Tootfinder

Learning Representations in Video Game Agents with Supervised Contrastive Imitation Learning
Carlos Celemin, Joseph Brennan, Pierluigi Vito Amadori, Tim Bradley
https://arxiv.org/abs/2509.11880

Learning Representations in Video Game Agents with Supervised Contrastive Imitation Learning
This paper introduces a novel application of Supervised Contrastive Learning (SupCon) to Imitation Learning (IL), with a focus on learning more effective state representations for agents in video game environments. The goal is to obtain latent representations of the observations that capture better the action-relevant factors, thereby modeling better the cause-effect relationship from the observations that are mapped to the actions performed by the demonstrator, for example, the player jumps wh…

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

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

GTA: Supervised-Guided Reinforcement Learning for Text Classification with Large Language Models
Min Zeng, Jinfei Sun, Xueyou Luo, Caiquan Liu, Shiqi Zhang, Li Xie, Xiaoxin Chen
https://arxiv.org/abs/2509.12108

GTA: Supervised-Guided Reinforcement Learning for Text Classification with Large Language Models
In natural language processing tasks, pure reinforcement learning (RL) fine-tuning methods often suffer from inefficient exploration and slow convergence; while supervised fine-tuning (SFT) methods, although efficient in training, have limited performance ceiling and less solid theoretical foundation compared to RL. To address efficiency-capability trade-off, we propose the Guess-Think-Answer (GTA) framework that combines the efficiency of SFT with the capability gains of RL in a unified traini…

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

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

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

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

Data-Efficient Psychiatric Disorder Detection via Self-supervised Learning on Frequency-enhanced Brain Networks
Mujie Liu, Mengchu Zhu, Qichao Dong, Ting Dang, Jiangang Ma, Jing Ren, Feng Xia
https://arxiv.org/abs/2509.10524

Data-Efficient Psychiatric Disorder Detection via Self-supervised Learning on Frequency-enhanced Brain Networks
Psychiatric disorders involve complex neural activity changes, with functional magnetic resonance imaging (fMRI) data serving as key diagnostic evidence. However, data scarcity and the diverse nature of fMRI information pose significant challenges. While graph-based self-supervised learning (SSL) methods have shown promise in brain network analysis, they primarily focus on time-domain representations, often overlooking the rich information embedded in the frequency domain. To overcome these lim…

Weakly Supervised Vulnerability Localization via Multiple Instance Learning
Wenchao Gu, Yupan Chen, Yanlin Wang, Hongyu Zhang, Cuiyun Gao, Michael R. Lyu
https://arxiv.org/abs/2509.11312

Weakly Supervised Vulnerability Localization via Multiple Instance Learning
Software vulnerability detection has emerged as a significant concern in the field of software security recently, capturing the attention of numerous researchers and developers. Most previous approaches focus on coarse-grained vulnerability detection, such as at the function or file level. However, the developers would still encounter the challenge of manually inspecting a large volume of code inside the vulnerable function to identify the specific vulnerable statements for modification, indica…

DeePAQ: A Perceptual Audio Quality Metric Based On Foundational Models and Weakly Supervised Learning
Guanxin Jiang, Andreas Brendel, Pablo M. Delgado, J\"urgen Herre
https://arxiv.org/abs/2510.12326

DeePAQ: A Perceptual Audio Quality Metric Based On Foundational Models and Weakly Supervised Learning
This paper presents the Deep learning-based Perceptual Audio Quality metric (DeePAQ) for evaluating general audio quality. Our approach leverages metric learning together with the music foundation model MERT, guided by surrogate labels, to construct an embedding space that captures distortion intensity in general audio. To the best of our knowledge, DeePAQ is the first in the general audio quality domain to leverage weakly supervised labels and metric learning for fine-tuning a music foundation…

Learning Majority-to-Minority Transformations with MMD and Triplet Loss for Imbalanced Classification
Suman Cha, Hyunjoong Kim
https://arxiv.org/abs/2509.11511 https://

Learning Majority-to-Minority Transformations with MMD and Triplet Loss for Imbalanced Classification
Class imbalance in supervised classification often degrades model performance by biasing predictions toward the majority class, particularly in critical applications such as medical diagnosis and fraud detection. Traditional oversampling techniques, including SMOTE and its variants, generate synthetic minority samples via local interpolation but fail to capture global data distributions in high-dimensional spaces. Deep generative models based on GANs offer richer distribution modeling yet suffe…

Learning from Uncertain Similarity and Unlabeled Data
Meng Wei, Zhongnian Li, Peng Ying, Xinzheng Xu
https://arxiv.org/abs/2509.11984 https://arxiv.org/pdf…

Learning from Uncertain Similarity and Unlabeled Data
Existing similarity-based weakly supervised learning approaches often rely on precise similarity annotations between data pairs, which may inadvertently expose sensitive label information and raise privacy risks. To mitigate this issue, we propose Uncertain Similarity and Unlabeled Learning (USimUL), a novel framework where each similarity pair is embedded with an uncertainty component to reduce label leakage. In this paper, we propose an unbiased risk estimator that learns from uncertain simil…

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

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

SS-DPPN: A self-supervised dual-path foundation model for the generalizable cardiac audio representation
Ummy Maria Muna, Md Mehedi Hasan Shawon, Md Jobayer, Sumaiya Akter, Md Rakibul Hasan, Md. Golam Rabiul Alam
https://arxiv.org/abs/2510.10719

SS-DPPN: A self-supervised dual-path foundation model for the generalizable cardiac audio representation
The automated analysis of phonocardiograms is vital for the early diagnosis of cardiovascular disease, yet supervised deep learning is often constrained by the scarcity of expert-annotated data. In this paper, we propose the Self-Supervised Dual-Path Prototypical Network (SS-DPPN), a foundation model for cardiac audio representation and classification from unlabeled data. The framework introduces a dual-path contrastive learning based architecture that simultaneously processes 1D waveforms and …

Reasoning Pattern Matters: Learning to Reason without Human Rationales
Chaoxu Pang, Yixuan Cao, Ping Luo
https://arxiv.org/abs/2510.12643 https://arxiv.org…

Reasoning Pattern Matters: Learning to Reason without Human Rationales
Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities under the widely adopted SFT+RLVR paradigm, which first performs Supervised Fine-Tuning (SFT) on human-annotated reasoning trajectories (rationales) to establish initial reasoning behaviors, then applies Reinforcement Learning with Verifiable Rewards (RLVR) to optimize the model using verifiable signals without golden rationales. However, annotating high-quality rationales for the SFT stage remains prohibitively ex…

Self-Supervised Representation Learning with ID-Content Modality Alignment for Sequential Recommendation
Donglin Zhou, Weike Pan, Zhong Ming
https://arxiv.org/abs/2510.10556 htt…

Self-Supervised Representation Learning with ID-Content Modality Alignment for Sequential Recommendation
Sequential recommendation (SR) models often capture user preferences based on the historically interacted item IDs, which usually obtain sub-optimal performance when the interaction history is limited. Content-based sequential recommendation has recently emerged as a promising direction that exploits items' textual and visual features to enhance preference learning. However, there are still three key challenges: (i) how to reduce the semantic gap between different content modality representatio…

Adapting Medical Vision Foundation Models for Volumetric Medical Image Segmentation via Active Learning and Selective Semi-supervised Fine-tuning
Jin Yang, Daniel S. Marcus, Aristeidis Sotiras
https://arxiv.org/abs/2509.10784

Adapting Medical Vision Foundation Models for Volumetric Medical Image Segmentation via Active Learning and Selective Semi-supervised Fine-tuning
Medical Vision Foundation Models (Med-VFMs) have superior capabilities of interpreting medical images due to the knowledge learned from self-supervised pre-training with extensive unannotated images. To improve their performance on adaptive downstream evaluations, especially segmentation, a few samples from target domains are selected randomly for fine-tuning them. However, there lacks works to explore the way of adapting Med-VFMs to achieve the optimal performance on target domains efficiently…

