Self-Supervised Pre-Training

Follow this topic Ask about this topic

Momentum

18 papers in the last four weeks, up 64% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 155

Aug 11, 2026cs.SD

DINO-A: Adapting Self-Distillation Vision Transformers to General Audio Representation Learning

We present DINO-A, an adaptation of self-distillation from vision to general audio representation learning. While DINO has become a canonical method in self-supervised vision and prior audio work has explored latent prediction (BYOL-A) and masked modeling (Audio-MAE, BEATs), no prior work has brought canonical DINO to general audio classification in the way BYOL-A brought BYOL. DINO-A retains DINO's multi-crop, EMA teacher, and high-dimensional projection, replacing only the input modality and augmentations with log-mel spectrograms and the BYOL-A v2 augmentation block. We pretrain three backbones, two Vision Transformers with 8x8 and 16x16 patches and a convolutional encoder, on FSD50K and evaluate them with linear probing on ESC-50, Speech Commands v2, UrbanSound8K, and GTZAN. Three findings characterize the resulting representations. Patch resolution within the Vision Transformer family has consistent effect on representation quality, with smaller patches winning across all four tasks. The choice between Vision Transformer and convolutional backbone interacts with task type: convolutional networks lead on speech while Vision Transformers lead on environmental sounds and music. Under identical pretraining and evaluation conditions, DINO-A and BYOL-A v2 differ by 11.96 percentage points on average, and we trace this difference to two mechanisms: the interaction between DINO's high-dimensional projection space and FSD50K's limited scale, and the additional cost of multi-crop augmentation, which DINO uses but BYOL-A v2 does not. The high-dimensional projection space, central to DINO's success in vision, becomes a liability at FSD50K scale.

Tomasz Radzikowski, Mateusz Modrzejewski, Przemysław Rokita

Warsaw University of Technology, Warsaw, Poland

Audio Representation Learning Self-Supervised Pre-Training Self-Distillation Audio Classification

Aug 11, 2026q-bio.BM

DegradeQuery: Counterfactual Tuple Pretraining for Context-Aware PROTAC Degradation Prediction

Proteolysis-targeting chimeras (PROTACs) induce protein degradation by recruiting a target protein to an E3 ubiquitin ligase, making degradation a joint outcome of the degrader molecule and its biological context. Although public databases contain thousands of structured molecule-target-E3 records, degradation measurements are available for only a small fraction of them. Existing supervised approaches therefore leave most recorded chemical-biological relationships unused. We introduce DegradeQuery, a context-aware prediction framework that converts these label-missing records into a pretraining signal. Its counterfactual tuple pretraining objective contrasts recorded tuples with alternatives formed by replacing the target, the E3 ligase, or both, enabling the model to learn contextual associations without assigning activity pseudo-labels. The resulting representation is then fine-tuned to predict degradation from the complete molecule-target-E3 context. On the official PROTAC-8K benchmark, DegradeQuery achieves an area under the receiver operating characteristic curve of 0.9065 and an accuracy of 0.8500, outperforming the compared methods. Controlled analyses further show that the improvement is primarily attributable to tuple-level pretraining, can be recovered using only label-missing records, and remains complementary to protein language model representations. These findings demonstrate that incompletely labeled PROTAC databases contain useful relational supervision and provide a practical route for learning context-aware degradation predictors from scarce experimental labels.

Dong Xu, Zhangfan Yang, Jiantao Wu +3

School of Artificial Intelligence, Shenzhen University · EasternDawn · School of Computer Science, University of Nottingham Ningbo

Contrastive Learning Self-Supervised Pre-Training Molecular Property Prediction

Aug 10, 2026cs.CL

The Announcement Carries the Cue: Markup, Boundaries, and the Notation of Pre-Training Corpora

How a document's arrangement is written down, its notation, is a training variable that no dataset card records. The field has established that text-extraction choices change model behaviour, and has never once measured the notation of what those choices put into the corpus. We define clean-window survival, a deterministic count of how much of a stream still demands the boundary inference, and measure notation on three fronts. What corpora carry: a census of thirteen public corpora, where survival falls to 0.153 in a vision-converted PDF slice against 0.889 in C4; the scarce resource is not unmarked text but long unmarked text; a pre-registered supply test finds what remains institutional, not consumer. Our own pre-registered prediction failed: converters do not fabricate structure on prose, and that null forced the reliability mechanism that survives it. What readers use: across five base models spanning 0.6B to 8.2B and two pipelines, deleting a structural announcement makes the following prose measurably harder to predict, while swapping its notation moves nothing. That zero does not make notation unimportant; it relocates the variable: the operative cue is the announcement, not the sigil. What writers impose: a bounded null. Base models do not impose the marked register above the authored baseline, and handed prose with every announcement deleted they do not put one back, at a rate indistinguishable from zero against an authored reference of zero. We ship the format those measurements imply: the pure frame, paragraphs in authored order, every announcement deleted into a reversible sidecar, mixed against the marked copy over announcement presence rather than notation. Choose format operators by the capability they train, not by the fidelity they preserve, and record extractor identity and survival on data cards.

E. M. Freeburg

Independent Researcher

Language Model Pretraining Self-Supervised Pre-Training

Aug 7, 2026cs.CV

Vernata: Self-Supervised Learning of LiDAR Point Representations

LiDAR serves as a primary sensing modality for robots operating in outdoor environments. However, the performance of deep learning models in this domain is severely limited by the scarcity of labeled data, a direct result of the high cost of 3D annotation. Self-supervised learning addresses this scarcity by learning general-purpose features from unlabeled data. In this work, we present a multi-modal, multi-teacher distillation framework for self-supervised learning on outdoor LiDAR point clouds. Building upon the Sonata architecture, we introduce Vernata, consisting of three extensions: sparse view augmentation to improve robustness against varying point densities, a memory bank mechanism to stabilize resource-constrained training, and cross-modal distillation utilizing dense, high-resolution 2D image features to enable fine-grained semantic guidance. We evaluate our method on the GrandTour, TartanGround, and Waymo datasets, as well as data collected from our own robotic platforms. Our experiments demonstrate a significant performance improvement over Sonata baselines, yielding mIoU scores of 54.7 on TartanGround (+5.9 points, +12.1%) and 57.1 on Waymo (+7.3 points, +14.7%). Finally, we show that the self-supervised approach maintains strong performance even in reduced-modality settings (lacking color or normals), achieving competitive mIoU scores of 49.4 and 50.2 on the respective datasets.

