Latest Self-Supervised Learning Research Papers

The newest Self-Supervised Learning papers from across the field — arXiv, NeurIPS, CVPR, Nature, and more — refreshed daily and ranked by relevance. Distill AI tracks Self-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

• LoRA-TSD: Tangent-Space Spectral Descent for LoRA via Muon-Style Updates
  Dmitrii Andriianov, Andrey Veprikov, Aleksandr Beznosikov · arXiv · Sep 2, 2026

  Low-rank adaptation (LoRA) is the standard way to fine-tune large models, yet when its two factors are trained independently, the update ignores the geometry of the low-rank weight change it induces. We introduce LoRA-TSD, an optimizer that…

• Sycophantic Agreement Transfers with Neutral Data via Contrastive Preference Optimization
  Camila Blank, Zhuofan Ying, Christopher Potts, Peter Hase et al. · arXiv · Aug 31, 2026

  Sycophantic agreement refers to a behavior in which language models excessively affirm the user, often at the cost of factual accuracy. Although sycophantic agreement is a well-known failure of model alignment, there is limited understandin…

• Parameter-Efficient Self-Supervised Adaptation for EEG-FM under Fixed Computational Budgets
  Meghal Dani, Stefanie Liebe · arXiv · Aug 25, 2026

  EEG foundation models pretrained via self-supervised learning promise transferable representations, but their generalization remains limited, especially across diverse clinical datasets. Full fine-tuning is impractical for resource-constrai…

• Leaf Values as Coordinates: Exact Contrastive Explanation for Gradient-Boosted Ensembles
  Emanuele Luzio · arXiv · Aug 19, 2026

  A gradient-boosted ensemble predicts by summing one leaf value per tree. Read those values as coordinates rather than as intermediate results, and every instance becomes a point in R^M on which the model acts linearly: the score is the sum …

• On the Fragility of Self-Improving Agents: Variance, Task Order, and Underspecification
  Qinyuan Ye, Yu Li, Yada Pruksachatkun, Jiaxin Zhang et al. · arXiv · Aug 18, 2026

  Memory-based self-improving agents--those that learn from an online stream of tasks and improve over time by maintaining a textual memory bank--have shown great promise in recent literature. However, the reliability aspects of these methods…

• Understanding the Surprising Generalization Properties of Tabular Foundation Models
  Nour Shaheen, Junwei Ma, Alex Labach, Frank Hutter et al. · arXiv · Aug 18, 2026

  Tabular Foundation Models (TFMs) increasingly rely on in-context learning, where a model receives labelled examples at inference time and predicts labels for new inputs without updating its weights. Existing TFMs are typically trained on ei…

• Cross modal reliable pixel contrastive learning for incomplete modal brain tumor segmentation
  Jingjing Xu, Zhiwei Yang, Xin Wu, Jian Xiong et al. · Scientific Reports · Aug 15, 2026

  <title>Abstract</title> In clinical practice, Magnetic Resonance Imaging (MRI) often lacks specific modalities, inevitably leading to a degradation in predictive performance. Different modes are currently treated as independent and non-inte…

• Catching the Imposter: Self-Supervised Learning of Physical Coherence with Cross-Entity Feature Permutations
  Aleksei Rozanov, Arvind Renganathan, Vipin Kumar · arXiv · Aug 14, 2026

  Scientific data often describe entities whose features are jointly governed by the laws of physics, yet existing self-supervised learning (SSL) objectives largely ignore this physical coherence. We introduce imposter, a discriminative prete…

• Self-supervised graph attention networks for community-engaged lead contamination risk assessment
  Raphael Anaadumba, Nazim A. Belabbaci, Yigit Bozkurt, Connor Sullivan et al. · Scientific Reports · Aug 11, 2026

  Lead contamination in residential water infrastructure poses a persistent public health risk, yet current assessment approaches rely on sparse homeowner sampling and tabular models that do not explicitly capture spatial dependencies in shar…

• RxnCLF: Contrastive Transformation-Aware Reaction Foundation Model for Improved Reactivity Prediction
  Yiting Zheng, Cheng Fang, Anthony Donofrio, Haote Li · arXiv · Aug 6, 2026