Learning kernels with quantum optical circuits
A. Mandilara, A. D. Papadopoulos, D. Syvridis
https://arxiv.org/abs/2509.12072 https://arxiv.org/pdf/2509.12…

Learning kernels with quantum optical circuits
Support Vector Machines (SVMs) are a cornerstone of supervised learning, widely used for data classification. A central component of their success lies in kernel functions, which enable efficient computation of inner products in high-dimensional feature spaces. Recent years have seen growing interest in leveraging quantum circuits --both qubit-based and quantum optical-- for computing kernel matrices, with ongoing research exploring potential quantum advantages. In this work, we investigate two…

NeuroStrike: Neuron-Level Attacks on Aligned LLMs
Lichao Wu, Sasha Behrouzi, Mohamadreza Rostami, Maximilian Thang, Stjepan Picek, Ahmad-Reza Sadeghi
https://arxiv.org/abs/2509.11864

NeuroStrike: Neuron-Level Attacks on Aligned LLMs
Safety alignment is critical for the ethical deployment of large language models (LLMs), guiding them to avoid generating harmful or unethical content. Current alignment techniques, such as supervised fine-tuning and reinforcement learning from human feedback, remain fragile and can be bypassed by carefully crafted adversarial prompts. Unfortunately, such attacks rely on trial and error, lack generalizability across models, and are constrained by scalability and reliability. This paper presen…

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

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

IF-D: A High-Frequency, General-Purpose Inertial Foundation Dataset for Self-Supervised Learning
Patrick Ferreira, Paula Costa
https://arxiv.org/abs/2510.09539 https://

IF-D: A High-Frequency, General-Purpose Inertial Foundation Dataset for Self-Supervised Learning
We present IF-D, a large-scale inertial dataset designed to enable self-supervised and foundational learning for IMU time series. IF-D comprises continuous, long-duration multichannel recordings (accelerometer, gyroscope, magnetometer) sampled at 200Hz using a UM7 IMU mounted inside a 3D-printed spherical enclosure that promotes diverse, free rotations during vehicle traversal. The collection spans approximately 135 minutes of recording, yielding around 1.6 million samples across nine sensor ch…

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

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

A Systematic Evaluation of Self-Supervised Learning for Label-Efficient Sleep Staging with Wearable EEG
Emilio Estevan, Mar\'ia Sierra-Torralba, Eduardo L\'opez-Larraz, Luis Montesano
https://arxiv.org/abs/2510.07960

A Systematic Evaluation of Self-Supervised Learning for Label-Efficient Sleep Staging with Wearable EEG
Wearable EEG devices have emerged as a promising alternative to polysomnography (PSG). As affordable and scalable solutions, their widespread adoption results in the collection of massive volumes of unlabeled data that cannot be analyzed by clinicians at scale. Meanwhile, the recent success of deep learning for sleep scoring has relied on large annotated datasets. Self-supervised learning (SSL) offers an opportunity to bridge this gap, leveraging unlabeled signals to address label scarcity and …

Identification of Gamma Ray Pulsar Candidates in the \emph{Fermi}-LAT 4FGL-DR4 Unassociated Sources Using Supervised Machine Learning
A. Pathania, K. K. Singh, S. K. Singh, A. Tolamatti, B. B. Singh, K. K. Yadav
https://arxiv.org/abs/2510.08654

Identification of Gamma Ray Pulsar Candidates in the \emph{Fermi}-LAT 4FGL-DR4 Unassociated Sources Using Supervised Machine Learning
The Large Area Telescope (LAT) on board the \emph{Fermi} Gamma-ray Space Telescope has been continuously providing good quality survey data of the entire sky in the high energy range from 30 MeV to 500 GeV and above since August 2008. A succession of gamma-ray source catalogs is published after a comprehensive analysis of the \emph{Fermi}--LAT data. The most recent release of data in the fourth \emph{Fermi}--LAT catalog of gamma-ray sources (4FGL-DR4), based on the first 14 years of obser…

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

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

Automatic Music Sample Identification with Multi-Track Contrastive Learning
Alain Riou, Joan Serr\`a, Yuki Mitsufuji
https://arxiv.org/abs/2510.11507 https://

Automatic Music Sample Identification with Multi-Track Contrastive Learning
Sampling, the technique of reusing pieces of existing audio tracks to create new music content, is a very common practice in modern music production. In this paper, we tackle the challenging task of automatic sample identification, that is, detecting such sampled content and retrieving the material from which it originates. To do so, we adopt a self-supervised learning approach that leverages a multi-track dataset to create positive pairs of artificial mixes, and design a novel contrastive lear…

Multi Anatomy X-Ray Foundation Model
Nishank Singla, Krisztian Koos, Farzin Haddadpour, Amin Honarmandi Shandiz, Lovish Chum, Xiaojian Xu, Qing Jin, Erhan Bas
https://arxiv.org/abs/2509.12146

Multi Anatomy X-Ray Foundation Model
X-ray imaging is a ubiquitous in radiology, yet most existing AI foundation models are limited to chest anatomy and fail to generalize across broader clinical tasks. In this work, we introduce XR-0, the multi-anatomy X-ray foundation model using self-supervised learning on a large, private dataset of 1.15 million images spanning diverse anatomical regions and evaluated across 12 datasets and 20 downstream tasks, including classification, retrieval, segmentation, localization, visual grounding, …

Few-shot Molecular Property Prediction: A Survey
Zeyu Wang, Tianyi Jiang, Huanchang Ma, Yao Lu, Xiaoze Bao, Shanqing Yu, Qi Xuan, Shirui Pan, Xin Zheng
https://arxiv.org/abs/2510.08900

Few-shot Molecular Property Prediction: A Survey
AI-assisted molecular property prediction has become a promising technique in early-stage drug discovery and materials design in recent years. However, due to high-cost and complex wet-lab experiments, real-world molecules usually experience the issue of scarce annotations, leading to limited labeled data for effective supervised AI model learning. In light of this, few-shot molecular property prediction (FSMPP) has emerged as an expressive paradigm that enables learning from only a few labeled…

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

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

Interpretable Generative and Discriminative Learning for Multimodal and Incomplete Clinical Data
Albert Belenguer-Llorens, Carlos Sevilla-Salcedo, Janaina Mourao-Miranda, Vanessa G\'omez-Verdejo
https://arxiv.org/abs/2510.09513

Interpretable Generative and Discriminative Learning for Multimodal and Incomplete Clinical Data
Real-world clinical problems are often characterized by multimodal data, usually associated with incomplete views and limited sample sizes in their cohorts, posing significant limitations for machine learning algorithms. In this work, we propose a Bayesian approach designed to efficiently handle these challenges while providing interpretable solutions. Our approach integrates (1) a generative formulation to capture cross-view relationships with a semi-supervised strategy, and (2) a discriminati…

MAE-SAM2: Mask Autoencoder-Enhanced SAM2 for Clinical Retinal Vascular Leakage Segmentation
Xin Xing, Irmak Karaca, Samira Badrloo, Quan Dong Nguyen, Mahadevan Subramaniam
https://arxiv.org/abs/2509.10554

MAE-SAM2: Mask Autoencoder-Enhanced SAM2 for Clinical Retinal Vascular Leakage Segmentation
We propose MAE-SAM2, a novel foundation model for retinal vascular leakage segmentation on fluorescein angiography images. Due to the small size and dense distribution of the leakage areas, along with the limited availability of labeled clinical data, this presents a significant challenge for segmentation tasks. Our approach integrates a Self-Supervised learning (SSL) strategy, Masked Autoencoder (MAE), with SAM2. In our implementation, we explore different loss functions and conclude a task-sp…

