasoning capability with drastically improved data efficiency by combining data-ef…

Unified Semi-Supervised Pipeline for Automatic Speech Recognition
Nune Tadevosyan, Nikolay Karpov, Andrei Andrusenko, Vitaly Lavrukhin, Ante Jukic
https://arxiv.org/abs/2506.07659

Unified Semi-Supervised Pipeline for Automatic Speech Recognition
Automatic Speech Recognition has been a longstanding research area, with substantial efforts dedicated to integrating semi-supervised learning due to the scarcity of labeled datasets. However, most prior work has focused on improving learning algorithms using existing datasets, without providing a complete public framework for large-scale semi-supervised training across new datasets or languages. In this work, we introduce a fully open-source semi-supervised training framework encompassing the …

Latent Acoustic Mapping for Direction of Arrival Estimation: A Self-Supervised Approach
Adrian S. Roman, Iran R. Roman, Juan P. Bello
https://arxiv.org/abs/2507.07066

Latent Acoustic Mapping for Direction of Arrival Estimation: A Self-Supervised Approach
Acoustic mapping techniques have long been used in spatial audio processing for direction of arrival estimation (DoAE). Traditional beamforming methods for acoustic mapping, while interpretable, often rely on iterative solvers that can be computationally intensive and sensitive to acoustic variability. On the other hand, recent supervised deep learning approaches offer feedforward speed and robustness but require large labeled datasets and lack interpretability. Despite their strengths, both me…

LPO: Towards Accurate GUI Agent Interaction via Location Preference Optimization
Jiaqi Tang, Yu Xia, Yi-Feng Wu, Yuwei Hu, Yuhui Chen, Qing-Guo Chen, Xiaogang Xu, Xiangyu Wu, Hao Lu, Yanqing Ma, Shiyin Lu, Qifeng Chen
https://arxiv.org/abs/2506.09373

LPO: Towards Accurate GUI Agent Interaction via Location Preference Optimization
The advent of autonomous agents is transforming interactions with Graphical User Interfaces (GUIs) by employing natural language as a powerful intermediary. Despite the predominance of Supervised Fine-Tuning (SFT) methods in current GUI agents for achieving spatial localization, these methods face substantial challenges due to their limited capacity to accurately perceive positional data. Existing strategies, such as reinforcement learning, often fail to assess positional accuracy effectively, …

Taming Data Challenges in ML-based Security Tasks: Lessons from Integrating Generative AI
Shravya Kanchi, Neal Mangaokar, Aravind Cheruvu, Sifat Muhammad Abdullah, Shirin Nilizadeh, Atul Prakash, Bimal Viswanath
https://arxiv.org/abs/2507.06092

Taming Data Challenges in ML-based Security Tasks: Lessons from Integrating Generative AI
Machine learning-based supervised classifiers are widely used for security tasks, and their improvement has been largely focused on algorithmic advancements. We argue that data challenges that negatively impact the performance of these classifiers have received limited attention. We address the following research question: Can developments in Generative AI (GenAI) address these data challenges and improve classifier performance? We propose augmenting training datasets with synthetic data genera…

TRACE: Contrastive learning for multi-trial time-series data in neuroscience
Lisa Schmors, Dominic Gonschorek, Jan Niklas B\"ohm, Yongrong Qiu, Na Zhou, Dmitry Kobak, Andreas Tolias, Fabian Sinz, Jacob Reimer, Katrin Franke, Sebastian Damrich, Philipp Berens
https://arxiv.org/abs/2506.04906

TRACE: Contrastive learning for multi-trial time-series data in neuroscience
Modern neural recording techniques such as two-photon imaging allow to acquire vast time-series datasets with responses of hundreds or thousands of neurons. Contrastive learning is a powerful self-supervised framework for learning representations of complex datasets. Existing applications for neural time series rely on generic data augmentations and do not exploit the multi-trial data structure inherent in many neural datasets. Here we present TRACE, a new contrastive learning framework that av…

Crowd-SFT: Crowdsourcing for LLM Alignment
Alex Sotiropoulos, Sulyab Thottungal Valapu, Linus Lei, Jared Coleman, Bhaskar Krishnamachari
https://arxiv.org/abs/2506.04063

Crowd-SFT: Crowdsourcing for LLM Alignment
Large Language Models (LLMs) increasingly rely on Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF) to align model responses with human preferences. While RLHF employs a reinforcement learning approach with a separate reward model, SFT uses human-curated datasets for supervised learning. Both approaches traditionally depend on small, vetted groups of annotators, making them costly, prone to bias, and limited in scalability. We propose an open, crowd-sourced fine…

Attention-Guided Multi-Scale Local Reconstruction for Point Clouds via Masked Autoencoder Self-Supervised Learning
Xin Cao, Haoyu Wang, Yuzhu Mao, Xinda Liu, Linzhi Su, Kang Li
https://arxiv.org/abs/2507.04084

Attention-Guided Multi-Scale Local Reconstruction for Point Clouds via Masked Autoencoder Self-Supervised Learning
Self-supervised learning has emerged as a prominent research direction in point cloud processing. While existing models predominantly concentrate on reconstruction tasks at higher encoder layers, they often neglect the effective utilization of low-level local features, which are typically employed solely for activation computations rather than directly contributing to reconstruction tasks. To overcome this limitation, we introduce PointAMaLR, a novel self-supervised learning framework that enha…

R1-RE: Cross-Domain Relationship Extraction with RLVR
Runpeng Dai, Tong Zheng, Run Yang, Hongtu Zhu
https://arxiv.org/abs/2507.04642 https://

R1-RE: Cross-Domain Relationship Extraction with RLVR
Relationship extraction (RE) is a core task in natural language processing. Traditional approaches typically frame RE as a supervised learning problem, directly mapping context to labels-an approach that often suffers from poor out-of-domain (OOD) generalization. Inspired by the workflow of human annotators, we reframe RE as a reasoning task guided by annotation guidelines and introduce R1-RE, the first reinforcement learning with verifiable reward (RLVR) framework for RE tasks. Our method elic…

This https://arxiv.org/abs/2505.20529 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSD_…