Oliver Lemke, Alexander Liniger, Abel Gawel +1

1Robotics and AI Institute · 2ETH Zurich

Self-Supervised Learning Self-Supervised Pre-Training Point Cloud Learning 3D Semantic Segmentation

Aug 7, 2026cs.AI

CellWorld: From Gene-Level Reconstruction to Latent Cell Prediction in Spatial Transcriptomics Foundation Models

This paper shows that latent-space predictive pretraining can provide a scalable route to foundation models for spatial transcriptomics. Existing spatial transcriptomics foundation models primarily reconstruct masked gene identities or expression values, potentially encouraging the reproduction of assay-specific technical variation and limiting representation transferability. To avoid directly reconstructing such variation, we shift the prediction target from observed gene measurements to latent cell representations and introduce CellWorld, which predicts the latent representations of masked cells from visible spatial context and a limited partial-expression hint. We pretrain four CellWorld variants, spanning 5.74M to 94.56M trainable parameters, on a corpus of 46 million human cells. Our controlled scaling experiments show that performance improves with model capacity, particularly on spatial tasks, while spatial transfer depends more on sufficient optimization and broad biological source diversity than on cell count alone. Across four held-out datasets, even CellWorld-Small, with 5.74M trainable parameters, outperforms every baseline on all 11 linear-probe benchmarks and all seven fine-tuned spatial benchmarks. Most notably, a frozen CellWorld-Large pretrained on only 5% of the corpus with broad biological source coverage outperforms every fully fine-tuned baseline across all seven spatial benchmarks. Code is available at https://github.com/UoM-HealthAI/CellWorld.

Haiping Liu, Qian Zhao, Lijing Lin +2

University of Manchester

Spatial Transcriptomics Self-Supervised Pre-Training Predictive Representation Learning

Aug 5, 2026cs.CV

Lesion Detection in CT with Frozen Self-Distilled Features: SALT, a Spatially Adaptive Label-Guided Temperature

Self-supervised pretraining objectives are spatially uniform: the teacher temperature and the per-patch loss weight are identical everywhere in the image, so a lesion a few patches wide contributes no more to the training signal than the surrounding parenchyma. Prior work biases the views toward annotated regions, which changes what the model sees but adds no pressure on the objective. We instead condition the targets of self-distillation, a method we call SALT (Spatially Adaptive Label-guided Temperature). Weak, box-derived labels, available only during pretraining, define a compact region on the encoder's patch grid, inside which the teacher's softmax temperature is sharpened and the masked-patch loss is up-weighted. The objectives, the masking policy and the centering statistics are otherwise unchanged, and at every downstream use the encoder is a plain feature extractor with no labels and no conditioning. We evaluate by freezing the encoder and training only a lightweight multi-depth CenterNet-style head, detecting lesions in 3D on four CT cohorts, and we isolate the mechanism against a backbone identical in architecture, pretraining data, schedule and label-guided cropping but with no target conditioning. We report patch-level separability, 3D detection stratified by cohort and by lesion size, box quality, and a detector-free probe in which a single frozen patch embedding re-identifies a lesion in a follow-up scan without registration, masks or fine-tuning. Because the conditioning is expressed through a spatial indicator rather than through label semantics, the formulation admits any weak spatial annotation; we instantiate and validate it for lesions.

Mahmut S. Gokmen, Evan W. Damron, Mitchell A. Klusty +3

University of Kentucky Lexington, KY, USA · University of Louisville Louisville, KY, USA

Self-Supervised Pre-Training Medical Image Analysis Self-Distillation Computed Tomography

Aug 5, 2026cs.SD

Helping Music Co-Creation Agents 'Listen' Well: Hierarchical Self-Supervised World Models for Understanding and Generation

Collaborative music agents need internal representations rich enough to support both understanding and generation, yet flexible enough for a workflow where the human retains agency. We present a hierarchical self-supervised ``world model'' for symbolic music: a 2.55M-parameter Swin V2 encoder trained on MIDI piano-roll images with JEPA-style objectives (pitch- and time-shift equivariance, masked embedding prediction, and a distributional regularizer), using no labels and no music-theory vocabulary. Probing the frozen embeddings shows that the level at which a musical property becomes decodable tracks its musical time scale: phrase boundaries are read off the coarsest levels, note density and harmonic detail off the finest. Temporal and phrase structure emerge from the self-supervised objectives alone, while harmonic content must be asked for; a small chord-supervision head raises joint chord recovery from .18 to .54, and key detection, which is never supervised, from .16 to .70. Following the Representation AutoEncoder paradigm, a conditional flow-matching model stands in for a trained decoder, flowing in pixel space from PCA-reduced conditioning: it reproduces a target window at pixel F1

0.996

, and the same per-level conditioning dropout that controls how far variations stray also enables graphical prompting for masked inpainting with no inpainting-specific sampler. The pipeline runs on CPU producing a suggestion in

2.8

s, or

0.6

s on Apple MPS, which we demonstrate in a live interactive demo. In concert with an LLM-based brain, these capabilities supply the core of a collaborative music creation agent in service of, rather than in place of, human agency.

Scott H. Hawley

Department of Chemistry & Physics Belmont University Nashville, TN, USA

Representation Learning Self-Supervised Pre-Training Controllable Music Generation Conditional Generative Modeling Human-AI Co-Creation

Aug 4, 2026cs.LG

ED-DiT: Physics-Guided Diffusion Pretraining for Transferable Molecular Representations from Electron Density

Pretraining has shown strong potential for learning transferable representations, yet it remains underexplored for electron-density-based molecular learning. Electron density provides a continuous three-dimensional description of molecular electronic structure, capturing both local spatial patterns and global physical quantities. This raises a key question: can electron-density fields be used for self-supervised pretraining to learn a shared representation that transfers across diverse electronic-structure-related tasks? We propose ED-DiT, a physics-guided Diffusion Transformer for self-supervised pretraining on electron-density point clouds. ED-DiT learns reusable representations by reconstructing corrupted and partially masked log-density fields across diffusion noise levels. An electron-number consistency constraint is further introduced to preserve the total electronic mass. The pretrained encoder can be adapted to property prediction, open-/closed-shell classification, molecule-electron-density retrieval, and molecule-conditioned electron-density prediction. Experiments on six EDBench tasks show that ED-DiT consistently outperforms the same architecture trained from scratch, especially under limited supervision. For molecule-conditioned electron-density prediction, it reduces RMSE from 2.2474 to 1.3753 and surpasses the available baseline. With only 10% labels, it improves orbital energy prediction RMSE from 0.0293 to 0.0138. These results demonstrate the effectiveness of physics-guided electron-density pretraining for learning transferable molecular representations.