PhishSSL: Self-Supervised Contrastive Learning for Phishing Website Detection
Wenhao Li, Selvakumar Manickam, Yung-Wey Chong, Shankar Karuppayah, Priyadarsi Nanda, Binyong Li
https://arxiv.org/abs/2510.05900

PhishSSL: Self-Supervised Contrastive Learning for Phishing Website Detection
Phishing websites remain a persistent cybersecurity threat by mimicking legitimate sites to steal sensitive user information. Existing machine learning-based detection methods often rely on supervised learning with labeled data, which not only incurs substantial annotation costs but also limits adaptability to novel attack patterns. To address these challenges, we propose PhishSSL, a self-supervised contrastive learning framework that eliminates the need for labeled phishing data during trainin…

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[1/5]:
- Enhancing Representations through Heterogeneous Self-Supervised Learning
Zhong-Yu Li, Bo-Wen Yin, Yongxiang Liu, Li Liu, Ming-Ming Cheng

Multitask finetuning and acceleration of chemical pretrained models for small molecule drug property prediction
Matthew Adrian, Yunsie Chung, Kevin Boyd, Saee Paliwal, Srimukh Prasad Veccham, Alan C. Cheng
https://arxiv.org/abs/2510.12719

Multitask finetuning and acceleration of chemical pretrained models for small molecule drug property prediction
Chemical pretrained models, sometimes referred to as foundation models, are receiving considerable interest for drug discovery applications. The general chemical knowledge extracted from self-supervised training has the potential to improve predictions for critical drug discovery endpoints, including on-target potency and ADMET properties. Multi-task learning has previously been successfully leveraged to improve predictive models. Here, we show that enabling multitasking in finetuning of chemic…

Improving Out-of-Domain Audio Deepfake Detection via Layer Selection and Fusion of SSL-Based Countermeasures
Pierre Serrano, Rapha\"el Duroselle, Florian Angulo, Jean-Fran\c{c}ois Bonastre, Olivier Boeffard
https://arxiv.org/abs/2509.12003

Improving Out-of-Domain Audio Deepfake Detection via Layer Selection and Fusion of SSL-Based Countermeasures
Audio deepfake detection systems based on frozen pre-trained self-supervised learning (SSL) encoders show a high level of performance when combined with layer-weighted pooling methods, such as multi-head factorized attentive pooling (MHFA). However, they still struggle to generalize to out-of-domain (OOD) conditions. We tackle this problem by studying the behavior of six different pre-trained SSLs, on four different test corpora. We perform a layer-by-layer analysis to determine which layers co…

Latent Representation Learning in Heavy-Ion Collisions with MaskPoint Transformer
Jing-Zong Zhang, Shuang Guo, Li-Lin Zhu, Lingxiao Wang, Guo-Liang Ma
https://arxiv.org/abs/2510.06691

Latent Representation Learning in Heavy-Ion Collisions with MaskPoint Transformer
A central challenge in high-energy nuclear physics is to extract informative features from the high-dimensional final-state data of heavy-ion collisions (HIC) in order to enable reliable downstream analyses. Traditional approaches often rely on selected observables, which may miss subtle but physically relevant structures in the data. To address this, we introduce a Transformer-based autoencoder trained with a two-stage paradigm: self-supervised pre-training followed by supervised fine-tuning. …

Organic geochemical evidence for life in Archean rocks identified by pyrolysis–GC–MS and supervised machine learning: #life in ancient rocks: https://gizmodo.com/ai-uncovers-evidence-of-life-in-3-3-billion-year-old-rocks-2000687539 / https://www.reuters.com/science/new-method-spots-signs-earths-primordial-life-ancient-rocks-2025-11-18/ - a machine-learning-enhanced approach to chemical analysis is drastically expanding the chemical record of life on Earth, and it could help us find evidence of life on other planets too.

Acoustic Overspecification in Electronic Dance Music Taxonomy
Weilun Xu, Tianhao Dai, Oscar Goudet, Xiaoxuan Wang
https://arxiv.org/abs/2509.11474 https://…

Acoustic Overspecification in Electronic Dance Music Taxonomy
Electronic Dance Music (EDM) classification typically relies on industry-defined taxonomies with numerous subgenres, yet the acoustic basis for these distinctions remains unclear. Current approaches use supervised learning with prescribed genre labels, assuming their validity without systematic evaluation. In this paper, we propose an unsupervised approach to discover the natural acoustic structure of EDM independent of commercial labels. Our method combines novel tempogram-based features captu…

From <Answer> to <Think>: Multidimensional Supervision of Reasoning Process for LLM Optimization
Beining Wang, Weihang Su, Hongtao Tian, Tao Yang, Yujia Zhou, Ting Yao, Qingyao Ai, Yiqun Liu
https://arxiv.org/abs/2510.11457

From to : Multidimensional Supervision of Reasoning Process for LLM Optimization
Improving the multi-step reasoning ability of Large Language Models (LLMs) is a critical yet challenging task. The dominant paradigm, outcome-supervised reinforcement learning (RLVR), rewards only correct final answers, often propagating flawed reasoning and suffering from sparse reward signals. While process-level reward models (PRMs) provide denser, step-by-step feedback, they lack generalizability and interpretability, requiring task-specific segmentation of the reasoning process. To this en…

Network Traffic Classification Using Self-Supervised Learning and Confident Learning
Ehsan Eslami, Walaa Hamouda
https://arxiv.org/abs/2509.23522 https://a…

Network Traffic Classification Using Self-Supervised Learning and Confident Learning
Network traffic classification (NTC) is vital for efficient network management, security, and performance optimization, particularly with 5G/6G technologies. Traditional methods, such as deep packet inspection (DPI) and port-based identification, struggle with the rise of encrypted traffic and dynamic port allocations. Supervised learning methods provide viable alternatives but rely on large labeled datasets, which are difficult to acquire given the diversity and volume of network traffic. Mean…

A Warm-basis Method for Bridging Learning and Iteration: a Case Study in Fluorescence Molecular Tomography
Ruchi Guo, Jiahua Jiang, Bangti Jin, Wuwei Ren, Jianru Zhang
https://arxiv.org/abs/2510.05926 …

A Warm-basis Method for Bridging Learning and Iteration: a Case Study in Fluorescence Molecular Tomography
Fluorescence Molecular Tomography (FMT) is a widely used non-invasive optical imaging technology in biomedical research. It usually faces significant accuracy challenges in depth reconstruction, and conventional iterative methods struggle with poor $z$-resolution even with advanced regularization. Supervised learning approaches can improve recovery accuracy but rely on large, high-quality paired training dataset that is often impractical to acquire in practice. This naturally raises the questio…

Residual-Informed Learning of Solutions to Algebraic Loops
Felix Brandt, Andreas Heuermann, Philip Hannebohm, Bernhard Bachmann
https://arxiv.org/abs/2510.09317 https://

Residual-Informed Learning of Solutions to Algebraic Loops
This paper presents a residual-informed machine learning approach for replacing algebraic loops in equation-based Modelica models with neural network surrogates. A feedforward neural network is trained using the residual (error) of the algebraic loop directly in its loss function, eliminating the need for a supervised dataset. This training strategy also resolves the issue of ambiguous solutions, allowing the surrogate to converge to a consistent solution rather than averaging multiple valid on…

Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation
Wenyao Zhang, Hongsi Liu, Bohan Li, Jiawei He, Zekun Qi, Yunnan Wang, Shengyang Zhao, Xinqiang Yu, Wenjun Zeng, Xin Jin
https://arxiv.org/abs/2510.09320

Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation
Current self-supervised monocular depth estimation (MDE) approaches encounter performance limitations due to insufficient semantic-spatial knowledge extraction. To address this challenge, we propose Hybrid-depth, a novel framework that systematically integrates foundation models (e.g., CLIP and DINO) to extract visual priors and acquire sufficient contextual information for MDE. Our approach introduces a coarse-to-fine progressive learning framework: 1) Firstly, we aggregate multi-grained featu…