Training Articulatory Inversion Models for Inter-Speaker Consistency
Acoustic-to-Articulatory Inversion (AAI) attempts to model the inverse mapping from speech to articulation. Exact articulatory prediction from speech alone may be impossible, as speakers can choose different forms of articulation seemingly without reference to their vocal tract structure. However, once a speaker has selected an articulatory form, their productions vary minimally. Recent works in AAI have proposed adapting Self-Supervised Learning (SSL) models to single-speaker datasets, claimin…

Table-r1: Self-supervised and Reinforcement Learning for Program-based Table Reasoning in Small Language Models
Rihui Jin, Zheyu Xin, Xing Xie, Zuoyi Li, Guilin Qi, Yongrui Chen, Xinbang Dai, Tongtong Wu, Gholamreza Haffari
https://arxiv.org/abs/2506.06137

Table-r1: Self-supervised and Reinforcement Learning for Program-based Table Reasoning in Small Language Models
Table reasoning (TR) requires structured reasoning over semi-structured tabular data and remains challenging, particularly for small language models (SLMs, e.g., LLaMA-8B) due to their limited capacity compared to large LMs (LLMs, e.g., GPT-4o). To narrow this gap, we explore program-based TR (P-TR), which circumvents key limitations of text-based TR (T-TR), notably in numerical reasoning, by generating executable programs. However, applying P-TR to SLMs introduces two challenges: (i) vulnerabi…

Conservative approximation-based feedforward neural network for WENO schemes
Kwanghyuk Park, Jiaxi Gu, Jae-Hun Jung
https://arxiv.org/abs/2507.06190 https:…

Conservative approximation-based feedforward neural network for WENO schemes
In this work, we present the feedforward neural network based on the conservative approximation to the derivative from point values, for the weighted essentially non-oscillatory (WENO) schemes in solving hyperbolic conservation laws. The feedforward neural network, whose inputs are point values from the three-point stencil and outputs are two nonlinear weights, takes the place of the classical WENO weighting procedure. For the training phase, we employ the supervised learning and create a new l…

MGS3: A Multi-Granularity Self-Supervised Code Search Framework
Rui Li, Junfeng Kang, Qi Liu, Liyang He, Zheng Zhang, Yunhao Sha, Linbo Zhu, Zhenya Huang
https://arxiv.org/abs/2505.24274

MGS3: A Multi-Granularity Self-Supervised Code Search Framework
In the pursuit of enhancing software reusability and developer productivity, code search has emerged as a key area, aimed at retrieving code snippets relevant to functionalities based on natural language queries. Despite significant progress in self-supervised code pre-training utilizing the vast amount of code data in repositories, existing methods have primarily focused on leveraging contrastive learning to align natural language with function-level code snippets. These studies have overlooke…

SGCL: Unifying Self-Supervised and Supervised Learning for Graph Recommendation
Weizhi Zhang, Liangwei Yang, Zihe Song, Henrry Peng Zou, Ke Xu, Yuanjie Zhu, Philip S. Yu
https://arxiv.org/abs/2507.13336

SGCL: Unifying Self-Supervised and Supervised Learning for Graph Recommendation
Recommender systems (RecSys) are essential for online platforms, providing personalized suggestions to users within a vast sea of information. Self-supervised graph learning seeks to harness high-order collaborative filtering signals through unsupervised augmentation on the user-item bipartite graph, primarily leveraging a multi-task learning framework that includes both supervised recommendation loss and self-supervised contrastive loss. However, this separate design introduces additional grap…

TerraFM: A Scalable Foundation Model for Unified Multisensor Earth Observation
Muhammad Sohail Danish, Muhammad Akhtar Munir, Syed Roshaan Ali Shah, Muhammad Haris Khan, Rao Muhammad Anwer, Jorma Laaksonen, Fahad Shahbaz Khan, Salman Khan
https://arxiv.org/abs/2506.06281

TerraFM: A Scalable Foundation Model for Unified Multisensor Earth Observation
Modern Earth observation (EO) increasingly leverages deep learning to harness the scale and diversity of satellite imagery across sensors and regions. While recent foundation models have demonstrated promising generalization across EO tasks, many remain limited by the scale, geographical coverage, and spectral diversity of their training data, factors critical for learning globally transferable representations. In this work, we introduce TerraFM, a scalable self-supervised learning model that l…

This https://arxiv.org/abs/2505.24765 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_qu…

Supervised Quantum Machine Learning: A Future Outlook from Qubits to Enterprise Applications
Supervised Quantum Machine Learning (QML) represents an intersection of quantum computing and classical machine learning, aiming to use quantum resources to support model training and inference. This paper reviews recent developments in supervised QML, focusing on methods such as variational quantum circuits, quantum neural networks, and quantum kernel methods, along with hybrid quantum-classical workflows. We examine recent experimental studies that show partial indications of quantum advantag…

DAFMSVC: One-Shot Singing Voice Conversion with Dual Attention Mechanism and Flow Matching
Wei Chen, Binzhu Sha, Dan Luo, Jing Yang, Zhuo Wang, Fan Fan, Zhiyong Wu
https://arxiv.org/abs/2508.05978

DAFMSVC: One-Shot Singing Voice Conversion with Dual Attention Mechanism and Flow Matching
Singing Voice Conversion (SVC) transfers a source singer's timbre to a target while keeping melody and lyrics. The key challenge in any-to-any SVC is adapting unseen speaker timbres to source audio without quality degradation. Existing methods either face timbre leakage or fail to achieve satisfactory timbre similarity and quality in the generated audio. To address these challenges, we propose DAFMSVC, where the self-supervised learning (SSL) features from the source audio are replaced with the…

This https://arxiv.org/abs/2505.16223 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

MADCluster: Model-agnostic Anomaly Detection with Self-supervised Clustering Network
In this paper, we propose MADCluster, a novel model-agnostic anomaly detection framework utilizing self-supervised clustering. MADCluster is applicable to various deep learning architectures and addresses the 'hypersphere collapse' problem inherent in existing deep learning-based anomaly detection methods. The core idea is to cluster normal pattern data into a 'single cluster' while simultaneously learning the cluster center and mapping data close to this center. Also, to improve expressiveness…