Liang Shuang, Haocheng Wang, Jiayi Song +2

Fudan University, Shanghai, China · Shenzhen Loop Area Institute, Shenzhen, China · The Chinese University of Hong Kong, Hong Kong SAR, China

Diffusion Transformer Self-Supervised Pre-Training Physics-Informed ML Molecular Representation Learning

Aug 3, 2026cs.LG

Understanding and Correcting Low-Frequency Bias in EEG Foundation Model

Increasing EEG pretraining data scale or model capacity does not consistently improve downstream performance. We identify a persistent low-frequency bias in representations learned by diverse EEG foundation models, which remains across dataset scales, model capacities, and pretraining objectives. Our analysis links this bias to the interaction between EEG's

1/f^α

-like spectral structure and neural networks' tendency to preferentially learn low-frequency components. In masked autoencoders, the

\ell_2

reconstruction objective further amplifies this imbalance: under comparable relative reconstruction errors, high-power low-frequency components contribute disproportionately to the loss. To address this issue, we introduce FAME, a frequency-balanced masked autoencoding framework that reconstructs time--frequency activity in predefined EEG bands from masked EEG inputs. FAME independently standardizes the reconstruction targets within each band and assigns equal weight to all band-specific losses, thereby balancing supervision across the EEG spectrum. Evaluated on 41 downstream tasks in OmniEEG-Bench, FAME learns more spectrally balanced representations and achieves state-of-the-art performance on 24 of them. These results underscore the importance of balanced spectral supervision for learning transferable EEG representations.

Junjie Yu, Zihan Deng, Jianyu Zhang +8

Department of Biomedical Engineering, Southern University of Science and Technology, Shenzhen, China · Omni-Intelligence, Shenzhen, China · College of Design and Engineering, National University of Singapore, Singapore +4

Masked Autoencoders Self-Supervised Pre-Training Frequency-Domain Feature Learning EEG Foundation Models

Aug 2, 2026cs.LG

Beyond Gene Reconstruction: Learning Cell Representations through Complementary Transcriptomic Views

The rapid growth of single-cell transcriptomic data has enabled the development of foundation models pretrained primarily by reconstructing masked expression values. This objective encourages these models to learn gene dependencies but does not directly optimize whole-cell representations, which are essential for many downstream tasks. To bridge this gap, we propose a contrastive pretraining framework that learns cell representations through complementary transcriptomic views. Since standard contrastive learning is not readily applicable to single-cell pretraining, we introduce specific adaptations along three dimensions --- co-expression-guided gene partitioning, expression-aware contrast-set construction, and competence-gated contrastive onset. Specifically, we first construct two complementary views of each cell by partitioning its genes according to their co-expression structure. Then, to prevent the model from using gene-set identity as a shortcut, we construct hard negatives by permuting expression values while keeping gene identities unchanged. Finally, we introduce a competence-aware controller to determine how the contrastive objective is applied. Experiments on cell-type annotation and gene regulatory network inference demonstrate competitive transfer under the evaluated protocols. In the six-network GRN evaluation, our method records the highest mean AUROC and AUPRC point estimates among the compared variants, while the highest-scoring variant differs across individual networks. These results establish complementary-view contrastive learning as an effective direction for single-cell pretraining beyond gene reconstruction.

Jiaqi Xiong, Yuntao hu, Yu Zheng +3

University of Oxford, Oxford, United Kingdom · Tongji University, Shanghai, China · Hunan University, Changsha, China +2

Contrastive Learning Representation Learning Self-Supervised Pre-Training Multi-View Learning Genomics Single-Cell Transcriptomics

Jul 31, 2026cs.AI

Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization

Neural Combinatorial Optimization (NCO) techniques have emerged as a highly efficient alternative to traditional exact algorithms for solving routing problems such as the Traveling Salesman Problem (TSP). However, the generalization capabilities of these Reinforcement Learning-based models are severely hindered when scaling to high-dimensional instances. This issue has been mitigated in other domains, like computer vision and natural language processing, by adopting a self-supervised pre-training strategy. Nevertheless, its application to routing graphs, which lack complex topological attributes beyond 2D spatial coordinates, remains a challenge. In this paper, we propose a geometric self-supervised pre-training framework specifically designed to capture spatial invariance and global relative distance distributions. By applying isometric transformations, such as rotations and axial reflections, the model learns robust structural representations prior to the policy optimization phase. Empirical results demonstrate that this strategy consistently outperforms models trained from scratch (baselines), achieving a 7.23% improvement in tour length for massive zero-shot extrapolation scenarios (TSP1,000). Furthermore, the proposed model exhibits remarkable computational efficiency, delivering speedups of up to two orders of magnitude over the exact solver Concorde at massive scales. The source code and pre-trained models are publicly available at https://github.com/davidaguadocosano/TSP-GeoPretrain.git.

