Latest Semi-Supervised Learning Research Papers

The newest Semi-Supervised Learning papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Semi-Supervised Learning so you don’t have to: get the standout work delivered to your inbox every morning, with 2-sentence summaries and the option to chat with any paper.

Recent papers

• Prestack Seismic AVO Inversion Method Based on the Fusion of Implicit Neural Representation and Semi-supervised Learning
  Xinxin LIANG, Hongling CHEN, Zhaoqi Gao, Ying ZHENG et al. · DOAJ (DOAJ: Directory of Op... · Nov 1, 2026

  Prestack seismic amplitude variation with offset (AVO) inversion is an important technique for obtaining subsurface elastic parameters and supporting complex reservoir prediction. However, because of the band-limited nature of seismic data,…

• Homebrewed SLMs: Autoregressive and Masked Diffusion Language Models Built at Home for Portuguese
  Pedro Carvalho Brom · arXiv · Oct 29, 2026

  Building a language model of one's own no longer requires a data centre. This tutorial trains one from scratch, tokenizer included, on one consumer GPU, and shows how to tell whether it is good for the tasks of a specialist domain. It propo…

• TSE-Net: Semi-supervised monocular height estimation from single remote sensing images
  Sining Chen, Xiao Xiang Zhu · ISPRS Journal of Photogramm... · Oct 24, 2026

  Monocular height estimation plays a critical role in 3D perception for remote sensing, offering a cost-effective alternative to multi-view or LiDAR-based methods. While deep learning has significantly advanced the capabilities of monocular …

• Stability-aware distribution-adaptive learning for semi-supervised facial expression recognition
  Qiuhong Wang, Na Wang, Jinbiao Zhao · Signal Image and Video Proc... · Oct 20, 2026
• Kronecker Delta Rule for Long Context Linear Attention
  Anamaria-Roberta Hartl, Levente Zólyomi, Michael List, Günter Klambauer et al. · arXiv · Oct 19, 2026

  We propose KronLSTM, a linear attention architecture based on the Kronecker Delta Rule, a novel update rule for associative matrix memories. KronLSTM extends the xLSTM family with a memory-revision mechanism that corrects targeted associati…

• Universal Semantic Enhancement for Weakly Supervised Anomaly Detection
  Siyu Zhou, Yuqin Xie, Hao Yuan, Yingjie Zhou · arXiv · Oct 16, 2026

  Weakly supervised anomaly detection on tabular data is an essential task in many label-scarce applications, since tabular data is widely encountered and it is commonly observed in practice that only a limited number of labeled anomalies are…

• Real-time nugget growth prediction in resistance spot welding via multi-source feature fusion and physics-constrained semi-supervised contrastive learning
  Qiang Song, YuJun Xia, XuPeng Li, Peihao Geng et al. · Journal of Manufacturing Pr... · Oct 9, 2026
• Decoupling Exploration from Optimization in RLVR
  Saif Punjwani, Micah Goldblum · arXiv · Oct 7, 2026

  Modern language models undergo reinforcement learning with verifiable rewards (RLVR) on top of already-trained checkpoints. A key promise of RLVR is the discovery of new reasoning strategies. In principle, a model can sample novel ideas abs…

• Semi-Supervised Generative Learning via Latent Space Distribution Matching
  Kwong Yu Chong, Long Feng · Journal of the American Sta... · Oct 7, 2026

  We introduce Latent Space Distribution Matching (LSDM), a novel framework for semi-supervised generative modeling of conditional distributions. LSDM operates in two stages: (i) learning a low-dimensional latent space from both paired and un…

• Prediction-powered inference for time series across space
  Shahzar Rizvi, David Burt, Vishwak Srinivasan, Renato Berlinghieri et al. · arXiv · Oct 6, 2026

  The following motif is common in spatiotemporal settings: we have a sequence of covariate and label pairs observed for a relatively short, recent time period. We have access to unlabeled covariates over a longer time period. Data is observe…