Scenario-Agnostic Deep-Learning-Based Localization with Contrastive Self-Supervised Pre-training
Lingyan Zhang, Yuanfeng Qiu, Dachuan Li, Shaohua Wu, Tingting Zhang, Qinyu Zhang
https://arxiv.org/abs/2508.03084

Scenario-Agnostic Deep-Learning-Based Localization with Contrastive Self-Supervised Pre-training
Wireless localization has become a promising technology for offering intelligent location-based services. Although its localization accuracy is improved under specific scenarios, the short of environmental dynamic vulnerability still hinders this approach from being fully practical applications. In this paper, we propose CSSLoc, a novel framework on contrastive self-supervised pre-training to learn generic representations for accurate localization in various scenarios. Without the location info…

WOCD: A Semi-Supervised Method for Overlapping Community Detection Using Weak Cliques
Shaozhen Ma, Hanchen Wang, Dong Wen, Wenjie Zhang, Wei Huang, Ying Zhang
https://arxiv.org/abs/2508.00927

WOCD: A Semi-Supervised Method for Overlapping Community Detection Using Weak Cliques
Overlapping community detection (OCD) is a fundamental graph data analysis task for extracting graph patterns. Traditional OCD methods can be broadly divided into node clustering and link clustering approaches, both of which rely solely on link information to identify overlapping communities. In recent years, deep learning-based methods have made significant advancements for this task. However, existing GNN-based approaches often face difficulties in effectively integrating link, attribute, and…

DreamGrasp: Zero-Shot 3D Multi-Object Reconstruction from Partial-View Images for Robotic Manipulation
Young Hun Kim, Seungyeon Kim, Yonghyeon Lee, Frank Chongwoo Park
https://arxiv.org/abs/2507.05627

DreamGrasp: Zero-Shot 3D Multi-Object Reconstruction from Partial-View Images for Robotic Manipulation
Partial-view 3D recognition -- reconstructing 3D geometry and identifying object instances from a few sparse RGB images -- is an exceptionally challenging yet practically essential task, particularly in cluttered, occluded real-world settings where full-view or reliable depth data are often unavailable. Existing methods, whether based on strong symmetry priors or supervised learning on curated datasets, fail to generalize to such scenarios. In this work, we introduce DreamGrasp, a framework tha…

SpecBPP: A Self-Supervised Learning Approach for Hyperspectral Representation and Soil Organic Carbon Estimation
Daniel La'ah Ayuba, Jean-Yves Guillemaut, Belen Marti-Cardona, Oscar Mendez Maldonado
https://arxiv.org/abs/2507.19781

SpecBPP: A Self-Supervised Learning Approach for Hyperspectral Representation and Soil Organic Carbon Estimation
Self-supervised learning has revolutionized representation learning in vision and language, but remains underexplored for hyperspectral imagery (HSI), where the sequential structure of spectral bands offers unique opportunities. In this work, we propose Spectral Band Permutation Prediction (SpecBPP), a novel self-supervised learning framework that leverages the inherent spectral continuity in HSI. Instead of reconstructing masked bands, SpecBPP challenges a model to recover the correct order of…

Self-supervised learning of speech representations with Dutch archival data
Nik Vaessen, David A. van Leeuwen, Roeland Ordelman
https://arxiv.org/abs/2507.04554

Self-supervised learning of speech representations with Dutch archival data
This paper explores the use of Dutch archival television broadcast data for self-supervised learning of speech foundation models, specifically wav2vec 2.0. We first study data quality assumptions for pre-training, and show how music, noise and speaker overlap affect SSL convergence and downstream fine-tuning performance. Secondly, we explore effectively pre-processing strategies to convert the noisy broadcast dataset into a qualitative dataset for pre-training, by using Whisper and WhisperX., T…

Self-Supervised Real-Time Tracking of Military Vehicles in Low-FPS UAV Footage
Markiyan Kostiv, Anatolii Adamovskyi, Yevhen Cherniavskyi, Mykyta Varenyk, Ostap Viniavskyi, Igor Krashenyi, Oles Dobosevych
https://arxiv.org/abs/2507.05229

Self-Supervised Real-Time Tracking of Military Vehicles in Low-FPS UAV Footage
Multi-object tracking (MOT) aims to maintain consistent identities of objects across video frames. Associating objects in low-frame-rate videos captured by moving unmanned aerial vehicles (UAVs) in actual combat scenarios is complex due to rapid changes in object appearance and position within the frame. The task becomes even more challenging due to image degradation caused by cloud video streaming and compression algorithms. We present how instance association learning from single-frame annota…

Revisiting Active Learning under (Human) Label Variation
Cornelia Gruber, Helen Alber, Bernd Bischl, G\"oran Kauermann, Barbara Plank, Matthias A{\ss}enmacher
https://arxiv.org/abs/2507.02593

Revisiting Active Learning under (Human) Label Variation
Access to high-quality labeled data remains a limiting factor in applied supervised learning. While label variation (LV), i.e., differing labels for the same instance, is common, especially in natural language processing, annotation frameworks often still rest on the assumption of a single ground truth. This overlooks human label variation (HLV), the occurrence of plausible differences in annotations, as an informative signal. Similarly, active learning (AL), a popular approach to optimizing th…

Semi-supervised learning for linear extremile regression
Rong Jiang, Keming Yu, Jiangfeng Wang
https://arxiv.org/abs/2507.01314 https://

Semi-supervised learning for linear extremile regression
Extremile regression, as a least squares analog of quantile regression, is potentially useful tool for modeling and understanding the extreme tails of a distribution. However, existing extremile regression methods, as nonparametric approaches, may face challenges in high-dimensional settings due to data sparsity, computational inefficiency, and the risk of overfitting. While linear regression serves as the foundation for many other statistical and machine learning models due to its simplicity, …

Identifying Radio Active Galactic Nuclei with Machine Learning and Large-Area Surveys
Xu-Liang Fan, Jie Li
https://arxiv.org/abs/2508.01596 https://arxiv.o…