David Aguado, Daniel Fuertes, Carlos R. del-Blanco +1

Grupo de Tratamiento de Imágenes, Information Processing and Telecomunications Center, ETSI Telecomunicación, Universidad Politécnica de Madrid, 28040, Madrid, Spain

Traveling Salesperson Problem Self-Supervised Learning Self-Supervised Pre-Training Geometric Representation Learning RL for Combinatorial Optimization Neural Combinatorial Optimization

Jul 31, 2026cs.CV

On the Efficacy of Self-Supervised Point Cloud Encoders for Efficient 3D Large Language Models

3D point cloud-language models (3D-LLMs) enable 3D understanding by pairing point cloud encoders with large language models, but existing methods rely on costly multi-modal encoders (e.g., ULIP-2) that require image-text-point cloud alignment on 8x A100-scale compute, creating high barriers for research and deployment. In this work, we systematically investigate whether low-cost self-supervised point cloud encoders, specifically PCP-MAE and Point-MAE, can serve as effective alternatives. Using MiniGPT-3D as our testbed, we evaluate 7 encoder initialization/pre-training setups (1 multi-modal baseline, 5 self-supervised, 1 random init) under frozen and unfrozen fine-tuning (12 total groups), across 2 architectures (MaskTransformer, PointTransformer), 3 objectives (PCP-MAE, Point-MAE, random init), and 2 datasets (Objaverse 660K, ShapeNet55-34 approximately 50K). Our experiments reveal three key findings: (1) The four-stage MiniGPT-3D pipeline can effectively train a 3D encoder from random initialization: an end-to-end trained random init encoder reaches 52.50% open-vocabulary accuracy and 44.45 captioning score, approaching top pre-trained variants; (2) Architecture and pre-training objective show strong crossover interaction: PCP-MAE + MaskTransformer achieves 59.00% accuracy (best self-supervised), while Point-MAE + MaskTransformer drops to 46.50%, with the pattern reversed for PointTransformer; (3) Closed-set ModelNet40 classification remains a core weakness of purely geometric encoders, reaching only ~13-18% accuracy vs. ~62% for the multi-modal baseline, even after end-to-end fine-tuning. Our results offer practical guidelines for cost-effective 3D-LLM design and reveal interaction patterns between self-supervised objectives and encoder architectures.

Yao Zheng, Tian Zhang

Beijing University of Posts and Telecommunications

Self-Supervised Pre-Training Point Cloud Learning 3D VLMs

Jul 29, 2026cs.LG

A Lightweight Foundation Model for Collider Physics with Multi-Domain Adaptation

We present a lightweight approach to foundation modeling (\textbf{NEXUS}) that leverages pre-trained learning from collider physics data towards out-of-domain tasks in other scientific datasets, using a fully connected autoencoder model with approximately 3 million parameters. The model pre-trains with no supervision over a large-scale collision dataset from the Large Hadron Collider modeled by charged particle track features. Downstream tasks for collider analyses, such as kinematic regression and event classification, are developed on pre-trained model weights and achieve improved accuracy with only small labeled datasets when compared to equivalent architectures trained from scratch. The benefits of pre-training are additionally investigated through latent space interpretation and application to other domains, including gravitational waves, flood forecasting, and neural activity. Furthermore, the relative computational simplicity of NEXUS is demonstrated compared to transformer approaches at comparable scale, opening the door to power-efficient inference and real-time or edge applications of foundation models in scientific experiments.

Liangyu Wu, Qibin Liu, Alexander Yue +1

Department of Physics, Stanford University, 450 Jane Stanford Way, Stanford, 94305, CA, USA. · SLAC National Accelerator Laboratory, 2575 Sand Hill Road, Menlo Park, 94025, CA, USA.

Self-Supervised Pre-Training High-Energy Physics Cross-Domain Transfer Learning Scientific ML

Jul 25, 2026cs.CV

SARATR-X-v2: Scale-Aware Structural Pre-Training for SAR Foundation Models

Masked image modeling has become a dominant paradigm for SAR pre-training, yet the design of the reconstruction target remains fundamentally unsettled. This article argues that a SAR pre-training target should satisfy two conditions to produce transferable representations: (i) physics-grounded stability, i.e., approximate invariance of the target operator to multiplicative speckle inherent in coherent imaging; and (ii) semantic scale compatibility, i.e., coverage of the heterogeneous spatial scales that downstream tasks demand. These two conditions are individually achievable but jointly difficult: physics-grounded stability favors fixed operators, while semantic scale compatibility favors data-driven composition. To this end, SARATR-X-v2 reconciles both within a single design. The target is constructed through fixed structural extractors spanning six receptive fields, from blind-spot local aggregation to directional log-ratio region contrast, and fused via learnable weights into one unified supervision signal for masked reconstruction. On twelve SAR benchmarks across classification, detection, and segmentation, SARATR-X-v2 achieves state-of-the-art transfer performance. Under synthetic speckle variation, the proposed target reduces perturbation drift in the learned representation by nearly two orders of magnitude relative to pixel-space supervision. Taken together, these results establish physics-grounded stability and semantic scale compatibility as a principled framework for pre-training target design under coherent imaging, and suggest that effective SAR pre-training is not about reconstructing more signal, but about reconstructing the right structural target.

Weijie Li, Yafei Song, Yongxiang Liu +7

College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China

Self-Supervised Pre-Training Synthetic Aperture Radar Masked Image Modeling

Jul 24, 2026cs.LG

IQ-JEPA: A Joint-Embedding Predictive Architecture with a Hermitian Vision Transformer for Sound Speed and Attenuation Estimation from Ultrasound IQ Data

The speed of sound in tissue is a prerequisite for well-focused imaging and has diagnostic value, but recovering it from raw pulse-echo channel data is fundamentally a nonlinear inverse problem. Learned solvers are fast yet label hungry. Simulated sound-speed labels are expensive, while abundant real channel data is unlabeled. We propose IQ-JEPA to exploit both data types. An encoder is pretrained without labels to predict the latent representation of masked in-phase and quadrature (IQ) regions from visible context, then fine-tuned on simulated maps. Sound speed appears in the IQ signal as a phase difference, invariant to the constant phase offset. The encoder is a Hermitian vision transformer that operates on the complex signal directly. Its attention is equivariant to that phase and its conjugate-product feed-forward is invariant to it, so the encoder reads a quantity analogous to the one classical coherence methods use. On 79,293 Fullwave 2.5 simulations at 2.5 MHz, pretraining on the 63,435 unlabeled acquisitions reaches 15.60 m/s at 10,000 labels. This is a roughly threefold gain in label efficiency over supervised training, growing to over fourfold at 1,000 labels. It is about 2.2x below an InversionNet baseline, and 8.71 m/s at full labels. The gain still grows with more unlabeled pretraining data. Our comparisons point to self-supervision as the dominant factor. The same encoder transfers. Its frozen features expose sound speed and attenuation, and cross-distribution pretraining between layered and abdominal phantoms costs little accuracy. We see this as a first step toward a foundation model for quantitative ultrasound.