  Reaction yield prediction remains challenging because labeled data are scarce and reaction space is both combinatorially large and sparsely populated, limiting the generalization of existing reaction representations. String-, fingerprint-, …

• Self-supervision drives representational convergence in medical foundation models more than clinical supervision
  Soroosh Tayebi Arasteh, Sebastian Ziegelmayer, Mahshad Lotfinia, Lisa Adams et al. · arXiv · Jul 22, 2026

  Medical image encoders from different groups are increasingly treated as interchangeable, on the assumption that scale and clinical supervision concentrate their representations onto a shared structure. Whether this convergence is real, wha…

• User-Centric Modeling of Transactional Sequences with Explainable State Space Models
  Ivan Palagin · arXiv · Jul 22, 2026

  We propose a hybrid approach for user-centric modeling of transactional event sequences that combines contrastive representation learning (CoLES) with State Space Models (SSMs). While contrastive methods yield high-quality compressed user r…

• CircuitKIT : Circuit Discovery, Evaluation, and Application Toolkit for Mechanistic Interpretability
  Pratinav Seth, Hem Gosalia, Aditya Kasliwal, Vinay Kumar Sankarapu · arXiv · Jul 21, 2026

  Circuit analysis can support not only model explanation but also downstream interventions such as pruning, editing, steering, and selective fine-tuning. However, conducting such analyses currently requires stitching together separate implem…

• Contrastive-Collapsed Loss for Flexible and Geometrically Optimal Embeddings and Faster Convergence
  Blanca Cano-Camarero, Ángela Fernández-Pascual, José R. Dorronsoro · arXiv · Jul 14, 2026

  In this work, we introduce CoCo, a loss function aimed at learning normalized and well-structured representations. The proposed loss encourages intra-class collapse and inter-class contrast while preserving sufficient flexibility for neural…

• Self-Supervised Learning as Discrete Communication
  Kawtar Zaher, Ilyass Moummad, Olivier Buisson, Alexis Joly · ICML 2026 regular · Apr 30, 2026

  Most self-supervised learning (SSL) methods learn continuous visual representations by aligning different views of the same input, offering limited control over how information is structured across representation dimensions. In this work, w…

• On the Alignment Between Supervised and Self-Supervised Contrastive Learning
  Achleshwar Luthra, Priyadarsi Mishra, Tomer Galanti · ICLR 2026 Poster · Jan 26, 2026

  Self-supervised contrastive learning (CL) has achieved remarkable empirical success, often producing representations that rival supervised pre-training on downstream tasks. Recent theory explains this by showing that the CL loss closely app…

• LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
  Randall Balestriero, Yann LeCun · arXiv.org · Nov 11, 2025

  Learning manipulable representations of the world and its dynamics is central to AI. Joint-Embedding Predictive Architectures (JEPAs) offer a promising blueprint, but lack of practical guidance and theory has led to ad-hoc R&D. We present a…

• Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations
  Yujia Zhang, Xiaoyang Wu, Yixing Lao, Chengyao Wang et al. · Neural Information Processing Systems · Oct 27, 2025

  Humans learn abstract concepts through multisensory synergy, and once formed, such representations can often be recalled from a single modality. Inspired by this principle, we introduce Concerto, a minimalist simulation of human concept lea…

• SSNet: Flexible and Robust Channel Extrapolation for Fluid Antenna Systems Enabled by a Self-Supervised Learning Framework
  Yuan Gao, Yiming Liu, Runze Yu, Shengli Liu et al. · IEEE Journal on Selected Areas in Communications · Sep 22, 2025

  Fluid antenna systems (FAS) signify a pivotal advancement in 6G communication by enhancing spectral efficiency and robustness. However, obtaining accurate channel state information (CSI) in FAS poses challenges due to its complex physical s…

• Anomaly detection in encrypted network traffic using self-supervised learning
  Sadaf Sattar, Shumaila Khan, M. I. Khan, A. Akhmediyarova et al. · Scientific Reports · Jul 22, 2025