Identifying Radio Active Galactic Nuclei with Machine Learning and Large-Area Surveys
Context. Active galactic nuclei (AGNs) and star forming galaxies (SFGs) are the primary sources of extragalactic radio sky. But it is difficult to distinguish the radio emission produced by AGNs from that by SFGs, especially when the radio sources are faint. Best et al. (2023) classified the radio sources in LoTSS Deep Fields DR1 through multiwavelength SED fitting. With the classification results of them, we perform a supervised machine learning to distinguish radio AGNs and radio SFGs. Aims…

Supervised Quantum Machine Learning: A Future Outlook from Qubits to Enterprise Applications
Srikanth Thudumu, Jason Fisher, Hung Du
https://arxiv.org/abs/2505.24765

Supervised Quantum Machine Learning: A Future Outlook from Qubits to Enterprise Applications
Supervised Quantum Machine Learning (QML) represents an intersection of quantum computing and classical machine learning, aiming to use quantum resources to support model training and inference. This paper reviews recent developments in supervised QML, focusing on methods such as variational quantum circuits, quantum neural networks, and quantum kernel methods, along with hybrid quantum-classical workflows. We examine recent experimental studies that show partial indications of quantum advantag…

A Semi-Supervised Federated Learning Framework with Hierarchical Clustering Aggregation for Heterogeneous Satellite Networks
Zhuocheng Liu, Zhishu Shen, Qiushi Zheng, Tiehua Zhang, Zheng Lei, Jiong Jin
https://arxiv.org/abs/2507.22339

A Semi-Supervised Federated Learning Framework with Hierarchical Clustering Aggregation for Heterogeneous Satellite Networks
Low Earth Orbit (LEO) satellites are emerging as key components of 6G networks, with many already deployed to support large-scale Earth observation and sensing related tasks. Federated Learning (FL) presents a promising paradigm for enabling distributed intelligence in these resource-constrained and dynamic environments. However, achieving reliable convergence, while minimizing both processing time and energy consumption, remains a substantial challenge, particularly in heterogeneous and partia…

Test-Time Reinforcement Learning for GUI Grounding via Region Consistency
Yong Du, Yuchen Yan, Fei Tang, Zhengxi Lu, Chang Zong, Weiming Lu, Shengpei Jiang, Yongliang Shen
https://arxiv.org/abs/2508.05615

Test-Time Reinforcement Learning for GUI Grounding via Region Consistency
Graphical User Interface (GUI) grounding, the task of mapping natural language instructions to precise screen coordinates, is fundamental to autonomous GUI agents. While existing methods achieve strong performance through extensive supervised training or reinforcement learning with labeled rewards, they remain constrained by the cost and availability of pixel-level annotations. We observe that when models generate multiple predictions for the same GUI element, the spatial overlap patterns revea…

DAS-MAE: A self-supervised pre-training framework for universal and high-performance representation learning of distributed fiber-optic acoustic sensing
Junyi Duan, Jiageng Chen, Zuyuan He
https://arxiv.org/abs/2506.04552

DAS-MAE: A self-supervised pre-training framework for universal and high-performance representation learning of distributed fiber-optic acoustic sensing
Distributed fiber-optic acoustic sensing (DAS) has emerged as a transformative approach for distributed vibration measurement with high spatial resolution and long measurement range while maintaining cost-efficiency. However, the two-dimensional spatial-temporal DAS signals present analytical challenges. The abstract signal morphology lacking intuitive physical correspondence complicates human interpretation, and its unique spatial-temporal coupling renders conventional image processing methods…

A Comprehensive Framework for Uncertainty Quantification of Voxel-wise Supervised Models in IVIM MRI
Nicola Casali, Alessandro Brusaferri, Giuseppe Baselli, Stefano Fumagalli, Edoardo Micotti, Gianluigi Forloni, Riaz Hussein, Giovanna Rizzo, Alfonso Mastropietro
https://arxiv.org/abs/2508.04588

A Comprehensive Framework for Uncertainty Quantification of Voxel-wise Supervised Models in IVIM MRI
Accurate estimation of intravoxel incoherent motion (IVIM) parameters from diffusion-weighted MRI remains challenging due to the ill-posed nature of the inverse problem and high sensitivity to noise, particularly in the perfusion compartment. In this work, we propose a probabilistic deep learning framework based on Deep Ensembles (DE) of Mixture Density Networks (MDNs), enabling estimation of total predictive uncertainty and decomposition into aleatoric (AU) and epistemic (EU) components. The m…

Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning
Fangyu Lei, Jinxiang Meng, Yiming Huang, Tinghong Chen, Yun Zhang, Shizhu He, Jun Zhao, Kang Liu
https://arxiv.org/abs/2506.01710

Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning
Table reasoning, encompassing tasks such as table question answering, fact verification, and text-to-SQL, requires precise understanding of structured tabular data, coupled with numerical computation and code manipulation for effective inference. Supervised fine-tuning (SFT) approaches have achieved notable success but often struggle with generalization and robustness due to biases inherent in imitative learning. We introduce Reasoning-Table, the first application of reinforcement learning (RL)…

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[3/6]:
- Shaping Sparse Rewards in Reinforcement Learning: A Semi-supervised Approach
Wenyun Li, Wenjie Huang, Chen Sun

This https://arxiv.org/abs/2401.01473 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_ees…

Self-supervised Reflective Learning through Self-distillation and Online Clustering for Speaker Representation Learning
Speaker representation learning is crucial for voice recognition systems, with recent advances in self-supervised approaches reducing dependency on labeled data. Current two-stage iterative frameworks, while effective, suffer from significant computational overhead due to repeated rounds of clustering and training. They also struggle with noisy pseudo labels that can impair model learning. This paper introduces self-supervised reflective learning (SSRL), an improved framework that addresses the…

AICO: Feature Significance Tests for Supervised Learning
Kay Giesecke, Enguerrand Horel, Chartsiri Jirachotkulthorn
https://arxiv.org/abs/2506.23396 https:…

AICO: Feature Significance Tests for Supervised Learning
The opacity of many supervised learning algorithms remains a key challenge, hindering scientific discovery and limiting broader deployment -- particularly in high-stakes domains. This paper develops model- and distribution-agnostic significance tests to assess the influence of input features in any regression or classification algorithm. Our method evaluates a feature's incremental contribution to model performance by masking its values across samples. Under the null hypothesis, the distributio…