Masashi Sode, Gianmarco Pinton

Joint Department of Biomedical Engineering, University of North Carolina at Chapel Hill and North Carolina State University, Chapel Hill, NC 27599 USA

Self-Supervised Pre-Training Joint-Embedding Predictive Architecture Complex-Valued Neural Networks Ultrasound Imaging Image Inverse Problems

Jul 23, 2026cs.AI

MSBraM: A Multi-scale Self-supervised Brain Foundation Model for Hierarchical EEG Dynamics Learning

Self-supervised foundation models have recently shown strong potential for electroencephalogram (EEG)-based analysis. However, existing approaches struggle to capture the inherently multi-scale temporal structure of EEG signals, where local neural patterns and long-range dependencies jointly encode task-relevant information. This limitation hampers cross-scale representation learning and generalization across diverse downstream tasks. To address this challenge, we propose MSBraM, a Multi-Scale self-supervised Brain foundation Model designed to learn hierarchical EEG representations. MSBraM follows a two-stage pretraining framework. First, a multi-scale neural tokenizer discretizes raw EEG signals into semantic codes at different temporal resolutions via vector-quantized reconstruction. Second, the model is pretrained to predict masked codes using a curriculum multi-scale masking strategy, progressively integrating fine-grained local patterns with global temporal context. We pretrain MSBraM on over 2,400 hours of EEG data and evaluate it across 10 downstream tasks on 12 public datasets. Extensive experiments show that MSBraM achieves superior performance on other state-of-the-art pretrained models, demonstrating strong generalization and transferability. These results indicate that explicitly modeling multi-scale temporal dynamics is critical for effective EEG foundation models.

Tao Zhou, Jing Han, Lingyu Shu +1

Hunan University Changsha, China

Electroencephalography Self-Supervised Pre-Training Hierarchical Representation Learning Multiscale Time-Series Modeling EEG Foundation Models

Jul 23, 2026cs.AI

Multimodal Pretraining for Generalizable EEG Representation Learning

Electroencephalography (EEG) models used for epilepsy are often limited to specific datasets and tasks. This limited approach can make it challenging to apply these models across different datasets or in various situations. However, recent studies in foundation models and self-supervised learning suggest that an adaptable EEG backbone could support a range of EEG related tasks. In this study, we have developed a multimodal EEG foundation model that combines a raw signal encoder based on the Mamba architecture, a Vision Transformer (ViT)-style encoder for time-frequency data, and a lightweight encoder for text, all within a shared embedding space. The pretraining process relies on several innovative techniques, such as masked modeling, cross-view contrastive alignment, and temporal consistency losses. These methods are designed to create rich, seizure-relevant representations without requiring labeled data. To assess the efficacy and generalization of our pretrained model, we fine-tuned it on the canonical CHB-MIT seizure detection benchmark and additional seizure detection datasets, and conducted extensive experiments comparing different model variants. On the standard CHB-MIT split, our best single model achieved an AUROC of 0.874, and an ensemble variant reached 0.878 AUROC, representing state-of-the-art performance on this benchmark. In addition to standard train-test splits, we evaluated performance under a leave-one-subject-out (LOSO) protocol, which is rarely reported in prior EEG seizure modeling work and highlights the difficulty of patient-independent seizure detection, with a mean LOSO balanced accuracy of 0.558 across 19 subjects. Across datasets and evaluation settings, our multimodal foundation model enabled robust seizure detection and straightforward adaptation to new seizure detection scenarios, while also supporting interpretable seizure localization.

Targol Bakhtiarvand, Jugal Kalita, Adham Atyabi

Department of Computer Science, University of Colorado Colorado Springs, Colorado Springs, CO, USA

Cross-Subject EEG Decoding Electroencephalography EEG Seizure Detection Self-Supervised Pre-Training Multimodal Pretraining EEG Foundation Models

Jul 22, 2026cs.CV

Self-supervision drives representational convergence in medical foundation models more than clinical supervision

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, what produces it, and whether it is clinically usable are untested, and the similarity measures behind such claims are fragile. We present a controlled dissection across 18 image and 7 text encoders, all open-weight and run locally, spanning 7M to 27B parameters and five imaging modalities, including 650,982 chest radiographs from six datasets. To isolate cause, we train encoders that vary only the objective under fixed data, architecture, and scale, and reproduce the effect in a synthetic model. Convergence is modest but above a random floor, driven by the self-supervised objective, not clinical supervision: matched self-supervised encoders aligned most (40.4% on chest radiography), with label-supervised (21.1%) and image-text (3.3%) far lower, and did not grow with size (Spearman 0.302, p=0.223) or capability. It is within-modality, does not reach clinical language, and does not reproduce how radiologists judge case similarity. Yet a linear classifier transfers across encoders and to five held-out hospitals, retaining about 85% of within-encoder performance. Convergence in medical imaging is therefore set by the pretraining objective, not inherited from scale or clinical supervision. Interoperability is accordingly something to design for through that objective, and to validate where the shared geometry is weakest, across patient subgroups and against clinical judgment.

Soroosh Tayebi Arasteh, Sebastian Ziegelmayer, Mahshad Lotfinia +4

Lab for AI in Medicine, RWTH Aachen University, Aachen, Germany · Department of Diagnostic and Interventional Radiology, University Hospital RWTH Aachen, Aachen, Germany · Department of Diagnostic and Interventional Radiology, TUM University Clinic, School of Medicine and Health, Klinikum rechts der Isar, Technical University of Munich, Munich, Germany +4

Medical Imaging Foundation Models Self-Supervised Pre-Training Medical Image Representation Learning Representation Alignment

Jul 22, 2026cs.CV

Not All Patches are Equal: Sampling Matters for Visible-Infrared Pre-Training

Visible-infrared (VIS-IR) alignment is a key pre-training task for robust multi-sensor perception. Most existing methods use uniform patch-wise contrastive learning, but this can be unreliable in VIS-IR data because imaging-physics differences make some spatially paired regions inherently less comparable, and aligning them with equal strength hinders representation learning and downstream transfer. In this paper, we revisit VIS-IR pre-training from a sampling perspective and propose Importance-Aware Sampling (IAS), which adjusts training emphasis based on patch reliability. Specifically, IAS (i) derives patch weights from infrared structural cues and uses them to reweight the contrastive objective; (ii) learns a soft importance mask with a lightweight sampler, optionally warm-started from the hand-crafted prior; and (iii) employs a patch curriculum learning strategy that gradually expands from high-reliability regions to harder patches. It is worth noting that IAS is plug-and-play and works with both patch-/correlation-level alignment (e.g., UNIV-style) and image-level contrastive baselines (e.g., ImageBind-style). Extensive experiments on multiple VIS-IR benchmarks demonstrate consistent improvements over strong baselines, including for IR semantic segmentation, IR object detection and VIS semantic segmentation and cross-modal retrieval task. Code will be released on https://github.com/KlayMa527/IAS.