  Privacy and security in network communication have been enhanced via encryption and traditional anomaly detection methods are no longer effective because of their payload inspection. In this paper, we describe ET-SSL, a new approach for enc…

• Self-supervised learning in drug discovery
  Yangyang Chen, Zixu Wang, Jianmin Wang, Yanyi Chu et al. · Science China Information Sciences · Jun 23, 2025
• Self-supervised learning of molecular representations from millions of tandem mass spectra using DreaMS
  Roman Bushuiev, Anton Bushuiev, Raman Samusevich, Corinna Brungs et al. · Nature Biotechnology · May 23, 2025

  Characterizing biological and environmental samples at a molecular level primarily uses tandem mass spectroscopy (MS/MS), yet the interpretation of tandem mass spectra from untargeted metabolomics experiments remains a challenge. Existing c…

• Joint Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self Supervised Learning
  Hugues Van Assel, Mark Ibrahim, Tommaso Biancalani, Aviv Regev et al. · Neural Information Processing Systems · May 18, 2025

  Reconstruction and joint embedding have emerged as two leading paradigms in Self Supervised Learning (SSL). Reconstruction methods focus on recovering the original sample from a different view in input space. On the other hand, joint embedd…

• Physics-driven self-supervised learning for fast high-resolution robust 3D reconstruction of light-field microscopy
  Zhi Lu, Manchang Jin, Shuai Chen, Xiaoge Wang et al. · Nature Methods · May 12, 2025

  Light-field microscopy (LFM) and its variants have significantly advanced intravital high-speed 3D imaging. However, their practical applications remain limited due to trade-offs among processing speed, fidelity, and generalization in exist…

• Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3D
  Sergio Arnaud, Paul Mcvay, Ada Martin, Arjun Majumdar et al. · International Conference on Machine Learning · Apr 19, 2025

  We present LOCATE 3D, a model for localizing objects in 3D scenes from referring expressions like"the small coffee table between the sofa and the lamp."LOCATE 3D sets a new state-of-the-art on standard referential grounding benchmarks and s…

• MENTOR: Multi-level Self-supervised Learning for Multimodal Recommendation
  Jinfeng Xu, Zheyu Chen, Shuo Yang, Jinze Li et al. · AAAI Conference on Artificial Intelligence · Apr 11, 2025

  As multimedia information proliferates, multimodal recommendation systems have garnered significant attention. These systems leverage multimodal information to alleviate the data sparsity issue inherent in recommendation systems, thereby en…

• Self-supervised learning for vehicle bearing fault diagnosis based on time–frequency dual-domain contrast and fusion
  Deqiang He, Yuan Xu, Haimeng Sun, Zhenzhen Jin et al. · Nonlinear dynamics · Apr 4, 2025
• Joint Supervised and Self-supervised Learning for MRI Reconstruction
  George Yiasemis, Nikita Moriakov, Clara I. Sánchez, Jan-Jakob Sonke et al. · MIDL 2025 Poster · Mar 27, 2025

  Magnetic Resonance Imaging (MRI) is a crucial modality but, its inherently slow acquisition process poses challenges in obtaining fully-sampled $k$-space data under motion. The lack of fully-sampled acquisitions, serving as ground truths, c…

• Sonata: Self-Supervised Learning of Reliable Point Representations
  Xiaoyang Wu, Daniel DeTone, Duncan P. Frost, Tianwei Shen et al. · Computer Vision and Pattern Recognition · Mar 20, 2025

  In this paper, we question whether we have a reliable self-supervised point cloud model that can be used for diverse 3D tasks via simple linear probing, even with limited data and minimal computation. We find that existing 3D self-supervise…

• Stealthy Backdoor Attack in Self-Supervised Learning Vision Encoders for Large Vision Language Models
  Zhao Liu, Huan Zhang · Computer Vision and Pattern Recognition · Feb 25, 2025

  Self-supervised learning (SSL) vision encoders learn high-quality image representations and thus have become a vital part of developing vision modality of large vision language models (LVLMs). Due to the high cost of training such encoders,…