• IdeaLens: Detecting AI Ideas in Long-form Writing
  Rishanth Rajendhran, Minjoon Choi, Jenna Russell, Ramya Namuduri et al. · arXiv · Oct 5, 2026

  While modern AI detectors identify who wrote the words, emerging policies on AI use increasingly hinge on a different question: who came up with the ideas? We introduce IdeaLens, a detector that identifies whether a document's ideas came fr…

• ZeroMAG: Zero-Shot Multimodal Adapter Generation for Plug-and-Play EEG Foundation Models
  Yubo Wang, Jingying Ma, Xinliang Zhou, Yangxuan Zhou et al. · arXiv · Oct 2, 2026

  EEG foundation models (EFMs) capture reusable knowledge from large-scale EEG data, while many EEG recordings also include companion physiological signals that provide complementary information beyond the EEG-only interface. The challenge is…

• Image Classifiers are Efficient Self-Supervised Video Representation Learners
  Owais Iqbal, Sudipta Sarkar, Shyam Marjit, Omprakash Chakraborty et al. · arXiv · Sep 30, 2026

  We introduce VideoMSN, a Masked Siamese Network framework for efficient self-supervised spatio-temporal representation learning in videos. Instead of relying on heavy 3D architectures or reconstruction-based autoencoders for learning with u…

• How Much Is an AI Token Worth? Scaling Laws for Wild AI-Generated Web Text
  Jenna Russell, Ben Glickenhaus, Katherine Thai, John Wieting et al. · arXiv · Sep 30, 2026

  Web text makes up the majority of pretraining data and is increasingly AI-generated. After applying FineWeb quality filtering, we find that 27.5% of tokens from June 2026 web data are labeled as AI-generated by Pangram, rising to 31.1% by A…

• hyperbolix: Hyperbolic Deep Learning in JAX
  Timo Klein, Thomas Lang, Yllka Velaj, Sebastian Tschiatschek · arXiv · Sep 23, 2026

  We present hyperbolix, an open-source library for hyperbolic deep learning in JAX, built on Flax NNX. To our knowledge, it is the first comprehensive, general-purpose hyperbolic deep learning library in JAX. It includes six manifolds with a…

• MUST: Extended Supplementary Materials
  Yuwen Zeng · Zenodo (CERN European Organ... · Sep 23, 2026

  Extended supplementary materials accompanying the manuscript “MUST: Mean-teacher inspired and Uncertainty-aware Semi-supervised Transformer for cell instance segmentation,” accepted for publication in the IEEE Journal of Biomedical and Heal…

• Automatic depth-based local center clustering via $β$-integrated local depth and adaptive grouping
  Siyi Wang, Alexandre Leblanc, Paul D. McNicholas · arXiv · Sep 22, 2026

  Clustering is an unsupervised learning technique that partitions unlabeled data into groups. Most existing methods require user-specified parameters, such as the number of clusters or neighborhood size. Conversely, we propose automatic dept…

• Label-Efficient Learning for Ground-Based Sky-Image Classification: A Benchmark of Transfer Learning, Active Learning, and Pseudo-Labeling on GCD
  Esther Bou Dagher, Viktoriya Bu-Dager, Boguslaw Zegarlinski · arXiv · Sep 22, 2026

  Accurate ground-based cloud classification is important for atmospheric monitoring, solar-energy forecasting, aviation weather assessment, and climate observation systems. However, reliable sky-image annotation is time-consuming, especially…

• Lightweight Semi-supervised Domain Adaptation for Bearing Fault Diagnosis on Edge Devices
  Chaoxuan Qiu · Applied and Computational E... · Sep 22, 2026

  Rolling bearings serve as critical components in rotating machinery, but practical fault diagnosis is affected by operating-condition changes, limited fault samples, and the restricted computing resources of edge devices. This paper propose…

• Detecting Sentiment Analysis Correlation Between Hotel Employee and Customer Reviews Using Machine Learning Algorithms
  Berat Bakan, Abdullah Ammar Karcıoğlu, Esra KATIRCIOĞLU · ICCK Transactions on Emergi... · Sep 22, 2026