Qiwei Ma, Bin Deng, Junjie Zhu +5

School of Artificial Intelligence and Robotics, Hunan University, Changsha, 410082, Hunan, China · Intelligent Game and Decision Lab, Beijing, 100166, Beijing, China · Yuelushan Center for Industrial Innovation, Changsha, 410082, Hunan, China

Visual Representation Learning Self-Supervised Pre-Training Cross-Modal Alignment Multimodal Contrastive Learning

Jul 21, 2026cs.AI

On the Effectiveness of Pretraining for Graph Combinatorial Optimization

This paper introduces a self-supervised pretraining framework for graph combinatorial optimization specifically designed to address the nature of routing problems like the Traveling Salesman Problem. By utilizing graph contrastive learning with geometric augmentations (specifically, rotations and axial reflections) the model is forced to learn invariant structural representations and global relative distance distributions. Results demonstrate that this pretraining strategy outperforms non-pretrained models across various problem scales. Notably, the hybrid strategy (combining rotation and reflection) achieved a 6.57% improvement in tour length for TSP1000, proving that geometric pretraining is an important inductive bias for effectively scaling neural solvers to high-dimensional instances.

David Aguado, Daniel Fuertes, Carlos R. del-Blanco +1

Grupo de Tratamiento de Imágenes, Information Processing and Telecomunications Center, ETSI Telecomunicación, Universidad Politécnica de Madrid, 28040, Madrid, Spain

Traveling Salesperson Problem Self-Supervised Pre-Training Combinatorial Optimization Graph Contrastive Learning Neural Combinatorial Optimization

Jul 20, 2026cs.CV

BrainNext: A General-Purpose Self-Supervised Foundation Model for Brain MRI Analysis

Foundation models pretrained using self-supervised learning have transformed computer vision by learning transferable representations from large-scale unlabeled data. However, existing foundation models for neuroimaging remain limited by task-specific training, slice-based learning strategies, or relatively small pretraining datasets, restricting their generalizability across diverse brain MRI applications. In this work, we present BrainNext, a general-purpose self-supervised foundation model for volumetric brain MRI analysis. BrainNext combines masked autoencoder (MAE) pretraining with a native three-dimensional Bi-Directional xLSTM-UNet architecture to learn rich anatomical representations from 60,551 unlabeled brain MRI examinations spanning multiple MRI modalities. The pretrained model is subsequently adapted to downstream tasks through lightweight task-specific fine-tuning. We evaluate BrainNext on the Foundation Models for Medical Imaging (FOMO) 2025 Method Track, encompassing classification, segmentation, and brain-age estimation, where it achieved second place overall and ranked first in the meningioma segmentation task on the official FOMO 2025 challenge leaderboard, demonstrating strong transferability across heterogeneous neuroimaging tasks. These results highlight the potential of large-scale self-supervised pretraining to learn robust and transferable volumetric representations, establishing BrainNext as a scalable foundation model for diverse brain MRI applications.

Moona Mazher, Abdul Qayyum, Steven A. Niederer +1

UCL Hawkes Institute, Department of Computer Science, University College London, London, United Kingdom · National Heart & Lung Institute, Imperial College London, London, United Kingdom · Division of Cardiovascular Medicine, Stanford Cardiovascular Institute, Stanford University, California, USA

Medical Imaging Foundation Models Self-Supervised Pre-Training Medical Image Representation Learning

Jul 18, 2026cs.LG

A Framework for Early Sepsis Prediction via Self-Supervised (JEPA) and Federated Representation Learning

Early sepsis prediction from electronic health records is challenged by irregular sampling, high missingness, and class imbalance. We systematically compare four modeling paradigms -- self-supervised Joint Embedding Predictive Architecture (JEPA) via masked latent prediction, self-supervised VICReg (variance-invariance-covariance regularization) with two-view augmentation, semi-supervised fine-tuning of a VICReg-pretrained encoder, and supervised Temporal Convolutional Network (TCN) -- alongside raw-feature baselines. All models share a common preprocessing pipeline of hourly binning with forward-fill imputation applied to 7 biomarkers selected via sparsity analysis from the MIMIC-III dataset. Our best model (JEPA + XGBoost + mean pooling) achieves AUPRC 0.636 at the time of onset (H0), approaching the SupMix benchmark (0.667) while using 83% fewer biomarkers. The Tier 1 pipeline -- VICReg pretraining followed by semi-supervised fine-tuning and XGBoost -- achieves AUPRC 0.510 at H0, a 3.1

\times

improvement over the raw-feature baseline (0.165) and a 7.6% improvement over the end-to-end supervised TCN (0.474). Crucially, the fine-tuned VICReg encoder exhibits the most temporally persistent representations, degrading only 16.8% from H0 to H10 compared to 47.5% for supervised TCN and 65.3% for JEPA, demonstrating that self-supervised pretraining with task-aware fine-tuning yields features that are both sharp near onset and robust across prediction horizons.