An Investigation into the Performance of Non-Contrastive Self-Supervised Learning Methods for Network Intrusion Detection
Hamed Fard, Tobias Schalau, Gerhard Wunder
https://arxiv.org/abs/2510.02349

An Investigation into the Performance of Non-Contrastive Self-Supervised Learning Methods for Network Intrusion Detection
Network intrusion detection, a well-explored cybersecurity field, has predominantly relied on supervised learning algorithms in the past two decades. However, their limitations in detecting only known anomalies prompt the exploration of alternative approaches. Motivated by the success of self-supervised learning in computer vision, there is a rising interest in adapting this paradigm for network intrusion detection. While prior research mainly delved into contrastive self-supervised methods, th…

VarCoNet: A variability-aware self-supervised framework for functional connectome extraction from resting-state fMRI
Charalampos Lamprou, Aamna Alshehhi, Leontios J. Hadjileontiadis, Mohamed L. Seghier
https://arxiv.org/abs/2510.02120

VarCoNet: A variability-aware self-supervised framework for functional connectome extraction from resting-state fMRI
Accounting for inter-individual variability in brain function is key to precision medicine. Here, by considering functional inter-individual variability as meaningful data rather than noise, we introduce VarCoNet, an enhanced self-supervised framework for robust functional connectome (FC) extraction from resting-state fMRI (rs-fMRI) data. VarCoNet employs self-supervised contrastive learning to exploit inherent functional inter-individual variability, serving as a brain function encoder that ge…

TACTFL: Temporal Contrastive Training for Multi-modal Federated Learning with Similarity-guided Model Aggregation
Guanxiong Sun, Majid Mirmehdi, Zahraa Abdallah, Raul Santos-Rodriguez, Ian Craddock, Telmo de Menezes e Silva Filho
https://arxiv.org/abs/2509.17532

TACTFL: Temporal Contrastive Training for Multi-modal Federated Learning with Similarity-guided Model Aggregation
Real-world federated learning faces two key challenges: limited access to labelled data and the presence of heterogeneous multi-modal inputs. This paper proposes TACTFL, a unified framework for semi-supervised multi-modal federated learning. TACTFL introduces a modality-agnostic temporal contrastive training scheme that conducts representation learning from unlabelled client data by leveraging temporal alignment across modalities. However, as clients perform self-supervised training on heteroge…

RLinf-VLA: A Unified and Efficient Framework for VLA RL Training
Hongzhi Zang, Mingjie Wei, Si Xu, Yongji Wu, Zhen Guo, Yuanqing Wang, Hao Lin, Liangzhi Shi, Yuqing Xie, Zhexuan Xu, Zhihao Liu, Kang Chen, Wenhao Tang, Quanlu Zhang, Weinan Zhang, Chao Yu, Yu Wang
https://arxiv.org/abs/2510.06710

RLinf-VLA: A Unified and Efficient Framework for VLA+RL Training
Recent progress in vision and language foundation models has significantly advanced multimodal understanding, reasoning, and generation, inspiring a surge of interest in extending such capabilities to embodied settings through vision-language-action (VLA) models. Yet, most VLA models are still trained with supervised fine-tuning (SFT), which struggles to generalize under distribution shifts due to error accumulation. Reinforcement learning (RL) offers a promising alternative by directly optimiz…

Contrastive Self-Supervised Learning at the Edge: An Energy Perspective
Fernanda Fam\'a, Roberto Pereira, Charalampos Kalalas, Paolo Dini, Lorena Qendro, Fahim Kawsar, Mohammad Malekzadeh
https://arxiv.org/abs/2510.08374

Contrastive Self-Supervised Learning at the Edge: An Energy Perspective
While contrastive learning (CL) shows considerable promise in self-supervised representation learning, its deployment on resource-constrained devices remains largely underexplored. The substantial computational demands required for training conventional CL frameworks pose a set of challenges, particularly in terms of energy consumption, data availability, and memory usage. We conduct an evaluation of four widely used CL frameworks: SimCLR, MoCo, SimSiam, and Barlow Twins. We focus on the practi…

Unsupervised lexicon learning from speech is limited by representations rather than clustering
Danel Adendorff, Simon Malan, Herman Kamper
https://arxiv.org/abs/2510.09225 https…

Unsupervised lexicon learning from speech is limited by representations rather than clustering
Zero-resource word segmentation and clustering systems aim to tokenise speech into word-like units without access to text labels. Despite progress, the induced lexicons are still far from perfect. In an idealised setting with gold word boundaries, we ask whether performance is limited by the representation of word segments, or by the clustering methods that group them into word-like types. We combine a range of self-supervised speech features (continuous/discrete, frame/word-level) with differe…

Automatic Identification of Magnetospheric Regions using Supervised Machine Learning Models
Narges Ahmadi, Robert Ergun, Xiangning Chu, Alex Chasapis, Victoria Wilder
https://arxiv.org/abs/2510.00190

Automatic Identification of Magnetospheric Regions using Supervised Machine Learning Models
We present an automated approach for identifying magnetospheric regions using supervised machine learning techniques applied to Magnetospheric MultiScale mission data. Our method utilizes ion energy spectra, total magnetic field, total ion temperature, and spacecraft position data to classify five distinct plasma environments: solar wind, magnetosheath, inner magnetosphere, plasma sheet, and lobe regions. The approach combines a convolutional neural network (CNN) for analyzing ion energy spectr…

Do We Really Need SFT? Prompt-as-Policy over Knowledge Graphs for Cold-start Next POI Recommendation
Jinze Wang, Lu Zhang, Yiyang Cui, Zhishu Shen, Xingjun Ma, Jiong Jin, Tiehua Zhang
https://arxiv.org/abs/2510.08012

Do We Really Need SFT? Prompt-as-Policy over Knowledge Graphs for Cold-start Next POI Recommendation
Next point-of-interest (POI) recommendation is crucial for smart urban services such as tourism, dining, and transportation, yet most approaches struggle under cold-start conditions where user-POI interactions are sparse. Recent efforts leveraging large language models (LLMs) address this challenge through either supervised fine-tuning (SFT) or in-context learning (ICL). However, SFT demands costly annotations and fails to generalize to inactive users, while static prompts in ICL cannot adapt t…

TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance
Jianhui Yang, Yiming Jin, Pengkun Jiao, Chenhe Dong, Zerui Huang, Shaowei Yao, Xiaojiang Zhou, Dan Ou, Haihong Tang
https://arxiv.org/abs/2510.08048

TaoSR-AGRL: Adaptive Guided Reinforcement Learning Framework for E-commerce Search Relevance
Query-product relevance prediction is fundamental to e-commerce search and has become even more critical in the era of AI-powered shopping, where semantic understanding and complex reasoning directly shape the user experience and business conversion. Large Language Models (LLMs) enable generative, reasoning-based approaches, typically aligned via supervised fine-tuning (SFT) or preference optimization methods like Direct Preference Optimization (DPO). However, the increasing complexity of busin…

Agent Learning via Early Experience
Kai Zhang, Xiangchao Chen, Bo Liu, Tianci Xue, Zeyi Liao, Zhihan Liu, Xiyao Wang, Yuting Ning, Zhaorun Chen, Xiaohan Fu, Jian Xie, Yuxuan Sun, Boyu Gou, Qi Qi, Zihang Meng, Jianwei Yang, Ning Zhang, Xian Li, Ashish Shah, Dat Huynh, Hengduo Li, Zi Yang, Sara Cao, Lawrence Jang, Shuyan Zhou, Jiacheng Zhu, Huan Sun, Jason Weston, Yu Su, Yifan Wu

Agent Learning via Early Experience
A long-term goal of language agents is to learn and improve through their own experience, ultimately outperforming humans in complex, real-world tasks. However, training agents from experience data with reinforcement learning remains difficult in many environments, which either lack verifiable rewards (e.g., websites) or require inefficient long-horizon rollouts (e.g., multi-turn tool use). As a result, most current agents rely on supervised fine-tuning on expert data, which is challenging to s…