  Analyzing heterogeneous online reviews from multiple stakeholder groups represents an emerging challenge in AI-driven service intelligence. This study proposes a two-stage sentiment correlation detection framework and applies it to customer…

• MiTHras: Task-specific Hierarchical Semi-supervised Contrastive Masked Autoencoder for Mitotic Figure Analysis
  Trinh T. L. Vuong, Simon Graham, Quoc Dang Vu, Phat T. H. Ho et al. · arXiv · Sep 21, 2026

  Mitotic figure (MF) analysis supports tumor grading and prognostic assessment, but automated models remain sensitive to differences in tissue type and image acquisition. We present MiTHras, a task-specific pretraining framework that combine…

• Residual-guided confidence learning and dynamic ensemble selection for semi-supervised hyperspectral image classification
  Hongliang Lü, Yutian Chen, Xianglin Huang · Scientific Reports · Sep 19, 2026
• Metaheuristic-optimized Topology-aware Evidential Deep Learning for Label-efficient Semi-supervised Retinal Vessel Segmentation
  Shilpa, Kiranpreet Kaur · International journal of in... · Sep 19, 2026

  Retinal vessel segmentation underpins automated screening for diabetic retinopathy, yet supervised networks demand dense pixel labels that are slow and costly to obtain.Semi-supervised learning lowers this cost, but the consistency methods …

• Mixed-integer linear optimization for semi-supervised optimal classification trees
  Jan Pablo Burgard, Maria Eduarda Pinheiro, Martin Schmidt · Journal of Global Optimization · Sep 18, 2026

  Abstract Decision trees are one of the most popular methods for solving classification problems, mainly because of their good interpretability properties. Moreover, due to advances in recent years in mixed-integer optimization, several mode…

• Predicting unknown mammalian viral hosts with Dynamic Positive–Unlabeled learning
  Gabriele Pignalberi, Andrea Tonelli, S. Giagu, Moreno Di Marco · Nature Communications · Sep 17, 2026

  Most emerging infectious diseases in humans are zoonotic in origin. Yet, knowledge of host–pathogen associations remains limited. Machine learning models have been increasingly used to infer missing zoonotic host–pathogen associations, but …

• Measured multi-source fusion graph neural network for semi-supervised imbalanced working condition recognition
  Shuo Yang, Bin Zhou, Yanjiang Wang, Weifeng Liu · Multimedia Systems · Sep 17, 2026
• Temporal graph anomaly detection based on multi-view semi-supervised learning
  Yifan Song, Yu Yang, Kangzheng Liu, Feng Zhao · World Wide Web · Sep 17, 2026
• Source-Free Domain Adaptation with Vision-Language Prior
  Song Tang, Yunxiang Bai, Wenxin Su, Mao Ye et al. · International Journal of Co... · Sep 17, 2026

  Abstract Source-Free Domain Adaptation (SFDA) seeks to adapt a source model, which is pre-trained on a supervised source domain, for a target domain, with only access to unlabeled target training data. Relying on pseudo labeling and/or auxi…

• OSCS: Offshore Semi-Supervised Contrastive Segmentation of Drilling-Platform Point Clouds Under Limited Scene-Level Annotations
  Zhaoxu Ding, Xiaobo Zhang, Shengli Wang, Shuyue Liu et al. · Journal of Marine Science a... · Sep 16, 2026

  Accurate as-built models of offshore platforms require component-level information from dense laser scans, but point-wise annotation is costly. We present Offshore Semi Supervised Contrastive Segmentation (OSCS), a framework for drilling pl…

• A semi-supervised compound fault diagnosis method based on hierarchical attention and self-supervised graph learning for the rotary components of robots’ joints
  Zida Zhao, Chengshang Si, Shilong Sun, Dong Wang et al. · Mechanical Systems and Sign... · Sep 10, 2026