MedCAL-Bench: A Comprehensive Benchmark on Cold-Start Active Learning with Foundation Models for Medical Image Analysis
Ning Zhu, Xiaochuan Ma, Shaoting Zhang, Guotai Wang
https://arxiv.org/abs/2508.03441

MedCAL-Bench: A Comprehensive Benchmark on Cold-Start Active Learning with Foundation Models for Medical Image Analysis
Cold-Start Active Learning (CSAL) aims to select informative samples for annotation without prior knowledge, which is important for improving annotation efficiency and model performance under a limited annotation budget in medical image analysis. Most existing CSAL methods rely on Self-Supervised Learning (SSL) on the target dataset for feature extraction, which is inefficient and limited by insufficient feature representation. Recently, pre-trained Foundation Models (FMs) have shown powerful f…

Revealing the Hidden Temporal Structure of HubertSoft Embeddings based on the Russian Phonetic Corpus
Anastasia Ananeva, Anton Tomilov, Marina Volkova
https://arxiv.org/abs/2507.06794

Revealing the Hidden Temporal Structure of HubertSoft Embeddings based on the Russian Phonetic Corpus
Self-supervised learning (SSL) models such as Wav2Vec 2.0 and HuBERT have shown remarkable success in extracting phonetic information from raw audio without labelled data. While prior work has demonstrated that SSL embeddings encode phonetic features at the frame level, it remains unclear whether these models preserve temporal structure, specifically, whether embeddings at phoneme boundaries reflect the identity and order of adjacent phonemes. This study investigates the extent to which boundar…

Latent Motion Profiling for Annotation-free Cardiac Phase Detection in Adult and Fetal Echocardiography Videos
Yingyu Yang, Qianye Yang, Kangning Cui, Can Peng, Elena D'Alberti, Netzahualcoyotl Hernandez-Cruz, Olga Patey, Aris T. Papageorghiou, J. Alison Noble
https://arxiv.org/abs/2507.05154…

Latent Motion Profiling for Annotation-free Cardiac Phase Detection in Adult and Fetal Echocardiography Videos
The identification of cardiac phase is an essential step for analysis and diagnosis of cardiac function. Automatic methods, especially data-driven methods for cardiac phase detection, typically require extensive annotations, which is time-consuming and labor-intensive. In this paper, we present an unsupervised framework for end-diastole (ED) and end-systole (ES) detection through self-supervised learning of latent cardiac motion trajectories from 4-chamber-view echocardiography videos. Our meth…

Two-sample comparison through additive tree models for density ratios
Naoki Awaya, Yuliang Xu, Li Ma
https://arxiv.org/abs/2508.03059 https://arxiv.org/pdf…

Two-sample comparison through additive tree models for density ratios
The ratio of two densities characterizes their differences. We consider learning the density ratio given i.i.d. observations from each of the two distributions. We propose additive tree models for the density ratio along with efficient algorithms for training these models using a new loss function called the balancing loss. With this loss, additive tree models for the density ratio can be trained using algorithms original designed for supervised learning. Specifically, they can be trained from …

UPLME: Uncertainty-Aware Probabilistic Language Modelling for Robust Empathy Regression
Md Rakibul Hasan, Md Zakir Hossain, Aneesh Krishna, Shafin Rahman, Tom Gedeon
https://arxiv.org/abs/2508.03520

UPLME: Uncertainty-Aware Probabilistic Language Modelling for Robust Empathy Regression
Supervised learning for empathy regression is challenged by noisy self-reported empathy scores. While many algorithms have been proposed for learning with noisy labels in textual classification problems, the regression counterpart is relatively under-explored. We propose UPLME, an uncertainty-aware probabilistic language modelling framework to capture label noise in the regression setting of empathy detection. UPLME includes a probabilistic language model that predicts both empathy score and he…

Audio-JEPA: Joint-Embedding Predictive Architecture for Audio Representation Learning
Ludovic Tuncay (IRIT-SAMoVA), Etienne Labb\'e (IRIT-SAMoVA), Emmanouil Benetos (QMUL), Thomas Pellegrini (IRIT-SAMoVA)
https://arxiv.org/abs/2507.02915

Audio-JEPA: Joint-Embedding Predictive Architecture for Audio Representation Learning
Building on the Joint-Embedding Predictive Architecture (JEPA) paradigm, a recent self-supervised learning framework that predicts latent representations of masked regions in high-level feature spaces, we propose Audio-JEPA (Audio Joint-Embedding Predictive Architecture), tailored specifically for audio data. Audio-JEPA uses a simple Vision Transformer backbone to predict latent representations of masked spectrogram patches rather than reconstructing raw audio. We pre-train on unlabeled AudioSe…

Principled Curriculum Learning using Parameter Continuation Methods
Harsh Nilesh Pathak, Randy Paffenroth
https://arxiv.org/abs/2507.22089 https://arxiv.or…

Principled Curriculum Learning using Parameter Continuation Methods
In this work, we propose a parameter continuation method for the optimization of neural networks. There is a close connection between parameter continuation, homotopies, and curriculum learning. The methods we propose here are theoretically justified and practically effective for several problems in deep neural networks. In particular, we demonstrate better generalization performance than state-of-the-art optimization techniques such as ADAM for supervised and unsupervised learning tasks.

Towards Hallucination-Free Music: A Reinforcement Learning Preference Optimization Framework for Reliable Song Generation
Huaicheng Zhang, Wei Tan, Guangzheng Li, Yixuan Zhang, Hangting Chen, Shun Lei, Chenyu Yang, Zhiyong Wu, Shuai Wang, Qijun Huang, Dong Yu
https://arxiv.org/abs/2508.05011

Towards Hallucination-Free Music: A Reinforcement Learning Preference Optimization Framework for Reliable Song Generation
Recent advances in audio-based generative language models have accelerated AI-driven lyric-to-song generation. However, these models frequently suffer from content hallucination, producing outputs misaligned with the input lyrics and undermining musical coherence. Current supervised fine-tuning (SFT) approaches, limited by passive label-fitting, exhibit constrained self-improvement and poor hallucination mitigation. To address this core challenge, we propose a novel reinforcement learning (RL) …