Adapting HFMCA to Graph Data: Self-Supervised Learning for Generalizable fMRI Representations
Jakub Frac, Alexander Schmatz, Qiang Li, Guido Van Wingen, Shujian Yu
https://arxiv.org/abs/2510.05177

Adapting HFMCA to Graph Data: Self-Supervised Learning for Generalizable fMRI Representations
Functional magnetic resonance imaging (fMRI) analysis faces significant challenges due to limited dataset sizes and domain variability between studies. Traditional self-supervised learning methods inspired by computer vision often rely on positive and negative sample pairs, which can be problematic for neuroimaging data where defining appropriate contrasts is non-trivial. We propose adapting a recently developed Hierarchical Functional Maximal Correlation Algorithm (HFMCA) to graph-structured f…

Bilevel optimization for learning hyperparameters: Application to solving PDEs and inverse problems with Gaussian processes
Nicholas H. Nelsen, Houman Owhadi, Andrew M. Stuart, Xianjin Yang, Zongren Zou
https://arxiv.org/abs/2510.05568

Bilevel optimization for learning hyperparameters: Application to solving PDEs and inverse problems with Gaussian processes
Methods for solving scientific computing and inference problems, such as kernel- and neural network-based approaches for partial differential equations (PDEs), inverse problems, and supervised learning tasks, depend crucially on the choice of hyperparameters. Specifically, the efficacy of such methods, and in particular their accuracy, stability, and generalization properties, strongly depends on the choice of hyperparameters. While bilevel optimization offers a principled framework for hyperpa…

Self-supervised Physics-guided Model with Implicit Representation Regularization for Fast MRI Reconstruction
Jingran Xu, Yuanyuan Liu, Yanjie Zhu
https://arxiv.org/abs/2510.06611

Self-supervised Physics-guided Model with Implicit Representation Regularization for Fast MRI Reconstruction
Magnetic Resonance Imaging (MRI) is a vital clinical diagnostic tool, yet its widespread application is limited by prolonged scan times. Fast MRI reconstruction techniques effectively reduce acquisition duration by reconstructing high-fidelity MR images from undersampled k-space data. In recent years, deep learning-based methods have demonstrated remarkable progress in this field, with self-supervised and unsupervised learning approaches proving particularly valuable in scenarios where fully sa…

Supervised Machine Learning for Predicting Open Quantum System Dynamics and Detecting Non-Markovian Memory Effects
Ali Abu-Nada, Subhashish Banerjee
https://arxiv.org/abs/2509.22758

Supervised Machine Learning for Predicting Open Quantum System Dynamics and Detecting Non-Markovian Memory Effects
We present a \emph{novel} and scalable supervised machine learning framework to predict open-quantum system dynamics and detect non-Markovian memory using only local ancilla measurements. A system qubit is coherently coupled to an ancilla via a symmetric XY Hamiltonian; the ancilla interacts with a noisy environment and is the only qubit we measure. A feedforward neural network, trained on short sliding windows of supplementary data from the past, forecasts the observable system $\langle Z_{(S)…

Bridged Clustering for Representation Learning: Semi-Supervised Sparse Bridging
Patrick Peixuan Ye, Chen Shani, Ellen Vitercik
https://arxiv.org/abs/2510.07182 https://

Bridged Clustering for Representation Learning: Semi-Supervised Sparse Bridging
We introduce Bridged Clustering, a semi-supervised framework to learn predictors from any unpaired input $X$ and output $Y$ dataset. Our method first clusters $X$ and $Y$ independently, then learns a sparse, interpretable bridge between clusters using only a few paired examples. At inference, a new input $x$ is assigned to its nearest input cluster, and the centroid of the linked output cluster is returned as the prediction $\hat{y}$. Unlike traditional SSL, Bridged Clustering explicitly levera…

Mouse-Guided Gaze: Semi-Supervised Learning of Intention-Aware Representations for Reading Detection
Seongsil Heo, Roberto Manduchi
https://arxiv.org/abs/2509.19574 https://

Mouse-Guided Gaze: Semi-Supervised Learning of Intention-Aware Representations for Reading Detection
Understanding user intent during magnified reading is critical for accessible interface design. Yet magnification collapses visual context and forces continual viewport dragging, producing fragmented, noisy gaze and obscuring reading intent. We present a semi-supervised framework that learns intention-aware gaze representations by leveraging mouse trajectories as weak supervision. The model is first pretrained to predict mouse velocity from unlabeled gaze, then fine-tuned to classify reading ve…

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 …

Self-supervised learning for phase retrieval
Victor Sechaud (Phys-ENS), Patrice Abry (Phys-ENS), Laurent Jacques (ICTEAM), Juli\'an Tachella (Phys-ENS, CNRS)
https://arxiv.org/abs/2509.26203

Self-supervised learning for phase retrieval
In recent years, deep neural networks have emerged as a solution for inverse imaging problems. These networks are generally trained using pairs of images: one degraded and the other of high quality, the latter being called 'ground truth'. However, in medical and scientific imaging, the lack of fully sampled data limits supervised learning. Recent advances have made it possible to reconstruct images from measurement data alone, eliminating the need for references. However, these methods remain l…

Equivariant Splitting: Self-supervised learning from incomplete data
Victor Sechaud, J\'er\'emy Scanvic, Quentin Barth\'elemy, Patrice Abry, Juli\'an Tachella
https://arxiv.org/abs/2510.00929

Equivariant Splitting: Self-supervised learning from incomplete data
Self-supervised learning for inverse problems allows to train a reconstruction network from noise and/or incomplete data alone. These methods have the potential of enabling learning-based solutions when obtaining ground-truth references for training is expensive or even impossible. In this paper, we propose a new self-supervised learning strategy devised for the challenging setting where measurements are observed via a single incomplete observation model. We introduce a new definition of equiva…

Discriminative Feature Feedback with General Teacher Classes
Omri Bar Oz, Tosca Lechner, Sivan Sabato
https://arxiv.org/abs/2510.07245 https://arxiv.org/pd…

Discriminative Feature Feedback with General Teacher Classes
We study the theoretical properties of the interactive learning protocol Discriminative Feature Feedback (DFF) (Dasgupta et al., 2018). The DFF learning protocol uses feedback in the form of discriminative feature explanations. We provide the first systematic study of DFF in a general framework that is comparable to that of classical protocols such as supervised learning and online learning. We study the optimal mistake bound of DFF in the realizable and the non-realizable settings, and obtain …

Latent Multi-view Learning for Robust Environmental Sound Representations
Sivan Sing, Julia Wilkins, Magdalena Fuentes, Juan Pablo Bello
https://arxiv.org/abs/2510.02500 https:/…

Latent Multi-view Learning for Robust Environmental Sound Representations
Self-supervised learning (SSL) approaches, such as contrastive and generative methods, have advanced environmental sound representation learning using unlabeled data. However, how these approaches can complement each other within a unified framework remains relatively underexplored. In this work, we propose a multi-view learning framework that integrates contrastive principles into a generative pipeline to capture sound source and device information. Our method encodes compressed audio latents …

HINT: Helping Ineffective Rollouts Navigate Towards Effectiveness
Xinyi Wang, Jinyi Han, Zishang Jiang, Tingyun Li, Jiaqing Liang, Sihang Jiang, Zhaoqian Dai, Shuguang Ma, Fei Yu, Yanghua Xiao
https://arxiv.org/abs/2510.09388

HINT: Helping Ineffective Rollouts Navigate Towards Effectiveness
Reinforcement Learning (RL) has become a key driver for enhancing the long chain-of-thought (CoT) reasoning capabilities of Large Language Models (LLMs). However, prevalent methods like GRPO often fail when task difficulty exceeds the model's capacity, leading to reward sparsity and inefficient training. While prior work attempts to mitigate this using off-policy data, such as mixing RL with Supervised Fine-Tuning (SFT) or using hints, they often misguide policy updates In this work, we identif…