Umair bin Mansoor, Munaf Rashid, Roomi Naqvi

Electrical Engg. Department, DHA Suffa University, Karachi, Pakistan · Salim Habib University, Karachi, Sindh, Pakistan · Intel Foundry Services, Intel, Tempe, Arizona, United States

Self-Supervised Pre-Training Joint-Embedding Predictive Architecture Clinical Prediction Longitudinal EHR Modeling Electronic Health Records Clinical Risk Prediction

Jul 16, 2026cs.CV

Multimodality as Supervision: Self-Supervised Specialization to the Test Environment via Multimodality

Cross-modal learning, i.e., learning to predict one modality from another, is a fundamental mechanism for self-supervision via leveraging multimodality. Many practical applications, e.g., deploying a household robot, involve devices that are equipped with a rich set of sensors that enable multimodal sensing in their test environment. This presents an opportunity to apply cross-modal learning to the multimodal data sensed by these devices to learn representations. Findings in developmental psychology also suggest that biological agents leverage it to build an effective representation of their surroundings. To study this, we propose a controlled setup, where we restrict a user device to just a given test environment. It results in a specialization setup where we attempt to develop a performant model for this specific test environment. Under this setup, we develop Test-Space Training (TST), which performs multimodal data collection in the test environment and performs self-supervised pre-training on it. We evaluate these models on various downstream tasks in the same environment. Under this setup, we find various interesting insights, such as collecting rich multimodal data only from the test environment and leveraging cross-modal learning, we can achieve competitive results with generalist models (e.g., DINOv2 and CLIP) pre-trained on large-scale internet datasets. This enables an alternative scenario where the need for external Internet-scale datasets for pre-training models is reduced. We also present a set of analyses and ablations that raise intriguing points on substituting data with (multi)modality, and how varying pre-training data enables a tradeoff between a model's abilities to specialise to a test environment, and generalize to held-out spaces.

Kunal Pratap Singh, Ali Garjani, Rishubh Singh +6

Swiss Federal Institute of Technology Lausanne (EPFL) · Apple

Cross-Modal Learning Cross-Modal Representation Learning Self-Supervised Pre-Training Multimodal Pretraining Domain-Adaptive Pretraining

Jul 16, 2026cs.SD

MIDI-RAE-JEPA: Hierarchical Representation Learning and Generation for Symbolic Music

Rich internal representations of musical structure are essential for music understanding tasks such as machine-assisted music co-writing, yet self-supervised approaches for symbolic music representation remain underexplored, particularly those that encode the hierarchical multiscale nature of musical structures. We present MIDI-RAE-JEPA, combining a pitch- and time-shift equivariance objective with LeJEPA and a Swin Transformer V2 encoder to learn such hierarchical representations of symbolic music encoded as piano roll images. The time-shift equivariance objective encourages the model to internalize temporal musical relationships. The encoder is trained purely on self-supervised objectives -- including a masked embedding predictor (MEP) -- with collapse prevented via SIGReg. A separate decoder trained on the frozen encoder embeddings achieves reconstruction F1 of 0.995, and a flow matching generative model conditioned on those embeddings produces generations that closely match the pitch register and rhythmic density of the conditioning excerpt, while mismatched conditioning yields unrelated but musically plausible output. Learned representations outperform a Haar scattering transform baseline on a downstream emotion classification task, and embedding distances increase monotonically with pitch and time shift magnitude, confirming measurable equivariance. These results suggest that equivariance-based SSL objectives, combined with sufficient fine-level encoder capacity, provide a viable path toward semantically rich, generatively useful representations of symbolic music.

Scott H. Hawley

Department of Chemistry & Physics, Belmont University, Nashville, TN, USA

Representation Learning Self-Supervised Pre-Training Symbolic Music Generation Hierarchical Representation Learning Equivariant Representation Learning

Jul 15, 2026cs.LG

Leveraging unlabelled data for generalizable neural population decoding

Robust and accurate neural decoders are integral to neurotechnologies such as brain-computer interfaces and closed-loop experiments. Recent work has shown that tokenizing neural data at the spike level facilitates multi-session pretraining and delivers state-of-the-art decoding performance. However, current spike-based models are restricted to supervised learning (SL), limiting training to datasets with paired behavioural labels. To address this limitation, we introduce MOJO (Masked autOencoder-based JOint training), a training framework for spike-tokenizing models that jointly leverages self-supervised learning (SSL) via masked autoencoding and SL objectives. We evaluate MOJO on three spiking datasets spanning monkey motor cortex during reaching tasks and multi-regional mouse recordings during vision and decision making tasks, demonstrating superior performance over purely SL-trained models. This improvement is especially pronounced when training with limited labelled data, particularly in few-shot finetuning, where only a small amount of labelled data from a new session is available. Incorporating SSL also yields more interpretable neuronal representations, improving performance on brain region classification and spike-statistics prediction without explicit optimization for these tasks. We further show that MOJO generalizes beyond spiking data to human electrocorticography during speech, where it continues to outperform purely SL-trained models and achieves performance comparable to neuro-foundation models (NFMs) designed specifically for continuous signals. Overall, augmenting spike-tokenizing models with SSL improves performance in label-impoverished settings and enables the use of unlabelled data across various tasks and species, while generalizing to other neural modalities. These results suggest a path towards more flexible and scalable data usage when training NFMs.

Ximeng Mao, Nanda H. Krishna, Avery Hee-Woon Ryoo +2

Mila – Quebec AI Institute · Université de Montréal · Canada CIFAR AI Chair

Masked Autoencoders Self-Supervised Pre-Training Neural Decoding

Jul 13, 2026cs.CV

Self-supervised training for high-resolution close-range multispectral remote sensing imagery

Although self-supervised learning (SSL) offers a promising way to reduce annotation effort in close-range remote sensing, its effectiveness for high-resolution multispectral unmanned aerial vehicle (UAV) imagery remains underexplored due to limited data. This study evaluated SSL pretraining for precision agriculture using cm-scale multispectral drone imagery collected across multiple sensors, years, and regions. Transformer-based encoders were pretrained with Momentum Contrast v3 (MoCo-v3) and Masked Autoencoders on a harmonized dataset combining msuav500K with newly collected multi-year UAV imagery from agricultural fields in Finland. Pretraining used four spectral bands (Green, Red, Red-Edge, Near-Infrared) for cross-sensor compatibility. The models were evaluated on crop-weed semantic segmentation using the WeedMap dataset with 5--100% training data. The following two subsets served as downstream tasks: Task A (Germany, RedEdge-M), where all pretrained models were compared under partial and full fine-tuning, and Task B (Switzerland, Sequoia), where the best encoder from Task A was assessed. Our Swin Transformer pretrained with MoCo-v3 achieved the strongest performance on both tasks, surpassing the Swin Transformer model of Doornbos et al. pretrained on a pre-release of msuav500K. Our pretrained Swin Transformer further demonstrated cross-sensor and cross-region generalization. We additionally provide a public multi-year multispectral UAV dataset from Finland to support future research.