AI for the Routine, Humans for the Complex: Accuracy-Driven Data Labelling with Mixed Integer Linear Programming
Mohammad Hossein Amini, Mehrdad Sabetzadeh, Shiva Nejati
https://arxiv.org/abs/2507.04990

AI for the Routine, Humans for the Complex: Accuracy-Driven Data Labelling with Mixed Integer Linear Programming
The scarcity of accurately labelled data remains a major challenge in deep learning (DL). Many DL approaches rely on semi-supervised methods, which focus on constructing large datasets that require only a minimal amount of human-labelled data. Since DL training algorithms can tolerate moderate label noise, it has generally been acceptable for the accuracy of labels in large training datasets to fall well short of a perfect 100%. However, when it comes to testing DL models, achieving high label …

Sparsity-Driven Parallel Imaging Consistency for Improved Self-Supervised MRI Reconstruction
Ya\c{s}ar Utku Al\c{c}alar, Mehmet Ak\c{c}akaya
https://arxiv.org/abs/2505.24136

Sparsity-Driven Parallel Imaging Consistency for Improved Self-Supervised MRI Reconstruction
Physics-driven deep learning (PD-DL) models have proven to be a powerful approach for improved reconstruction of rapid MRI scans. In order to train these models in scenarios where fully-sampled reference data is unavailable, self-supervised learning has gained prominence. However, its application at high acceleration rates frequently introduces artifacts, compromising image fidelity. To mitigate this shortcoming, we propose a novel way to train PD-DL networks via carefully-designed perturbation…

IMPACT: Industrial Machine Perception via Acoustic Cognitive Transformer
Changheon Han, Yuseop Sim, Hoin Jung, Jiho Lee, Hojun Lee, Yun Seok Kang, Sucheol Woo, Garam Kim, Hyung Wook Park, Martin Byung-Guk Jun
https://arxiv.org/abs/2507.06481

IMPACT: Industrial Machine Perception via Acoustic Cognitive Transformer
Acoustic signals from industrial machines offer valuable insights for anomaly detection, predictive maintenance, and operational efficiency enhancement. However, existing task-specific, supervised learning methods often scale poorly and fail to generalize across diverse industrial scenarios, whose acoustic characteristics are distinct from general audio. Furthermore, the scarcity of accessible, large-scale datasets and pretrained models tailored for industrial audio impedes community-driven res…

Leveraging machine learning features for linear optical interferometer control
Sergei S. Kuzmin, Ivan V. Dyakonov, Stanislav S. Straupe
https://arxiv.org/abs/2505.24032

Leveraging machine learning features for linear optical interferometer control
We have developed an algorithm that constructs a model of a reconfigurable optical interferometer, independent of specific architectural constraints. The programming of unitary transformations on the interferometer's optical modes relies on either an analytical method for deriving the unitary matrix from a set of phase shifts or an optimization routine when such decomposition is not available. Our algorithm employs a supervised learning approach, aligning the interferometer model with a trainin…

Neural Collapse based Deep Supervised Federated Learning for Signal Detection in OFDM Systems
Kaidi Xu, Shenglong Zhou, Geoffrey Ye Li
https://arxiv.org/abs/2506.19476

Neural Collapse based Deep Supervised Federated Learning for Signal Detection in OFDM Systems
Future wireless networks are expected to be AI-empowered, making their performance highly dependent on the quality of training datasets. However, physical-layer entities often observe only partial wireless environments characterized by different power delay profiles. Federated learning is capable of addressing this limited observability, but often struggles with data heterogeneity. To tackle this challenge, we propose a neural collapse (NC) inspired deep supervised federated learning (NCDSFL) a…

Active Learning for Manifold Gaussian Process Regression
Yuanxing Cheng, Lulu Kang, Yiwei Wang, Chun Liu
https://arxiv.org/abs/2506.20928 https://

Active Learning for Manifold Gaussian Process Regression
This paper introduces an active learning framework for manifold Gaussian Process (GP) regression, combining manifold learning with strategic data selection to improve accuracy in high-dimensional spaces. Our method jointly optimizes a neural network for dimensionality reduction and a Gaussian process regressor in the latent space, supervised by an active learning criterion that minimizes global prediction error. Experiments on synthetic data demonstrate superior performance over randomly sequen…

Physics-Guided Dual Implicit Neural Representations for Source Separation
Yuan Ni, Zhantao Chen, Alexander N. Petsch, Edmund Xu, Cheng Peng, Alexander I. Kolesnikov, Sugata Chowdhury, Arun Bansil, Jana B. Thayer, Joshua J. Turner
https://arxiv.org/abs/2507.05249

Physics-Guided Dual Implicit Neural Representations for Source Separation
Significant challenges exist in efficient data analysis of most advanced experimental and observational techniques because the collected signals often include unwanted contributions--such as background and signal distortions--that can obscure the physically relevant information of interest. To address this, we have developed a self-supervised machine-learning approach for source separation using a dual implicit neural representation framework that jointly trains two neural networks: one for app…

Translation-Equivariant Self-Supervised Learning for Pitch Estimation with Optimal Transport
Bernardo Torres, Alain Riou, Ga\"el Richard, Geoffroy Peeters
https://arxiv.org/abs/2508.01493

Translation-Equivariant Self-Supervised Learning for Pitch Estimation with Optimal Transport
In this paper, we propose an Optimal Transport objective for learning one-dimensional translation-equivariant systems and demonstrate its applicability to single pitch estimation. Our method provides a theoretically grounded, more numerically stable, and simpler alternative for training state-of-the-art self-supervised pitch estimators.