Accelerated Aggregated D-Optimal Designs for Estimating Main Effects in Black-Box Models
Chih-Yu Chang, Ming-Chung Chang
https://arxiv.org/abs/2510.08465 https://

Accelerated Aggregated D-Optimal Designs for Estimating Main Effects in Black-Box Models
Recent advances in supervised learning have driven growing interest in explaining black-box models, particularly by estimating the effects of input variables on model predictions. However, existing approaches often face key limitations, including poor scalability, sensitivity to out-of-distribution sampling, and instability under correlated features. To address these issues, we propose A2D2E, an $\textbf{E}$stimator based on $\textbf{A}$ccelerated $\textbf{A}$ggregated $\textbf{D}$-Optimal $\te…

Training-Free Group Relative Policy Optimization
Yuzheng Cai, Siqi Cai, Yuchen Shi, Zihan Xu, Lichao Chen, Yulei Qin, Xiaoyu Tan, Gang Li, Zongyi Li, Haojia Lin, Yong Mao, Ke Li, Xing Sun
https://arxiv.org/abs/2510.08191

Training-Free Group Relative Policy Optimization
Recent advances in Large Language Model (LLM) agents have demonstrated their promising general capabilities. However, their performance in specialized real-world domains often degrades due to challenges in effectively integrating external tools and specific prompting strategies. While methods like agentic reinforcement learning have been proposed to address this, they typically rely on costly parameter updates, for example, through a process that uses Supervised Fine-Tuning (SFT) followed by a …

Resolution scaling governs DINOv3 transfer performance in chest radiograph classification
Soroosh Tayebi Arasteh, Mina Shaigan, Christiane Kuhl, Jakob Nikolas Kather, Sven Nebelung, Daniel Truhn
https://arxiv.org/abs/2510.07191

Resolution scaling governs DINOv3 transfer performance in chest radiograph classification
Self-supervised learning (SSL) has advanced visual representation learning, but its value in chest radiography, a high-volume imaging modality with fine-grained findings, remains unclear. Meta's DINOv3 extends earlier SSL models through Gram-anchored self-distillation. Whether these design choices improve transfer learning for chest radiography has not been systematically tested. We benchmarked DINOv3 against DINOv2 and ImageNet initialization across seven datasets (n>814,000). Two representati…

UniAPL: A Unified Adversarial Preference Learning Framework for Instruct-Following
FaQiang Qian, WeiKun Zhang, Ziliang Wang, Kang An, Xuhui Zheng, Liangjian Wen, Mengya Gao, Yong Dai, Yichao Wu
https://arxiv.org/abs/2509.25148

UniAPL: A Unified Adversarial Preference Learning Framework for Instruct-Following
Shaping powerful LLMs to be beneficial and safe is central to AI alignment. We argue that post-training alignment is fundamentally a unified Preference Learning problem, involving two modalities: demonstrated preferences (e.g., Supervised Fine-Tuning, SFT) and comparative preferences (e.g., Reinforcement Learning, RL).The standard sequential pipeline-SFT followed by RL-is flawed due to a critical distributional mismatch: SFT uses static expert data, but as the policy evolves, its generation dis…

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning
Haoyu Zhang, Jiaxian Guo, Yusuke Iwasawa, Yutaka Matsuo
https://arxiv.org/abs/2510.05478

AQA-TTRL: Self-Adaptation in Audio Question Answering with Test-Time Reinforcement Learning
Large Audio Language Models (LALMs) demonstrate impressive general audio understanding, but once deployed, they are static and fail to improve with new real-world audio data. As traditional supervised fine-tuning is costly, we introduce a novel framework for test-time audio understanding, AQA-TTRL, where an LALM evolves on-the-fly using only unlabeled test data. It first generates pseudo-labels from the prediction via majority voting, then optimizes the model via reinforcement learning. To hand…

EMORL-TTS: Reinforcement Learning for Fine-Grained Emotion Control in LLM-based TTS
Haoxun Li, Yu Liu, Yuqing Sun, Hanlei Shi, Leyuan Qu, Taihao Li
https://arxiv.org/abs/2510.05758

EMORL-TTS: Reinforcement Learning for Fine-Grained Emotion Control in LLM-based TTS
Recent LLM-based TTS systems achieve strong quality and zero-shot ability, but lack fine-grained emotional control due to their reliance on discrete speech tokens. Existing approaches either limit emotions to categorical labels or cannot generalize to LLM-based architectures. We propose EMORL-TTS (Fine-grained Emotion-controllable TTS with Reinforcement Learning), a framework that unifies global intensity control in the VAD space with local emphasis regulation. Our method combines supervised fi…

It's not Easy: Applying Supervised Machine Learning to Detect Malicious Extensions in the Chrome Web Store
Ben Rosenzweig, Valentino Dalla Valle, Giovanni Apruzzese, Aurore Fass
https://arxiv.org/abs/2509.21590

It's not Easy: Applying Supervised Machine Learning to Detect Malicious Extensions in the Chrome Web Store
Google Chrome is the most popular Web browser. Users can customize it with extensions that enhance their browsing experience. The most well-known marketplace of such extensions is the Chrome Web Store (CWS). Developers can upload their extensions on the CWS, but such extensions are made available to users only after a vetting process carried out by Google itself. Unfortunately, some malicious extensions bypass such checks, putting the security and privacy of downstream browser extension users a…

One-Token Rollout: Guiding Supervised Fine-Tuning of LLMs with Policy Gradient
Rui Ming, Haoyuan Wu, Shoubo Hu, Zhuolun He, Bei Yu
https://arxiv.org/abs/2509.26313 https://

One-Token Rollout: Guiding Supervised Fine-Tuning of LLMs with Policy Gradient
Supervised fine-tuning (SFT) is the predominant method for adapting large language models (LLMs), yet it often struggles with generalization compared to reinforcement learning (RL). In this work, we posit that this performance disparity stems not just from the loss function, but from a more fundamental difference: SFT learns from a fixed, pre-collected dataset, whereas RL utilizes on-policy data sampled from the current policy. Building on this hypothesis, we introduce one-token rollout (OTR), …

Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspective
Siwei Wang, Yifei Shen, Haoran Sun, Shi Feng, Shang-Hua Teng, Li Dong, Yaru Hao, Wei Chen
https://arxiv.org/abs/2509.22613

Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspective
Recent reinforcement learning (RL) methods have substantially enhanced the planning capabilities of Large Language Models (LLMs), yet the theoretical basis for their effectiveness remains elusive. In this work, we investigate RL's benefits and limitations through a tractable graph-based abstraction, focusing on policy gradient (PG) and Q-learning methods. Our theoretical analyses reveal that supervised fine-tuning (SFT) may introduce co-occurrence-based spurious solutions, whereas RL achieves c…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[4/7]:
- GPS-MTM: Capturing Pattern of Normalcy in GPS-Trajectories with self-supervised learning
Umang Garg, Bowen Zhang, Anantajit Subrahmanya, Chandrakanth Gudavalli, BS Manjunath

Evaluating Self-Supervised Speech Models via Text-Based LLMS
Takashi Maekaku, Keita Goto, Jinchuan Tian, Yusuke Shinohara, Shinji Watanabe
https://arxiv.org/abs/2510.04463 https…

Evaluating Self-Supervised Speech Models via Text-Based LLMS
Self-Supervised Learning (SSL) has gained traction for its ability to learn rich representations with low labeling costs, applicable across diverse downstream tasks. However, assessing the downstream-task performance remains challenging due to the cost of extra training and evaluation. Existing methods for task-agnostic evaluation also require extra training or hyperparameter tuning. We propose a novel evaluation metric using large language models (LLMs). By inputting discrete token sequences a…