Leon-Friedrich Thomas, Mikael Änäkkälä, Antti Lajunen

University of Helsinki, Department of Agricultural Sciences, P.O. Box 28, Fi-00014 Helsinki, Finland · University of Helsinki, Department of Forest Sciences, P.O. Box 27, Fi-00014 Helsinki, Finland

Agricultural Image Analysis Remote Sensing Image Segmentation Agricultural Remote Sensing Self-Supervised Pre-Training UAV Remote Sensing

Jul 10, 2026cs.CV

Scalable Visual Pretraining for Language Intelligence

The rapid progress of large foundation models has been driven predominantly by pretraining on large-scale text corpora. However, many forms of knowledge are conveyed through visual representations, where figures, typeset equations, and page layouts carry rich information that cannot be faithfully or completely captured by text alone. Yet current pretraining approaches discard these visual cues by converting visually rich sources, such as documents and web pages, into plain text for learning language intelligence. This paper challenges the default assumption that language models must be trained on text-only representations and shows that Visual Pretraining is a scalable learner for foundation model intelligence. To this end, we conduct a systematic study of unsupervised visual pretraining paradigms that directly leverage visual documents without text extraction. Across multiple backbones and benchmarks, visual pretraining on the same underlying corpora consistently outperforms text-only pretraining, offering an efficient pathway to scalable language intelligence.

Yiming Zhang, Zhonghan Zhao, Wenwei Zhang +13

Shanghai Artificial Intelligence Laboratory · University of Science and Technology of China · Zhejiang University +1

Language Model Pretraining Self-Supervised Pre-Training

Jul 10, 2026cs.LG

CoCoT-EEG: Contrastive-Pretrained Multiscale Convolutional Transformer for EEG Decoding

Self-supervised pretrained foundation models (FM) have shown early promise for non-invasive electroencephalogram (EEG) decoding applications. Many recent large-scale models converged on the approach of tokenizing raw EEG followed by masked reconstruction pretraining. However, this recipe has been shown to be suboptimal for data, like EEG, with high noise amplitude and information confined to limited dimensions such as narrow frequency bands. Building on this insight, we develop a novel contrastive-pretrained EEG model with multiscale temporal convolution input layers and Transformer encoder blocks (CoCoT). CoCoT matches or beats state-of-the-art reconstruction-pretrained EEG models on extensive benchmark decoding tasks with heterogeneous electrode configurations. Furthermore, CoCoT trained from scratch outperforms previous single-task decoding models and even rivals pretrained models, showcasing the architecture's flexibility and data efficiency. Through systematic ablations, including model architecture and pretraining objective, we demonstrate the viability of contrastive learning for building EEG FMs while suggesting key architectural design considerations, prompting further investigations in alternative large-scale pretraining strategies.

Gabriel Mahuas, Victoria Shevchenko, Ugo Tanielian +2

Sigma Nova Paris, France · Goethe University Frankfurt Frankfurt, Germany

Contrastive Learning Hybrid CNN-Transformer Architectures Self-Supervised Pre-Training EEG Decoding EEG Foundation Models

Jul 9, 2026cs.LG

JEPA for AI-Native 6G: Predictive Representations and Open Challenges

Sixth-generation (6G) networks are moving toward AI-native operation, where learning modules are embedded across the radio access network (RAN), edge, and core. This transition requires learning from limited labels, heterogeneous wireless and network data, partial observations, non-stationary propagation, and latency-constrained control loops. Joint-embedding predictive architecture (JEPA) is a promising self-supervised paradigm for this setting because it predicts missing or future representations in latent space instead of reconstructing raw measurements or using contrastive negative samples. This article presents a wireless-oriented tutorial on JEPA for 6G intelligence. We define the JEPA training mechanism, describe how CSI, beam measurements, KPIs, topology graphs, and sensing observations can be tokenized and masked, and position the learned encoder as a predictive representation layer for RAN, O-RAN, edge, and core functions, with task-specific heads or controllers producing final decisions. Then we present an illustrative, beam-management case study suggesting that a wireless-aware target, specifically an auxiliary future beam-energy target during self-supervised pretraining, can improve label efficiency and robustness across shifted deployment conditions relative to a supervised source domain. Finally, we outline open challenges in multi-timescale prediction, action-conditioned modeling, distributed training, trustworthiness, efficient deployment, benchmarking, and standardization.

Sheikh Salman Hassan, Irshad A. Meer, Almoatssimbillah Saifaldawla +9

IDCoM, University of Edinburgh, Edinburgh EH9 3BF, UK · KTH Royal Institute of Technology, SE-100 44 Stockholm, Sweden · SnT, University of Luxembourg, L-1855 Luxembourg +6

6G Networks Self-Supervised Pre-Training Joint-Embedding Predictive Architecture Wireless Communications Predictive Representation Learning

Jul 8, 2026cs.CV

Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence

Despite the recent promise in robot control, video generative models suffer from a domain mismatch due to their primary focus on content creation. For example, their design inherently prioritizes visual fidelity and creativity over computational efficiency and physical realism. In this work, we present LingBot-Video, a DiT-based video pretraining paradigm specifically tailored for embodied intelligence. From the architecture perspective, we adopt the Mixture-of-Experts (MoE), instead of dense, framework to achieve a better trade-off between modeling capacity and inference efficiency, and manage to scale it up from scratch. From the data perspective, we construct a data profiling engine that augments standard internet videos with extensive robot-oriented footage, encompassing manipulation, navigation, and egocentric perspectives, to equip the base model with an intrinsic understanding of actions and world dynamics. From the training perspective, we develop a multi-dimensional reward system to enforce the alignment regarding physical rationality and task completion, going beyond standard criteria such as aesthetics, prompt-following, and motion consistency. Comprehensive evaluations validate its performance and efficiency as a video foundation model. We contribute LingBot-Video as the inaugural large-scale, open-source MoE video foundation model to the community, in a pioneering effort to bridge digital creativity and physical actuation.

Shuailei Ma, Jiaqi Liao, Xinyang Wang +24

Video Diffusion Models Self-Supervised Pre-Training Video Generation Mixture-of-Experts Models