Quantum Advantage in Learning Quantum Dynamics via Fourier coefficient extraction
Alice Barthe, Mahtab Yaghubi Rad, Michele Grossi, Vedran Dunjko
https://arxiv.org/abs/2506.17089 …

Quantum Advantage in Learning Quantum Dynamics via Fourier coefficient extraction
One of the key challenges in quantum machine learning is finding relevant machine learning tasks with a provable quantum advantage. A natural candidate for this is learning unknown Hamiltonian dynamics. Here, we tackle the supervised learning version of this problem, where we are given random examples of the inputs to the dynamics as classical data, paired with the expectation values of some observable after the time evolution, as corresponding output labels. The task is to replicate the corres…

Robust brain age estimation from structural MRI with contrastive learning
Carlo Alberto Barbano, Benoit Dufumier, Edouard Duchesnay, Marco Grangetto, Pietro Gori
https://arxiv.org/abs/2507.01794

Robust brain age estimation from structural MRI with contrastive learning
Estimating brain age from structural MRI has emerged as a powerful tool for characterizing normative and pathological aging. In this work, we explore contrastive learning as a scalable and robust alternative to supervised approaches for brain age estimation. We introduce a novel contrastive loss function, $\mathcal{L}^{exp}$, and evaluate it across multiple public neuroimaging datasets comprising over 20,000 scans. Our experiments reveal four key findings. First, scaling pre-training on diverse…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[2/5]:
- Decision by Supervised Learning with Deep Ensembles: A Practical Framework for Robust Portfolio O...
Juhyeong Kim, Sungyoon Choi, Youngbin Lee, Yejin Kim, Yongmin Choi, Yongjae Lee

CoughViT: A Self-Supervised Vision Transformer for Cough Audio Representation Learning
Justin Luong, Hao Xue, Flora D. Salim
https://arxiv.org/abs/2508.03764 https://

CoughViT: A Self-Supervised Vision Transformer for Cough Audio Representation Learning
Physicians routinely assess respiratory sounds during the diagnostic process, providing insight into the condition of a patient's airways. In recent years, AI-based diagnostic systems operating on respiratory sounds, have demonstrated success in respiratory disease detection. These systems represent a crucial advancement in early and accessible diagnosis which is essential for timely treatment. However, label and data scarcity remain key challenges, especially for conditions beyond COVID-19, li…

Prompt learning with bounding box constraints for medical image segmentation
M\'elanie Gaillochet, Mehrdad Noori, Sahar Dastani, Christian Desrosiers, Herv\'e Lombaert
https://arxiv.org/abs/2507.02743

Prompt learning with bounding box constraints for medical image segmentation
Pixel-wise annotations are notoriously labourious and costly to obtain in the medical domain. To mitigate this burden, weakly supervised approaches based on bounding box annotations-much easier to acquire-offer a practical alternative. Vision foundation models have recently shown noteworthy segmentation performance when provided with prompts such as points or bounding boxes. Prompt learning exploits these models by adapting them to downstream tasks and automating segmentation, thereby reducing …

ASDA: Audio Spectrogram Differential Attention Mechanism for Self-Supervised Representation Learning
Junyu Wang, Tianrui Wang, Meng Ge, Longbiao Wang, Jianwu Dang
https://arxiv.org/abs/2507.02666

ASDA: Audio Spectrogram Differential Attention Mechanism for Self-Supervised Representation Learning
In recent advancements in audio self-supervised representation learning, the standard Transformer architecture has emerged as the predominant approach, yet its attention mechanism often allocates a portion of attention weights to irrelevant information, potentially impairing the model's discriminative ability. To address this, we introduce a differential attention mechanism, which effectively mitigates ineffective attention allocation through the integration of dual-softmax operations and appro…

Weakly Supervised Intracranial Aneurysm Detection and Segmentation in MR angiography via Multi-task UNet with Vesselness Prior
Erin Rainville, Amirhossein Rasoulian, Hassan Rivaz, Yiming Xiao
https://arxiv.org/abs/2508.00235

Weakly Supervised Intracranial Aneurysm Detection and Segmentation in MR angiography via Multi-task UNet with Vesselness Prior
Intracranial aneurysms (IAs) are abnormal dilations of cerebral blood vessels that, if ruptured, can lead to life-threatening consequences. However, their small size and soft contrast in radiological scans often make it difficult to perform accurate and efficient detection and morphological analyses, which are critical in the clinical care of the disorder. Furthermore, the lack of large public datasets with voxel-wise expert annotations pose challenges for developing deep learning algorithms to…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[4/5]:
- A Review on Self-Supervised Learning for Time Series Anomaly Detection: Recent Advances and Open ...
Aitor S\'anchez-Ferrera, Borja Calvo, Jose A. Lozano

Bi-Level Optimization for Self-Supervised AI-Generated Face Detection
Mian Zou, Nan Zhong, Baosheng Yu, Yibing Zhan, Kede Ma
https://arxiv.org/abs/2507.22824 https://

Bi-Level Optimization for Self-Supervised AI-Generated Face Detection
AI-generated face detectors trained via supervised learning typically rely on synthesized images from specific generators, limiting their generalization to emerging generative techniques. To overcome this limitation, we introduce a self-supervised method based on bi-level optimization. In the inner loop, we pretrain a vision encoder only on photographic face images using a set of linearly weighted pretext tasks: classification of categorical exchangeable image file format (EXIF) tags, ranking o…

AdvMIM: Adversarial Masked Image Modeling for Semi-Supervised Medical Image Segmentation
Lei Zhu, Jun Zhou, Rick Siow Mong Goh, Yong Liu
https://arxiv.org/abs/2506.20563

AdvMIM: Adversarial Masked Image Modeling for Semi-Supervised Medical Image Segmentation
Vision Transformer has recently gained tremendous popularity in medical image segmentation task due to its superior capability in capturing long-range dependencies. However, transformer requires a large amount of labeled data to be effective, which hinders its applicability in annotation scarce semi-supervised learning scenario where only limited labeled data is available. State-of-the-art semi-supervised learning methods propose combinatorial CNN-Transformer learning to cross teach a transform…

Learning from Anatomy: Supervised Anatomical Pretraining (SAP) for Improved Metastatic Bone Disease Segmentation in Whole-Body MRI
Joris Wuts, Jakub Ceranka, Nicolas Michoux, Fr\'ed\'eric Lecouvet, Jef Vandemeulebroucke
https://arxiv.org/abs/2506.19590

Learning from Anatomy: Supervised Anatomical Pretraining (SAP) for Improved Metastatic Bone Disease Segmentation in Whole-Body MRI
The segmentation of metastatic bone disease (MBD) in whole-body MRI (WB-MRI) is a challenging problem. Due to varying appearances and anatomical locations of lesions, ambiguous boundaries, and severe class imbalance, obtaining reliable segmentations requires large, well-annotated datasets capturing lesion variability. Generating such datasets requires substantial time and expertise, and is prone to error. While self-supervised learning (SSL) can leverage large unlabeled datasets, learned generi…