SpikeMatch: Semi-Supervised Learning with Temporal Dynamics of Spiking Neural Networks
Jini Yang, Beomseok Oh, Seungryong Kim, Sunok Kim
https://arxiv.org/abs/2509.22581 https:/…

SpikeMatch: Semi-Supervised Learning with Temporal Dynamics of Spiking Neural Networks
Spiking neural networks (SNNs) have recently been attracting significant attention for their biological plausibility and energy efficiency, but semi-supervised learning (SSL) methods for SNN-based models remain underexplored compared to those for artificial neural networks (ANNs). In this paper, we introduce SpikeMatch, the first SSL framework for SNNs that leverages the temporal dynamics through the leakage factor of SNNs for diverse pseudo-labeling within a co-training framework. By utilizing…

AWM: Accurate Weight-Matrix Fingerprint for Large Language Models
Boyi Zeng, Lin Chen, Ziwei He, Xinbing Wang, Zhouhan Lin
https://arxiv.org/abs/2510.06738 https://

AWM: Accurate Weight-Matrix Fingerprint for Large Language Models
Protecting the intellectual property of large language models (LLMs) is crucial, given the substantial resources required for their training. Consequently, there is an urgent need for both model owners and third parties to determine whether a suspect LLM is trained from scratch or derived from an existing base model. However, the intensive post-training processes that models typically undergo-such as supervised fine-tuning, extensive continued pretraining, reinforcement learning, multi-modal ex…

WavJEPA: Semantic learning unlocks robust audio foundation models for raw waveforms
Goksenin Yuksel, Pierre Guetschel, Michael Tangermann, Marcel van Gerven, Kiki van der Heijden
https://arxiv.org/abs/2509.23238

WavJEPA: Semantic learning unlocks robust audio foundation models for raw waveforms
Learning audio representations from raw waveforms overcomes key limitations of spectrogram-based audio representation learning, such as the long latency of spectrogram computation and the loss of phase information. Yet, while self-supervised speech representation learning from raw waveforms has been remarkably successful, these approaches have not achieved similar feats for general-purpose audio representation learning from waveforms. Here, we propose WavJEPA, a waveform-based version of the Jo…

A Semantics-Aware Hierarchical Self-Supervised Approach to Classification of Remote Sensing Images
Giulio Weikmann, Gianmarco Perantoni, Lorenzo Bruzzone
https://arxiv.org/abs/2510.04916

A Semantics-Aware Hierarchical Self-Supervised Approach to Classification of Remote Sensing Images
Deep learning has become increasingly important in remote sensing image classification due to its ability to extract semantic information from complex data. Classification tasks often include predefined label hierarchies that represent the semantic relationships among classes. However, these hierarchies are frequently overlooked, and most approaches focus only on fine-grained classification schemes. In this paper, we present a novel Semantics-Aware Hierarchical Consensus (SAHC) method for learn…

Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining
Boshra Ariguib, Mathias Niepert, Andrei Manolache
https://arxiv.org/abs/2509.22468

Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining
High-quality molecular representations are essential for property prediction and molecular design, yet large labeled datasets remain scarce. While self-supervised pretraining on molecular graphs has shown promise, many existing approaches either depend on hand-crafted augmentations or complex generative objectives, and often rely solely on 2D topology, leaving valuable 3D structural information underutilized. To address this gap, we introduce C-FREE (Contrast-Free Representation learning on Ego…

An overview of neural architectures for self-supervised audio representation learning from masked spectrograms
Sarthak Yadav, Sergios Theodoridis, Zheng-Hua Tan
https://arxiv.org/abs/2509.18691

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…

Can multimodal representation learning by alignment preserve modality-specific information?
Romain Thoreau, Jessie Levillain, Dawa Derksen
https://arxiv.org/abs/2509.17943 https…

Can multimodal representation learning by alignment preserve modality-specific information?
Combining multimodal data is a key issue in a wide range of machine learning tasks, including many remote sensing problems. In Earth observation, early multimodal data fusion methods were based on specific neural network architectures and supervised learning. Ever since, the scarcity of labeled data has motivated self-supervised learning techniques. State-of-the-art multimodal representation learning techniques leverage the spatial alignment between satellite data from different modalities acqu…

Chunk Based Speech Pre-training with High Resolution Finite Scalar Quantization
Yun Tang, Cindy Tseng
https://arxiv.org/abs/2509.15579 https://arxiv.org/pd…

Chunk Based Speech Pre-training with High Resolution Finite Scalar Quantization
Low latency speech human-machine communication is becoming increasingly necessary as speech technology advances quickly in the last decade. One of the primary factors behind the advancement of speech technology is self-supervised learning. Most self-supervised learning algorithms are designed with full utterance assumption and compromises have to made if partial utterances are presented, which are common in the streaming applications. In this work, we propose a chunk based self-supervised learn…

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…

ACMID: Automatic Curation of Musical Instrument Dataset for 7-Stem Music Source Separation
Ji Yu, Yang shuo, Xu Yuetonghui, Liu Mengmei, Ji Qiang, Han Zerui
https://arxiv.org/abs/2510.07840

ACMID: Automatic Curation of Musical Instrument Dataset for 7-Stem Music Source Separation
Most current music source separation (MSS) methods rely on supervised learning, limited by training data quan- tity and quality. Though web-crawling can bring abundant data, platform-level track labeling often causes metadata mismatches, impeding accurate "audio-label" pair acquisi- tion. To address this, we present ACMID: a dataset for MSS generated through web crawling of extensive raw data, fol- lowed by automatic cleaning via an instrument classifier built on a pre-trained audio encoder tha…

Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models
Runze Liu, Jiakang Wang, Yuling Shi, Zhihui Xie, Chenxin An, Kaiyan Zhang, Jian Zhao, Xiaodong Gu, Lei Lin, Wenping Hu, Xiu Li, Fuzheng Zhang, Guorui Zhou, Kun Gai
https://arxiv.org/abs/2509.26628

Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models
Reinforcement Learning (RL) has shown remarkable success in enhancing the reasoning capabilities of Large Language Models (LLMs). Process-Supervised RL (PSRL) has emerged as a more effective paradigm compared to outcome-based RL. However, existing PSRL approaches suffer from limited exploration efficiency, both in terms of branching positions and sampling. In this paper, we introduce a novel PSRL framework (AttnRL), which enables efficient exploration for reasoning models. Motivated by prelimin…

Self-Supervised Cross-Modal Learning for Image-to-Point Cloud Registration
Xingmei Wang, Xiaoyu Hu, Chengkai Huang, Ziyan Zeng, Guohao Nie, Quan Z. Sheng, Lina Yao
https://arxiv.org/abs/2509.15882

Self-Supervised Cross-Modal Learning for Image-to-Point Cloud Registration
Bridging 2D and 3D sensor modalities is critical for robust perception in autonomous systems. However, image-to-point cloud (I2P) registration remains challenging due to the semantic-geometric gap between texture-rich but depth-ambiguous images and sparse yet metrically precise point clouds, as well as the tendency of existing methods to converge to local optima. To overcome these limitations, we introduce CrossI2P, a self-supervised framework that unifies cross-modal learning and two-stage reg…

LTA-L2S: Lexical Tone-Aware Lip-to-Speech Synthesis for Mandarin with Cross-Lingual Transfer Learning
Kang Yang, Yifan Liang, Fangkun Liu, Zhenping Xie, Chengshi Zheng
https://arxiv.org/abs/2509.25670 …

LTA-L2S: Lexical Tone-Aware Lip-to-Speech Synthesis for Mandarin with Cross-Lingual Transfer Learning
Lip-to-speech (L2S) synthesis for Mandarin is a significant challenge, hindered by complex viseme-to-phoneme mappings and the critical role of lexical tones in intelligibility. To address this issue, we propose Lexical Tone-Aware Lip-to-Speech (LTA-L2S). To tackle viseme-to-phoneme complexity, our model adapts an English pre-trained audio-visual self-supervised learning (SSL) model via a cross-lingual transfer learning strategy. This strategy not only transfers universal knowledge learned from …

Machine-Learning Driven Load Shedding to Mitigate Instability Attacks in Power Grids
Justin Tackett, Benjamin Francis, Luis Garcia, David Grimsman, Sean Warnick
https://arxiv.org/abs/2509.26532

Machine-Learning Driven Load Shedding to Mitigate Instability Attacks in Power Grids
Every year critical infrastructure becomes more complex and we grow to rely on it more and more. With this reliance, it becomes an attractive target for cyberattacks from sophisticated actors, with one of the most attractive targets being the power grid. One class of attacks, instability attacks, is a newer type of attack that has relatively few protections developed. We present a cost effective, data-driven approach to training a supervised machine learning model to retrofit load shedding deci…

Adversarial Graph Fusion for Incomplete Multi-view Semi-supervised Learning with Tensorial Imputation
Zhangqi Jiang, Tingjin Luo, Xu Yang, Xinyan Liang
https://arxiv.org/abs/2509.15955

Adversarial Graph Fusion for Incomplete Multi-view Semi-supervised Learning with Tensorial Imputation
View missing remains a significant challenge in graph-based multi-view semi-supervised learning, hindering their real-world applications. To address this issue, traditional methods introduce a missing indicator matrix and focus on mining partial structure among existing samples in each view for label propagation (LP). However, we argue that these disregarded missing samples sometimes induce discontinuous local structures, i.e., sub-clusters, breaking the fundamental smoothness assumption in LP.…

IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning
Aayush Mishra, Daniel Khashabi, Anqi Liu
https://arxiv.org/abs/2509.22621 https://arxiv…

IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning
Supervised Fine-Tuning (SFT) is used to specialize model behavior by training weights to produce intended target responses for queries. In contrast, In-Context Learning (ICL) adapts models during inference with instructions or demonstrations in the prompt. ICL can offer better generalizability and more calibrated responses compared to SFT in data scarce settings, at the cost of more inference compute. In this work, we ask the question: Can ICL's internal computations be used to improve the qual…

Enhancing Dual Network Based Semi-Supervised Medical Image Segmentation with Uncertainty-Guided Pseudo-Labeling
Yunyao Lu, Yihang Wu, Ahmad Chaddad, Tareef Daqqaq, Reem Kateb
https://arxiv.org/abs/2509.13084

Enhancing Dual Network Based Semi-Supervised Medical Image Segmentation with Uncertainty-Guided Pseudo-Labeling
Despite the remarkable performance of supervised medical image segmentation models, relying on a large amount of labeled data is impractical in real-world situations. Semi-supervised learning approaches aim to alleviate this challenge using unlabeled data through pseudo-label generation. Yet, existing semi-supervised segmentation methods still suffer from noisy pseudo-labels and insufficient supervision within the feature space. To solve these challenges, this paper proposes a novel semi-superv…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[6/6]:
- VarCoNet: A variability-aware self-supervised framework for functional connectome extraction from...
Charalampos Lamprou, Aamna Alshehhi, Leontios J. Hadjileontiadis, Mohamed L. Seghier

Not every day is a sunny day: Synthetic cloud injection for deep land cover segmentation robustness evaluation across data sources
Sara Mobsite, Renaud Hostache, Laure Berti Equille, Emmanuel Roux, Joris Guerin
https://arxiv.org/abs/2510.03006

Not every day is a sunny day: Synthetic cloud injection for deep land cover segmentation robustness evaluation across data sources
Supervised deep learning for land cover semantic segmentation (LCS) relies on labeled satellite data. However, most existing Sentinel-2 datasets are cloud-free, which limits their usefulness in tropical regions where clouds are common. To properly evaluate the extent of this problem, we developed a cloud injection algorithm that simulates realistic cloud cover, allowing us to test how Sentinel-1 radar data can fill in the gaps caused by cloud-obstructed optical imagery. We also tackle the issue…

Intra-Cluster Mixup: An Effective Data Augmentation Technique for Complementary-Label Learning
Tan-Ha Mai, Hsuan-Tien Lin
https://arxiv.org/abs/2509.17971 https://

Intra-Cluster Mixup: An Effective Data Augmentation Technique for Complementary-Label Learning
In this paper, we investigate the challenges of complementary-label learning (CLL), a specialized form of weakly-supervised learning (WSL) where models are trained with labels indicating classes to which instances do not belong, rather than standard ordinary labels. This alternative supervision is appealing because collecting complementary labels is generally cheaper and less labor-intensive. Although most existing research in CLL emphasizes the development of novel loss functions, the potentia…

Point2RBox-v3: Self-Bootstrapping from Point Annotations via Integrated Pseudo-Label Refinement and Utilization
Teng Zhang, Ziqian Fan, Mingxin Liu, Xin Zhang, Xudong Lu, Wentong Li, Yue Zhou, Yi Yu, Xiang Li, Junchi Yan, Xue Yang
https://arxiv.org/abs/2509.26281

Point2RBox-v3: Self-Bootstrapping from Point Annotations via Integrated Pseudo-Label Refinement and Utilization
Driven by the growing need for Oriented Object Detection (OOD), learning from point annotations under a weakly-supervised framework has emerged as a promising alternative to costly and laborious manual labeling. In this paper, we discuss two deficiencies in existing point-supervised methods: inefficient utilization and poor quality of pseudo labels. Therefore, we present Point2RBox-v3. At the core are two principles: 1) Progressive Label Assignment (PLA). It dynamically estimates instance sizes…

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…

Efficient Cell Painting Image Representation Learning via Cross-Well Aligned Masked Siamese Network
Pin-Jui Huang, Yu-Hsuan Liao, SooHeon Kim, NoSeong Park, JongBae Park, DongMyung Shin
https://arxiv.org/abs/2509.19896

Efficient Cell Painting Image Representation Learning via Cross-Well Aligned Masked Siamese Network
Computational models that predict cellular phenotypic responses to chemical and genetic perturbations can accelerate drug discovery by prioritizing therapeutic hypotheses and reducing costly wet-lab iteration. However, extracting biologically meaningful and batch-robust cell painting representations remains challenging. Conventional self-supervised and contrastive learning approaches often require a large-scale model and/or a huge amount of carefully curated data, still struggling with batch ef…

Semi-MoE: Mixture-of-Experts meets Semi-Supervised Histopathology Segmentation
Nguyen Lan Vi Vu, Thanh-Huy Nguyen, Thien Nguyen, Daisuke Kihara, Tianyang Wang, Xingjian Li, Min Xu
https://arxiv.org/abs/2509.13834

Semi-MoE: Mixture-of-Experts meets Semi-Supervised Histopathology Segmentation
Semi-supervised learning has been employed to alleviate the need for extensive labeled data for histopathology image segmentation, but existing methods struggle with noisy pseudo-labels due to ambiguous gland boundaries and morphological misclassification. This paper introduces Semi-MOE, to the best of our knowledge, the first multi-task Mixture-of-Experts framework for semi-supervised histopathology image segmentation. Our approach leverages three specialized expert networks: A main segmentati…

Enhancing Semantic Segmentation with Continual Self-Supervised Pre-training
Brown Ebouky, Ajad Chhatkuli, Cristiano Malossi, Christoph Studer, Roy Assaf, Andrea Bartezzaghi
https://arxiv.org/abs/2509.17816

Enhancing Semantic Segmentation with Continual Self-Supervised Pre-training
Self-supervised learning (SSL) has emerged as a central paradigm for training foundation models by leveraging large-scale unlabeled datasets, often producing representations with strong generalization capabilities. These models are typically pre-trained on general-purpose datasets such as ImageNet and subsequently adapted to various downstream tasks through finetuning. While recent advances have explored parameter-efficient strategies for adapting pre-trained models, extending SSL pre-training …