Emergent musical properties of a transformer under contrastive self-supervised learning
Yuexuan Kong, Gabriel Meseguer-Brocal, Vincent Lostanlen, Mathieu Lagrange, Romain Hennequin
https://arxiv.org/abs/2506.23873

Emergent musical properties of a transformer under contrastive self-supervised learning
In music information retrieval (MIR), contrastive self-supervised learning for general-purpose representation models is effective for global tasks such as automatic tagging. However, for local tasks such as chord estimation, it is widely assumed that contrastively trained general-purpose self-supervised models are inadequate and that more sophisticated SSL is necessary; e.g., masked modeling. Our paper challenges this assumption by revealing the potential of contrastive SSL paired with a transf…

Synthetic Speech Source Tracing using Metric Learning
Dimitrios Koutsianos, Stavros Zacharopoulos, Yannis Panagakis, Themos Stafylakis
https://arxiv.org/abs/2506.02590

Synthetic Speech Source Tracing using Metric Learning
This paper addresses source tracing in synthetic speech-identifying generative systems behind manipulated audio via speaker recognition-inspired pipelines. While prior work focuses on spoofing detection, source tracing lacks robust solutions. We evaluate two approaches: classification-based and metric-learning. We tested our methods on the MLAADv5 benchmark using ResNet and self-supervised learning (SSL) backbones. The results show that ResNet achieves competitive performance with the metric le…

Speech Quality Assessment Model Based on Mixture of Experts: System-Level Performance Enhancement and Utterance-Level Challenge Analysis
Xintong Hu, Yixuan Chen, Rui Yang, Wenxiang Guo, Changhao Pan
https://arxiv.org/abs/2507.06116

Speech Quality Assessment Model Based on Mixture of Experts: System-Level Performance Enhancement and Utterance-Level Challenge Analysis
Automatic speech quality assessment plays a crucial role in the development of speech synthesis systems, but existing models exhibit significant performance variations across different granularity levels of prediction tasks. This paper proposes an enhanced MOS prediction system based on self-supervised learning speech models, incorporating a Mixture of Experts (MoE) classification head and utilizing synthetic data from multiple commercial generation models for data augmentation. Our method buil…

StruMamba3D: Exploring Structural Mamba for Self-supervised Point Cloud Representation Learning
Chuxin Wang, Yixin Zha, Wenfei Yang, Tianzhu Zhang
https://arxiv.org/abs/2506.21541

StruMamba3D: Exploring Structural Mamba for Self-supervised Point Cloud Representation Learning
Recently, Mamba-based methods have demonstrated impressive performance in point cloud representation learning by leveraging State Space Model (SSM) with the efficient context modeling ability and linear complexity. However, these methods still face two key issues that limit the potential of SSM: Destroying the adjacency of 3D points during SSM processing and failing to retain long-sequence memory as the input length increases in downstream tasks. To address these issues, we propose StruMamba3D,…

Balancing Information Preservation and Disentanglement in Self-Supervised Music Representation Learning
Julia Wilkins, Sivan Ding, Magdalena Fuentes, Juan Pablo Bello
https://arxiv.org/abs/2507.22995

Balancing Information Preservation and Disentanglement in Self-Supervised Music Representation Learning
Recent advances in self-supervised learning (SSL) methods offer a range of strategies for capturing useful representations from music audio without the need for labeled data. While some techniques focus on preserving comprehensive details through reconstruction, others favor semantic structure via contrastive objectives. Few works examine the interaction between these paradigms in a unified SSL framework. In this work, we propose a multi-view SSL framework for disentangling music audio represen…

Efficient Learning for Product Attributes with Compact Multimodal Models
Mandar Kulkarni
https://arxiv.org/abs/2507.19679 https://arxiv.org/pdf/2507.19679

Efficient Learning for Product Attributes with Compact Multimodal Models
Image-based product attribute prediction in e-commerce is a crucial task with numerous applications. The supervised fine-tuning of Vision Language Models (VLMs) faces significant scale challenges due to the cost of manual or API based annotation. In this paper, we investigate label-efficient semi-supervised fine-tuning strategies for compact VLMs (2B-3B parameters) that leverage unlabeled product listings through Direct Preference Optimization (DPO). Beginning with a small, API-based, annotated…

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[1/4]:
- CPCL: Cross-Modal Prototypical Contrastive Learning for Weakly Supervised Text-based Person Retri...
Xinpeng Zhao, Yanwei Zheng, Chuanlin Lan, Xiaowei Zhang, Bowen Huang, Jibin Yang, Dongxiao Yu

RECA-PD: A Robust Explainable Cross-Attention Method for Speech-based Parkinson's Disease Classification
Terry Yi Zhong, Cristian Tejedor-Garcia, Martha Larson, Bastiaan R. Bloem
https://arxiv.org/abs/2507.03594

RECA-PD: A Robust Explainable Cross-Attention Method for Speech-based Parkinson's Disease Classification
Parkinson's Disease (PD) affects over 10 million people globally, with speech impairments often preceding motor symptoms by years, making speech a valuable modality for early, non-invasive detection. While recent deep-learning models achieve high accuracy, they typically lack the explainability required for clinical use. To address this, we propose RECA-PD, a novel, robust, and explainable cross-attention architecture that combines interpretable speech features with self-supervised representati…

Scaling Self-Supervised Representation Learning for Symbolic Piano Performance
Louis Bradshaw, Honglu Fan, Alexander Spangher, Stella Biderman, Simon Colton
https://arxiv.org/abs/2506.23869

Scaling Self-Supervised Representation Learning for Symbolic Piano Performance
We study the capabilities of generative autoregressive transformer models trained on large amounts of symbolic solo-piano transcriptions. After first pretraining on approximately 60,000 hours of music, we use a comparatively smaller, high-quality subset, to finetune models to produce musical continuations, perform symbolic classification tasks, and produce general-purpose contrastive MIDI embeddings by adapting the SimCLR framework to symbolic music. When evaluating piano continuation coherence…